Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Richie
|
748894f99f |
@@ -1,28 +0,0 @@
|
||||
.git
|
||||
.direnv
|
||||
.mypy_cache
|
||||
.pytest_cache
|
||||
.ruff_cache
|
||||
.venv
|
||||
**/.venv
|
||||
.env
|
||||
.cache
|
||||
.claude
|
||||
.coverage
|
||||
.vscode
|
||||
.stfolder
|
||||
.literotica_data
|
||||
esphome
|
||||
htmlcov
|
||||
data
|
||||
ebooks
|
||||
__pycache__
|
||||
**/__pycache__
|
||||
*.pyc
|
||||
*.pyo
|
||||
.ebook_search_bm25
|
||||
result
|
||||
result-*
|
||||
*.egg-info
|
||||
dist
|
||||
build
|
||||
@@ -4,8 +4,6 @@ on:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [main]
|
||||
schedule:
|
||||
- cron: "0 22 * * *"
|
||||
|
||||
jobs:
|
||||
build:
|
||||
@@ -15,13 +13,13 @@ jobs:
|
||||
matrix:
|
||||
system:
|
||||
- "bob"
|
||||
- "brain"
|
||||
- "jeeves"
|
||||
- "rhapsody-in-green"
|
||||
continue-on-error: true
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Build default package
|
||||
run: "nixos-rebuild build --accept-flake-config --flake ./#${{ matrix.system }}"
|
||||
run: "nixos-rebuild build --flake ./#${{ matrix.system }}"
|
||||
- name: copy to nix-cache
|
||||
run: nix copy --accept-flake-config --to unix:///host-nix/var/nix/daemon-socket/socket .#nixosConfigurations.${{ matrix.system }}.config.system.build.toplevel
|
||||
env:
|
||||
NIX_SSHOPTS: "-vvvv"
|
||||
run: nix copy --to ssh://jeeves .#nixosConfigurations.${{ matrix.system }}.config.system.build.toplevel
|
||||
|
||||
@@ -1,23 +0,0 @@
|
||||
name: merge_flake_lock_update
|
||||
on:
|
||||
workflow_dispatch:
|
||||
schedule:
|
||||
- cron: "0 2 * * 6"
|
||||
|
||||
jobs:
|
||||
merge:
|
||||
runs-on: self-hosted
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: write
|
||||
|
||||
steps:
|
||||
- name: merge_flake_lock_update
|
||||
run: >-
|
||||
nix develop .#devShells.x86_64-linux.default -c
|
||||
python -m python.gitea_flake_lock merge
|
||||
--repo "${{ github.repository }}"
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
GITEA_URL: https://gitea.tmmworkshop.com
|
||||
@@ -1,19 +0,0 @@
|
||||
name: pytest
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
branches:
|
||||
- main
|
||||
|
||||
jobs:
|
||||
pytest:
|
||||
runs-on: self-hosted
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Run tests
|
||||
run: nix develop .#devShells.x86_64-linux.default -c pytest tests
|
||||
@@ -1,26 +0,0 @@
|
||||
name: test ebook search
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
branches:
|
||||
- main
|
||||
|
||||
env:
|
||||
UV_PYTHON_DOWNLOADS: never
|
||||
UV_CACHE_DIR: /var/cache/uv
|
||||
UV_LINK_MODE: copy
|
||||
|
||||
jobs:
|
||||
test-ebook-search:
|
||||
runs-on: self-hosted
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Install dependencies
|
||||
run: nix develop .#devShells.x86_64-linux.ebook-search -c uv sync --locked --project python/ebook_search/docker
|
||||
- name: Run ebook search tests
|
||||
run: nix develop .#devShells.x86_64-linux.ebook-search -c uv run --project python/ebook_search/docker --no-sync pytest tests/ebook_search --override-ini addopts="-n auto -ra"
|
||||
@@ -1,15 +0,0 @@
|
||||
name: treefmt
|
||||
on:
|
||||
workflow_dispatch:
|
||||
pull_request:
|
||||
push:
|
||||
branches: [main]
|
||||
|
||||
jobs:
|
||||
treefmt:
|
||||
name: nix fmt
|
||||
runs-on: self-hosted
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: runs treefmt
|
||||
run: "treefmt --ci"
|
||||
@@ -2,25 +2,21 @@ name: update-flake-lock
|
||||
on:
|
||||
workflow_dispatch:
|
||||
schedule:
|
||||
- cron: "0 0 * * 6"
|
||||
- cron: "0 0 * * *"
|
||||
|
||||
jobs:
|
||||
lockfile:
|
||||
runs-on: self-hosted
|
||||
permissions:
|
||||
actions: write
|
||||
contents: write
|
||||
pull-requests: write
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
- name: Install Nix
|
||||
uses: DeterminateSystems/nix-installer-action@main
|
||||
- name: Update flake.lock
|
||||
run: nix flake update
|
||||
- name: Create or update flake.lock PR
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
GITEA_URL: https://gitea.tmmworkshop.com
|
||||
run: >-
|
||||
nix develop .#devShells.x86_64-linux.default -c
|
||||
python -m python.gitea_flake_lock update
|
||||
--repo "${{ github.repository }}"
|
||||
uses: DeterminateSystems/update-flake-lock@main
|
||||
with:
|
||||
token: ${{ secrets.GH_TOKEN_FOR_UPDATES }}
|
||||
pr-title: "Update flake.lock"
|
||||
pr-labels: |
|
||||
dependencies
|
||||
automated
|
||||
|
||||
-11
@@ -165,14 +165,3 @@ test.*
|
||||
|
||||
# syncthing
|
||||
.stfolder
|
||||
|
||||
# Frontend build output
|
||||
frontend/dist/
|
||||
frontend/node_modules/
|
||||
|
||||
# data from testing llms
|
||||
data/*
|
||||
.ebook_search_bm25
|
||||
|
||||
# gems data
|
||||
.gems
|
||||
|
||||
+6
-9
@@ -1,13 +1,10 @@
|
||||
# Generate AGE keys from SSH keys with:
|
||||
# ssh-keygen -A
|
||||
# nix-shell -p ssh-to-age --run 'cat /etc/ssh/ssh_host_ed25519_key.pub | ssh-to-age'
|
||||
keys:
|
||||
- &admin_richie age1u8zj599elqqvcmhxn8zuwrufsz8w8w366d3ayrljjejljt2q45kq8mxw9c # cspell:disable-line
|
||||
- &admin_richie age1u8zj599elqqvcmhxn8zuwrufsz8w8w366d3ayrljjejljt2q45kq8mxw9c
|
||||
|
||||
- &system_bob age1q47vup0tjhulkg7d6xwmdsgrw64h4ax3la3evzqpxyy4adsmk9fs56qz3y # cspell:disable-line
|
||||
- &system_brain age1jhf7vm0005j60mjq63696frrmjhpy8kpc2d66mw044lqap5mjv4snmwvwm # cspell:disable-line
|
||||
- &system_jeeves age13lmqgc3jvkyah5e3vcwmj4s5wsc2akctcga0lpc0x8v8du3fxprqp4ldkv # cspell:disable-line
|
||||
- &system_rhapsody age1ufnewppysaq2wwcl4ugngjz8pfzc5a35yg7luq0qmuqvctajcycs5lf6k4 # cspell:disable-line
|
||||
- &system_bob age1q47vup0tjhulkg7d6xwmdsgrw64h4ax3la3evzqpxyy4adsmk9fs56qz3y
|
||||
- &system_jeeves age13lmqgc3jvkyah5e3vcwmj4s5wsc2akctcga0lpc0x8v8du3fxprqp4ldkv
|
||||
- &system_router age1xzxryqq63x65yuza9lmmkud7crjjxpnkdew070yhx6xn7xe4tdws5twxsv
|
||||
- &system_rhapsody age1ufnewppysaq2wwcl4ugngjz8pfzc5a35yg7luq0qmuqvctajcycs5lf6k4
|
||||
|
||||
creation_rules:
|
||||
- path_regex: users/secrets\.yaml$
|
||||
@@ -15,6 +12,6 @@ creation_rules:
|
||||
- age:
|
||||
- *admin_richie
|
||||
- *system_bob
|
||||
- *system_brain
|
||||
- *system_jeeves
|
||||
- *system_router
|
||||
- *system_rhapsody
|
||||
|
||||
Vendored
+10
-83
@@ -2,7 +2,6 @@
|
||||
"cSpell.words": [
|
||||
"aboutwelcome",
|
||||
"acltype",
|
||||
"addopts",
|
||||
"addstr",
|
||||
"advplyr",
|
||||
"ahci",
|
||||
@@ -10,7 +9,6 @@
|
||||
"aiounifi",
|
||||
"alsa",
|
||||
"apiclient",
|
||||
"apscheduler",
|
||||
"archlinux",
|
||||
"ashift",
|
||||
"asrouter",
|
||||
@@ -28,7 +26,6 @@
|
||||
"azuretools",
|
||||
"bantime",
|
||||
"bazarr",
|
||||
"bgwriter",
|
||||
"binhex",
|
||||
"bitwarden",
|
||||
"blkdiscard",
|
||||
@@ -39,26 +36,20 @@
|
||||
"captivedetect",
|
||||
"cgroupdriver",
|
||||
"charliermarsh",
|
||||
"Checkpointing",
|
||||
"codellama",
|
||||
"cloudflared",
|
||||
"codezombiech",
|
||||
"compactmode",
|
||||
"Compat",
|
||||
"contentblocking",
|
||||
"cookiebanners",
|
||||
"createdb",
|
||||
"createrole",
|
||||
"crlite",
|
||||
"cryptsetup",
|
||||
"cuda",
|
||||
"darkreader",
|
||||
"datagrip",
|
||||
"datareporting",
|
||||
"davidanson",
|
||||
"dconf",
|
||||
"dearrow",
|
||||
"debugpy",
|
||||
"deepseek",
|
||||
"dialout",
|
||||
"diffie",
|
||||
"direnv",
|
||||
@@ -66,29 +57,23 @@
|
||||
"dnodesize",
|
||||
"dotfiles",
|
||||
"drawio",
|
||||
"duckdns",
|
||||
"eamodio",
|
||||
"ehci",
|
||||
"emerg",
|
||||
"endlessh",
|
||||
"ents",
|
||||
"errorlens",
|
||||
"esbenp",
|
||||
"esphome",
|
||||
"extest",
|
||||
"fadvise",
|
||||
"fastfetch",
|
||||
"fastforwardteam",
|
||||
"FASTFOX",
|
||||
"ffmpegthumbnailer",
|
||||
"filebot",
|
||||
"filebrowser",
|
||||
"fileroller",
|
||||
"findbar",
|
||||
"Fira",
|
||||
"fmask",
|
||||
"fontconfig",
|
||||
"formfill",
|
||||
"forwardfor",
|
||||
"foxundermoon",
|
||||
"FULLSCREEN",
|
||||
"fwupd",
|
||||
@@ -98,7 +83,6 @@
|
||||
"getch",
|
||||
"getmaxyx",
|
||||
"ghdeploy",
|
||||
"gitea",
|
||||
"globalprivacycontrol",
|
||||
"gparted",
|
||||
"gtts",
|
||||
@@ -114,12 +98,8 @@
|
||||
"HPKP",
|
||||
"hplip",
|
||||
"htmlaboutaddons",
|
||||
"httpchk",
|
||||
"hurlenko",
|
||||
"hwloc",
|
||||
"ical",
|
||||
"ignorelist",
|
||||
"improv",
|
||||
"INITDB",
|
||||
"iocharset",
|
||||
"ioit",
|
||||
@@ -129,10 +109,7 @@
|
||||
"jnoortheen",
|
||||
"jsbc",
|
||||
"kagi",
|
||||
"keyformat",
|
||||
"keylocation",
|
||||
"kuma",
|
||||
"lazer",
|
||||
"levelname",
|
||||
"libglvnd",
|
||||
"libmysqlclient",
|
||||
@@ -147,58 +124,43 @@
|
||||
"lynis",
|
||||
"mangohud",
|
||||
"markdownlint",
|
||||
"maxconn",
|
||||
"maxpages",
|
||||
"maxretry",
|
||||
"maxtime",
|
||||
"mechatroner",
|
||||
"mediainfo",
|
||||
"mixtral",
|
||||
"microvm",
|
||||
"mklabel",
|
||||
"mkpart",
|
||||
"modbus",
|
||||
"modbuss",
|
||||
"modesetting",
|
||||
"mountpoint",
|
||||
"mountpoints",
|
||||
"mousewheel",
|
||||
"mqtt",
|
||||
"mtxr",
|
||||
"mypy",
|
||||
"ncdu",
|
||||
"nemo",
|
||||
"neofetch",
|
||||
"nerdfonts",
|
||||
"netdev",
|
||||
"netdevs",
|
||||
"Networkd",
|
||||
"networkmanager",
|
||||
"newtabpage",
|
||||
"ngram",
|
||||
"ngrams",
|
||||
"nixfmt",
|
||||
"nixos",
|
||||
"nixpkgs",
|
||||
"nmap",
|
||||
"noauto",
|
||||
"nodev",
|
||||
"noecho",
|
||||
"nonsponsored",
|
||||
"Noto",
|
||||
"nprt",
|
||||
"nvme",
|
||||
"OCSP",
|
||||
"oderwat",
|
||||
"ollama",
|
||||
"ondemand",
|
||||
"oneshot",
|
||||
"openwakeword",
|
||||
"optimise",
|
||||
"optoutstudies",
|
||||
"overalljails",
|
||||
"overscroll",
|
||||
"overseerr",
|
||||
"paho",
|
||||
"partitionwise",
|
||||
"pbmode",
|
||||
"pciutils",
|
||||
"pcscd",
|
||||
@@ -206,18 +168,15 @@
|
||||
"peerconnection",
|
||||
"PESKYFOX",
|
||||
"PGID",
|
||||
"pgvector",
|
||||
"pipewire",
|
||||
"pkgs",
|
||||
"plugdev",
|
||||
"poppler",
|
||||
"posixacl",
|
||||
"powertop",
|
||||
"primarycache",
|
||||
"prismlauncher",
|
||||
"privatebrowsing",
|
||||
"PRIVOXY",
|
||||
"protontricks",
|
||||
"prowlarr",
|
||||
"proxychains",
|
||||
"prusa",
|
||||
@@ -226,29 +185,23 @@
|
||||
"pulseaudio",
|
||||
"punycode",
|
||||
"pychromecast",
|
||||
"pydocstyle",
|
||||
"pyfakefs",
|
||||
"pylance",
|
||||
"pylint",
|
||||
"pymetno",
|
||||
"pymodbus",
|
||||
"pyopenweathermap",
|
||||
"pyownet",
|
||||
"pytest",
|
||||
"qalculate",
|
||||
"qbit",
|
||||
"qbittorrent",
|
||||
"qbittorrentvpn",
|
||||
"qbitvpn",
|
||||
"quicksuggest",
|
||||
"radarr",
|
||||
"readahead",
|
||||
"receiveencrypted",
|
||||
"recordsize",
|
||||
"Redistributable",
|
||||
"referer",
|
||||
"REFERERS",
|
||||
"relatime",
|
||||
"rerank",
|
||||
"Rhosts",
|
||||
"ripgrep",
|
||||
"roboto",
|
||||
"rokuecp",
|
||||
"routable",
|
||||
"rspace",
|
||||
@@ -258,10 +211,8 @@
|
||||
"schemeless",
|
||||
"scrollback",
|
||||
"SECUREFOX",
|
||||
"sessionmaker",
|
||||
"sessionstore",
|
||||
"shellcheck",
|
||||
"signalbot",
|
||||
"signon",
|
||||
"Signons",
|
||||
"skia",
|
||||
@@ -271,7 +222,6 @@
|
||||
"socialtracking",
|
||||
"sonarr",
|
||||
"sponsorblock",
|
||||
"sqlalchemy",
|
||||
"sqltools",
|
||||
"ssdp",
|
||||
"SSHOPTS",
|
||||
@@ -282,30 +232,20 @@
|
||||
"sysstat",
|
||||
"tabmanager",
|
||||
"tamasfe",
|
||||
"TCPIP",
|
||||
"testdisk",
|
||||
"tiktok",
|
||||
"timonwong",
|
||||
"titlebar",
|
||||
"tmmworkshop",
|
||||
"Tmpfs",
|
||||
"topsites",
|
||||
"topstories",
|
||||
"treefmt",
|
||||
"torrenting",
|
||||
"twimg",
|
||||
"typedmonarchmoney",
|
||||
"typer",
|
||||
"uaccess",
|
||||
"ubiquiti",
|
||||
"ublock",
|
||||
"uiprotect",
|
||||
"uitour",
|
||||
"unifi",
|
||||
"unjudged",
|
||||
"unrar",
|
||||
"unstorable",
|
||||
"unsubmitted",
|
||||
"uptimekuma",
|
||||
"urlbar",
|
||||
"urlclassifier",
|
||||
"usbhid",
|
||||
@@ -313,25 +253,17 @@
|
||||
"useragent",
|
||||
"usernamehw",
|
||||
"userprefs",
|
||||
"vaninventory",
|
||||
"vdev",
|
||||
"vfat",
|
||||
"victron",
|
||||
"virt",
|
||||
"virtualisation",
|
||||
"vpnpromourl",
|
||||
"wakeonlan",
|
||||
"webchannel",
|
||||
"WEBRTC",
|
||||
"WEBUI",
|
||||
"wireplumber",
|
||||
"wireshark",
|
||||
"Workqueues",
|
||||
"xattr",
|
||||
"xcursorgen",
|
||||
"xdist",
|
||||
"xhci",
|
||||
"yake",
|
||||
"yazi",
|
||||
"yubikey",
|
||||
"yubioath",
|
||||
@@ -342,10 +274,5 @@
|
||||
"zoxide",
|
||||
"zram",
|
||||
"zstd"
|
||||
],
|
||||
"python-envs.defaultEnvManager": "ms-python.python:system",
|
||||
"python-envs.pythonProjects": [],
|
||||
"python.testing.pytestArgs": ["tests"],
|
||||
"python.testing.unittestEnabled": false,
|
||||
"python.testing.pytestEnabled": true
|
||||
]
|
||||
}
|
||||
|
||||
@@ -1,51 +1 @@
|
||||
# dotfiles
|
||||
|
||||
## Installer ISO
|
||||
|
||||
Build a bootable NixOS ISO with the installer preinstalled:
|
||||
|
||||
```sh
|
||||
nix build .#iso
|
||||
```
|
||||
|
||||
Write `result/iso/nixos-zfs-installer.iso` to a USB stick (for example with `dd`) or boot it in a VM. The image is the minimal NixOS installation CD with ZFS enabled and `nixos-installer` on `PATH`. SSH is enabled and the `nixos` and `root` accounts use the password `nixos`, so you can also run the installer remotely. Once booted:
|
||||
|
||||
```sh
|
||||
sudo nixos-installer
|
||||
```
|
||||
|
||||
The ISO bundles the `.#installer-nixos` package, a variant of the binary that keeps its Nix store linkage instead of being patched for foreign distributions.
|
||||
|
||||
## Installer binary
|
||||
|
||||
Build the self-contained installer executable with:
|
||||
|
||||
```sh
|
||||
nix build .#installer
|
||||
```
|
||||
|
||||
The flake package (defined in `python/installer/package.nix`) uses the Python builder in `python/installer/build.py`, which stages only the installer modules before running PyInstaller. You can also call it directly when `pyinstaller` and `patchelf` are on `PATH`:
|
||||
|
||||
```sh
|
||||
python -m python.installer.build --output ./nixos-installer
|
||||
```
|
||||
|
||||
Copy `result/bin/nixos-installer` to the installer USB stick and run it as root from the NixOS live environment:
|
||||
|
||||
```sh
|
||||
sudo ./nixos-installer
|
||||
```
|
||||
|
||||
Validate the live environment first with:
|
||||
|
||||
```sh
|
||||
./nixos-installer --check
|
||||
```
|
||||
|
||||
Paste a value into the TUI encryption password field to enable LUKS during install, or set `ENCRYPT_KEY`:
|
||||
|
||||
```sh
|
||||
sudo env ENCRYPT_KEY='change-me' ./nixos-installer
|
||||
```
|
||||
|
||||
The binary bundles the Python runtime and only the installer modules it imports. It still expects the NixOS installer environment to provide system install tools such as `parted`, `zfs`, `zpool`, `cryptsetup`, `nixos-generate-config`, and `nixos-install`.
|
||||
|
||||
@@ -23,10 +23,7 @@
|
||||
boot = {
|
||||
tmp.useTmpfs = true;
|
||||
kernelPackages = lib.mkDefault pkgs.linuxPackages_6_12;
|
||||
zfs = {
|
||||
package = lib.mkDefault pkgs.zfs_2_4;
|
||||
forceImportRoot = lib.mkDefault false;
|
||||
};
|
||||
zfs.package = lib.mkDefault pkgs.zfs_2_3;
|
||||
};
|
||||
|
||||
hardware.enableRedistributableFirmware = true;
|
||||
@@ -34,30 +31,20 @@
|
||||
home-manager = {
|
||||
useGlobalPkgs = true;
|
||||
useUserPackages = true;
|
||||
extraSpecialArgs = { inherit inputs outputs; };
|
||||
extraSpecialArgs = {inherit inputs outputs;};
|
||||
backupFileExtension = "backup";
|
||||
};
|
||||
|
||||
nixpkgs = {
|
||||
overlays = builtins.attrValues outputs.overlays;
|
||||
config = {
|
||||
allowUnfree = true;
|
||||
permittedInsecurePackages = [
|
||||
"openssl-1.1.1w" # This is for discord-canary
|
||||
];
|
||||
};
|
||||
config.allowUnfree = true;
|
||||
};
|
||||
|
||||
services = {
|
||||
dbus.implementation = "dbus";
|
||||
|
||||
# firmware update
|
||||
fwupd.enable = true;
|
||||
|
||||
snapshot_manager = {
|
||||
enable = lib.mkDefault true;
|
||||
PYTHONPATH = "${inputs.self}/";
|
||||
};
|
||||
snapshot_manager.enable = lib.mkDefault true;
|
||||
|
||||
zfs = {
|
||||
trim.enable = lib.mkDefault true;
|
||||
@@ -65,18 +52,9 @@
|
||||
};
|
||||
};
|
||||
|
||||
powerManagement.powertop.enable = lib.mkDefault true;
|
||||
|
||||
programs.zsh.enable = true;
|
||||
|
||||
security = {
|
||||
auditd.enable = lib.mkDefault true;
|
||||
sudo-rs = {
|
||||
enable = true;
|
||||
execWheelOnly = true;
|
||||
};
|
||||
sudo.enable = false;
|
||||
};
|
||||
security.auditd.enable = lib.mkDefault true;
|
||||
|
||||
users.mutableUsers = lib.mkDefault false;
|
||||
|
||||
|
||||
@@ -1,10 +1,4 @@
|
||||
{ lib, pkgs, ... }:
|
||||
let
|
||||
libPath = pkgs.lib.makeLibraryPath [
|
||||
pkgs.zlib
|
||||
pkgs.stdenv.cc.cc.lib
|
||||
];
|
||||
in
|
||||
{
|
||||
programs.nix-ld = {
|
||||
enable = lib.mkDefault true;
|
||||
@@ -21,7 +15,6 @@ in
|
||||
libxml2
|
||||
openssl
|
||||
stdenv.cc.cc
|
||||
stdenv.cc.cc.lib
|
||||
systemd
|
||||
util-linux
|
||||
xz
|
||||
@@ -30,9 +23,4 @@ in
|
||||
zstd
|
||||
];
|
||||
};
|
||||
|
||||
environment = {
|
||||
sessionVariables.LD_LIBRARY_PATH = lib.mkDefault libPath;
|
||||
variables.LD_LIBRARY_PATH = lib.mkDefault libPath;
|
||||
};
|
||||
}
|
||||
|
||||
@@ -4,7 +4,8 @@
|
||||
console.keyMap = lib.mkDefault "us";
|
||||
|
||||
i18n = {
|
||||
defaultLocale = lib.mkDefault "en_US.UTF-8";
|
||||
defaultLocale = lib.mkDefault "en_US.utf8";
|
||||
supportedLocales = lib.mkDefault [ "en_US.UTF-8/UTF-8" ];
|
||||
extraLocaleSettings = lib.mkDefault {
|
||||
LC_ADDRESS = "en_US.UTF-8";
|
||||
LC_IDENTIFICATION = "en_US.UTF-8";
|
||||
|
||||
@@ -2,11 +2,9 @@
|
||||
inputs,
|
||||
lib,
|
||||
...
|
||||
}:
|
||||
let
|
||||
}: let
|
||||
flakeInputs = lib.filterAttrs (_: lib.isType "flake") inputs;
|
||||
in
|
||||
{
|
||||
in {
|
||||
nix = {
|
||||
settings = {
|
||||
trusted-users = [
|
||||
@@ -15,14 +13,17 @@ in
|
||||
];
|
||||
trusted-substituters = [
|
||||
"https://cache.nixos.org"
|
||||
"https://cache.tmmworkshop.com"
|
||||
"https://nix-community.cachix.org"
|
||||
];
|
||||
substituters = [
|
||||
"https://cache.nixos.org/?priority=2&want-mass-query=true"
|
||||
"https://cache.tmmworkshop.com/?priority=2&want-mass-query=true"
|
||||
"https://nix-community.cachix.org/?priority=10&want-mass-query=true"
|
||||
];
|
||||
trusted-public-keys = [
|
||||
"cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY="
|
||||
"cache.tmmworkshop.com:jHffkpgbmEdstQPoihJPYW9TQe6jnQbWR2LqkNGV3iA="
|
||||
"nix-community.cachix.org-1:mB9FSh9qf2dCimDSUo8Zy7bkq5CX+/rkCWyvRCYg3Fs="
|
||||
];
|
||||
auto-optimise-store = lib.mkDefault true;
|
||||
@@ -33,13 +34,10 @@ in
|
||||
];
|
||||
warn-dirty = false;
|
||||
flake-registry = ""; # disable global flake registries
|
||||
connect-timeout = 10;
|
||||
download-buffer-size = 536870912;
|
||||
fallback = true;
|
||||
};
|
||||
|
||||
# Add each flake input as a registry and nix_path
|
||||
registry = lib.mapAttrs (_: flake: { inherit flake; }) flakeInputs;
|
||||
registry = lib.mapAttrs (_: flake: {inherit flake;}) flakeInputs;
|
||||
nixPath = lib.mapAttrsToList (n: _: "${n}=flake:${n}") flakeInputs;
|
||||
};
|
||||
}
|
||||
|
||||
@@ -2,6 +2,6 @@
|
||||
{
|
||||
environment.systemPackages = with pkgs; [
|
||||
git
|
||||
my_python
|
||||
python313
|
||||
];
|
||||
}
|
||||
|
||||
@@ -1,57 +1,37 @@
|
||||
{
|
||||
pkgs,
|
||||
lib,
|
||||
config,
|
||||
...
|
||||
}:
|
||||
{ inputs, pkgs, lib, config, ... }:
|
||||
let
|
||||
cfg = config.services.snapshot_manager;
|
||||
in
|
||||
{
|
||||
options = {
|
||||
services.snapshot_manager = {
|
||||
enable = lib.mkEnableOption "ZFS snapshot manager";
|
||||
enable = lib.mkOption {
|
||||
default = true;
|
||||
example = true;
|
||||
description = "Whether to enable k3s-net.";
|
||||
type = lib.types.bool;
|
||||
};
|
||||
path = lib.mkOption {
|
||||
type = lib.types.path;
|
||||
description = "Path that needs to be updated via git pull";
|
||||
default = ./snapshot_config.toml;
|
||||
description = "Path to the snapshot_manager TOML config.";
|
||||
};
|
||||
PYTHONPATH = lib.mkOption {
|
||||
type = lib.types.str;
|
||||
description = ''
|
||||
the PYTHONPATH to use for the snapshot_manager service.
|
||||
'';
|
||||
};
|
||||
EnvironmentFile = lib.mkOption {
|
||||
type = lib.types.nullOr (lib.types.coercedTo lib.types.path toString lib.types.str);
|
||||
default = null;
|
||||
description = ''
|
||||
Single environment file for the service (e.g. /etc/snapshot-manager/env).
|
||||
Use a leading "-" to ignore if missing (systemd feature).
|
||||
'';
|
||||
};
|
||||
};
|
||||
};
|
||||
|
||||
config = lib.mkIf cfg.enable {
|
||||
systemd = {
|
||||
services.snapshot_manager = {
|
||||
services."snapshot_manager" = {
|
||||
description = "ZFS Snapshot Manager";
|
||||
requires = [ "zfs-import.target" ];
|
||||
after = [ "zfs-import.target" ];
|
||||
path = [ pkgs.zfs ];
|
||||
environment = {
|
||||
PYTHONPATH = cfg.PYTHONPATH;
|
||||
};
|
||||
serviceConfig = {
|
||||
Type = "oneshot";
|
||||
ExecStart = "${pkgs.my_python}/bin/python -m python.tools.snapshot_manager ${lib.escapeShellArg cfg.path}";
|
||||
}
|
||||
// lib.optionalAttrs (cfg.EnvironmentFile != null) {
|
||||
EnvironmentFile = cfg.EnvironmentFile;
|
||||
ExecStart = "${inputs.system_tools.packages.x86_64-linux.default}/bin/snapshot_manager --config-file='${cfg.path}'";
|
||||
};
|
||||
};
|
||||
timers.snapshot_manager = {
|
||||
timers."snapshot_manager" = {
|
||||
wantedBy = [ "timers.target" ];
|
||||
timerConfig = {
|
||||
OnBootSec = "15m";
|
||||
@@ -61,4 +41,4 @@ in
|
||||
};
|
||||
};
|
||||
};
|
||||
}
|
||||
}
|
||||
@@ -37,8 +37,6 @@
|
||||
TcpKeepAlive = "no";
|
||||
X11Forwarding = lib.mkDefault false;
|
||||
KexAlgorithms = [
|
||||
"sntrup761x25519-sha512@openssh.com"
|
||||
"mlkem768x25519-sha256"
|
||||
"curve25519-sha256@libssh.org"
|
||||
"diffie-hellman-group-exchange-sha256"
|
||||
];
|
||||
@@ -69,5 +67,5 @@
|
||||
};
|
||||
};
|
||||
|
||||
networking.firewall.allowedTCPPorts = [ 22 ];
|
||||
networking.firewall.allowedTCPPorts = [ 22 ];
|
||||
}
|
||||
|
||||
@@ -1,6 +0,0 @@
|
||||
{
|
||||
nix.settings = {
|
||||
trusted-substituters = [ "http://192.168.95.35:5000" ];
|
||||
substituters = [ "http://192.168.95.35:5000/?priority=1&want-mass-query=true" ];
|
||||
};
|
||||
}
|
||||
@@ -1,8 +1,8 @@
|
||||
{ pkgs, ... }:
|
||||
{
|
||||
boot = {
|
||||
kernelPackages = pkgs.linuxPackages_6_18;
|
||||
zfs.package = pkgs.zfs_2_4;
|
||||
kernelPackages = pkgs.linuxPackages_6_12;
|
||||
zfs.package = pkgs.zfs_2_3;
|
||||
};
|
||||
|
||||
hardware.bluetooth = {
|
||||
|
||||
@@ -1,256 +0,0 @@
|
||||
{
|
||||
config,
|
||||
lib,
|
||||
pkgs,
|
||||
...
|
||||
}:
|
||||
let
|
||||
monitoringInterface = "ztwfunumly";
|
||||
nodeTextfileDir = "/var/lib/prometheus-node-exporter-textfile";
|
||||
|
||||
mkProcessNameTemplate =
|
||||
perPid: template: if perPid then "${template}:{{.PID}}:{{.StartTime}}" else template;
|
||||
|
||||
mkProcessMatchers = perPid: [
|
||||
{
|
||||
name = mkProcessNameTemplate perPid "{{.Username}}:{{.Matches.Module}}";
|
||||
cmdline = [ "^/nix/store[^ ]*/bin/python[^ ]* -m (?P<Module>[^ ]+)" ];
|
||||
}
|
||||
{
|
||||
name = mkProcessNameTemplate perPid "{{.Username}}:{{.Matches.Wrapped}}";
|
||||
cmdline = [
|
||||
"^/nix/store[^ ]*/bin/python[^ ]* /nix/store[^ ]*/bin/\\.?(?P<Wrapped>[^ /]+?)(?:-wrapped)?(?:\\s|$)"
|
||||
];
|
||||
}
|
||||
{
|
||||
name = mkProcessNameTemplate perPid "{{.Username}}:{{.Matches.Wrapped}}";
|
||||
cmdline = [
|
||||
"^/nix/store[^ ]*/bin/node /nix/store[^ ]*-(?P<Wrapped>[A-Za-z0-9._+-]+)-[0-9][^ /]*/"
|
||||
];
|
||||
}
|
||||
{
|
||||
name = mkProcessNameTemplate perPid "{{.Username}}:{{.Matches.Wrapped}}";
|
||||
cmdline = [ "^/nix/store[^ ]*/(?:bin/|lib/[^ ]*/)?\\.?(?P<Wrapped>[^ /]+?)(?:-wrapped)?(?:\\s|$)" ];
|
||||
}
|
||||
{
|
||||
name = mkProcessNameTemplate perPid "{{.Username}}:{{.ExeBase}}";
|
||||
cmdline = [ ".+" ];
|
||||
}
|
||||
];
|
||||
|
||||
perPidConfig = pkgs.writeText "process-exporter-per-pid.yaml" (
|
||||
builtins.toJSON {
|
||||
process_names = mkProcessMatchers true;
|
||||
}
|
||||
);
|
||||
|
||||
zpoolLatencyScript = pkgs.writeShellScript "zpool-latency-exporter" ''
|
||||
set -euo pipefail
|
||||
|
||||
out_dir=${lib.escapeShellArg nodeTextfileDir}
|
||||
host=${lib.escapeShellArg config.networking.hostName}
|
||||
tmp_file="$(mktemp "$out_dir/zpool.prom.XXXXXX")"
|
||||
trap 'rm -f "$tmp_file"' EXIT
|
||||
|
||||
pools="$(zpool list -H -o name | paste -sd, -)"
|
||||
|
||||
cat >"$tmp_file" <<'EOF'
|
||||
# HELP zpool_iostat_total_wait_read_ns Average total read wait time reported by zpool iostat.
|
||||
# TYPE zpool_iostat_total_wait_read_ns gauge
|
||||
# HELP zpool_iostat_total_wait_write_ns Average total write wait time reported by zpool iostat.
|
||||
# TYPE zpool_iostat_total_wait_write_ns gauge
|
||||
# HELP zpool_iostat_disk_wait_read_ns Average disk read wait time reported by zpool iostat.
|
||||
# TYPE zpool_iostat_disk_wait_read_ns gauge
|
||||
# HELP zpool_iostat_disk_wait_write_ns Average disk write wait time reported by zpool iostat.
|
||||
# TYPE zpool_iostat_disk_wait_write_ns gauge
|
||||
# HELP zpool_iostat_syncq_wait_read_ns Average synchronous queue read wait time reported by zpool iostat.
|
||||
# TYPE zpool_iostat_syncq_wait_read_ns gauge
|
||||
# HELP zpool_iostat_syncq_wait_write_ns Average synchronous queue write wait time reported by zpool iostat.
|
||||
# TYPE zpool_iostat_syncq_wait_write_ns gauge
|
||||
# HELP zpool_iostat_asyncq_wait_read_ns Average asynchronous queue read wait time reported by zpool iostat.
|
||||
# TYPE zpool_iostat_asyncq_wait_read_ns gauge
|
||||
# HELP zpool_iostat_asyncq_wait_write_ns Average asynchronous queue write wait time reported by zpool iostat.
|
||||
# TYPE zpool_iostat_asyncq_wait_write_ns gauge
|
||||
EOF
|
||||
|
||||
zpool iostat -Hplvy -y 1 1 | awk -F '\t' -v host="$host" -v pools="$pools" '
|
||||
function esc(str, out) {
|
||||
out = str
|
||||
gsub(/\\/, "\\\\", out)
|
||||
gsub(/"/, "\\\"", out)
|
||||
return out
|
||||
}
|
||||
|
||||
function emit(metric, pool, vdev, value) {
|
||||
if (value == "" || value == "-") {
|
||||
return
|
||||
}
|
||||
|
||||
printf "%s{host=\"%s\",pool=\"%s\",vdev=\"%s\"} %s\n",
|
||||
metric,
|
||||
esc(host),
|
||||
esc(pool),
|
||||
esc(vdev),
|
||||
value
|
||||
}
|
||||
|
||||
BEGIN {
|
||||
split(pools, pool_names, ",")
|
||||
for (idx in pool_names) {
|
||||
if (pool_names[idx] != "") {
|
||||
known_pools[pool_names[idx]] = 1
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
NF == 0 {
|
||||
next
|
||||
}
|
||||
|
||||
{
|
||||
row_name = $1
|
||||
|
||||
if (row_name in known_pools) {
|
||||
current_pool = row_name
|
||||
current_vdev = "_pool"
|
||||
} else if (current_pool == "") {
|
||||
next
|
||||
} else {
|
||||
current_vdev = row_name
|
||||
}
|
||||
|
||||
emit("zpool_iostat_total_wait_read_ns", current_pool, current_vdev, $8)
|
||||
emit("zpool_iostat_total_wait_write_ns", current_pool, current_vdev, $9)
|
||||
emit("zpool_iostat_disk_wait_read_ns", current_pool, current_vdev, $10)
|
||||
emit("zpool_iostat_disk_wait_write_ns", current_pool, current_vdev, $11)
|
||||
emit("zpool_iostat_syncq_wait_read_ns", current_pool, current_vdev, $12)
|
||||
emit("zpool_iostat_syncq_wait_write_ns", current_pool, current_vdev, $13)
|
||||
emit("zpool_iostat_asyncq_wait_read_ns", current_pool, current_vdev, $14)
|
||||
emit("zpool_iostat_asyncq_wait_write_ns", current_pool, current_vdev, $15)
|
||||
}
|
||||
' >>"$tmp_file"
|
||||
|
||||
mv "$tmp_file" "$out_dir/zpool.prom"
|
||||
trap - EXIT
|
||||
'';
|
||||
in
|
||||
{
|
||||
networking.firewall.interfaces.${monitoringInterface}.allowedTCPPorts = [
|
||||
9100
|
||||
9134
|
||||
9256
|
||||
9257
|
||||
9633
|
||||
];
|
||||
|
||||
services.prometheus.exporters = {
|
||||
node = {
|
||||
enable = true;
|
||||
enabledCollectors = [
|
||||
"pressure"
|
||||
"processes"
|
||||
"systemd"
|
||||
];
|
||||
extraFlags = [ "--collector.textfile.directory=${nodeTextfileDir}" ];
|
||||
};
|
||||
|
||||
process = {
|
||||
enable = true;
|
||||
user = "root";
|
||||
group = "root";
|
||||
settings.process_names = mkProcessMatchers false;
|
||||
extraFlags = [
|
||||
"-gather-smaps=false"
|
||||
"-remove-empty-groups=true"
|
||||
"-threads=false"
|
||||
];
|
||||
};
|
||||
|
||||
smartctl.enable = true;
|
||||
zfs.enable = true;
|
||||
};
|
||||
|
||||
programs.atop = {
|
||||
enable = true;
|
||||
atopService.enable = true;
|
||||
atopRotateTimer.enable = true;
|
||||
atopacctService.enable = true;
|
||||
settings.interval = 30;
|
||||
};
|
||||
|
||||
systemd = {
|
||||
services = {
|
||||
prometheus-process-pid-exporter = {
|
||||
description = "Prometheus process exporter with per-PID naming";
|
||||
wantedBy = [ "multi-user.target" ];
|
||||
after = [ "network.target" ];
|
||||
serviceConfig = {
|
||||
ExecStart = ''
|
||||
${pkgs.prometheus-process-exporter}/bin/process-exporter \
|
||||
--web.listen-address 0.0.0.0:9257 \
|
||||
--config.path ${perPidConfig} \
|
||||
-children=false \
|
||||
-gather-smaps=false \
|
||||
-remove-empty-groups=true \
|
||||
-threads=false
|
||||
'';
|
||||
User = "root";
|
||||
Group = "root";
|
||||
Restart = "always";
|
||||
WorkingDirectory = "/tmp";
|
||||
CapabilityBoundingSet = [ "" ];
|
||||
DeviceAllow = [ "" ];
|
||||
LockPersonality = true;
|
||||
MemoryDenyWriteExecute = true;
|
||||
NoNewPrivileges = true;
|
||||
PrivateDevices = true;
|
||||
PrivateTmp = true;
|
||||
ProtectClock = true;
|
||||
ProtectControlGroups = true;
|
||||
ProtectHome = true;
|
||||
ProtectHostname = true;
|
||||
ProtectKernelLogs = true;
|
||||
ProtectKernelModules = true;
|
||||
ProtectKernelTunables = true;
|
||||
ProtectSystem = "strict";
|
||||
RemoveIPC = true;
|
||||
RestrictAddressFamilies = [
|
||||
"AF_INET"
|
||||
"AF_INET6"
|
||||
];
|
||||
RestrictNamespaces = true;
|
||||
RestrictRealtime = true;
|
||||
RestrictSUIDSGID = true;
|
||||
SystemCallArchitectures = "native";
|
||||
UMask = "0077";
|
||||
};
|
||||
};
|
||||
|
||||
zpool-latency-exporter = {
|
||||
description = "Exports ZFS latency metrics for node_exporter textfile collection";
|
||||
after = [ "zfs-import.target" ];
|
||||
requires = [ "zfs-import.target" ];
|
||||
path = [
|
||||
config.boot.zfs.package
|
||||
pkgs.coreutils
|
||||
pkgs.gawk
|
||||
];
|
||||
serviceConfig = {
|
||||
Type = "oneshot";
|
||||
ExecStart = zpoolLatencyScript;
|
||||
};
|
||||
};
|
||||
};
|
||||
|
||||
timers.zpool-latency-exporter = {
|
||||
wantedBy = [ "timers.target" ];
|
||||
timerConfig = {
|
||||
OnBootSec = "2m";
|
||||
OnUnitActiveSec = "60s";
|
||||
Unit = "zpool-latency-exporter.service";
|
||||
};
|
||||
};
|
||||
|
||||
tmpfiles.rules = [ "d ${nodeTextfileDir} 0755 root root - -" ];
|
||||
};
|
||||
}
|
||||
@@ -2,9 +2,6 @@
|
||||
{
|
||||
services.printing = {
|
||||
enable = true;
|
||||
drivers = with pkgs; [
|
||||
gutenprint
|
||||
hplip
|
||||
];
|
||||
drivers = with pkgs; [ gutenprint hplip ];
|
||||
};
|
||||
}
|
||||
|
||||
@@ -10,9 +10,6 @@
|
||||
authorizedKeys = config.users.users.richie.openssh.authorizedKeys.keys;
|
||||
};
|
||||
};
|
||||
availableKernelModules = [
|
||||
"igb"
|
||||
"r8152"
|
||||
];
|
||||
availableKernelModules = [ "igb" ];
|
||||
};
|
||||
}
|
||||
|
||||
@@ -1,9 +1,6 @@
|
||||
{ pkgs, ... }:
|
||||
{
|
||||
environment.systemPackages = with pkgs; [
|
||||
mangohud
|
||||
steam-run
|
||||
];
|
||||
environment.systemPackages = with pkgs; [mangohud steam-run];
|
||||
hardware.steam-hardware.enable = true;
|
||||
|
||||
programs = {
|
||||
@@ -14,7 +11,7 @@
|
||||
remotePlay.openFirewall = true;
|
||||
localNetworkGameTransfers.openFirewall = true;
|
||||
protontricks.enable = true;
|
||||
extraCompatPackages = with pkgs; [ proton-ge-bin ];
|
||||
extraCompatPackages = with pkgs; [proton-ge-bin];
|
||||
extest.enable = true;
|
||||
};
|
||||
gamescope = {
|
||||
|
||||
@@ -1,18 +1,16 @@
|
||||
{ lib, ... }:
|
||||
{
|
||||
services.syncthing = {
|
||||
enable = true;
|
||||
user = "richie";
|
||||
overrideDevices = true;
|
||||
overrideFolders = lib.mkDefault true;
|
||||
overrideFolders = true;
|
||||
dataDir = "/home/richie/Syncthing";
|
||||
configDir = "/home/richie/.config/syncthing";
|
||||
settings.devices = {
|
||||
bob.id = "CJIAPEJ-VO74RR4-F75VU6M-QNZAMYG-FYUJG7Y-6AT62HJ-355PRPL-PJFETAZ"; # cspell:disable-line
|
||||
brain.id = "SSCGIPI-IV3VYKB-TRNIJE3-COV4T2H-CDBER7F-I2CGHYA-NWOEUDU-3T5QAAN"; # cspell:disable-line
|
||||
ipad.id = "KI76T3X-SFUGV2L-VSNYTKR-TSIUV5L-SHWD3HE-GQRGRCN-GY4UFMD-CW6Z6AX"; # cspell:disable-line
|
||||
phone.id = "LTGPLAE-M4ZDJTM-TZ3DJGY-SLLAVWF-CQDVEVS-RGCS75T-GAPZYK3-KUM6LA5"; # cspell:disable-line
|
||||
jeeves.id = "ICRHXZW-ECYJCUZ-I4CZ64R-3XRK7CG-LL2HAAK-FGOHD22-BQA4AI6-5OAL6AG"; # cspell:disable-line
|
||||
phone.id = "JPVQKQW-CFXOJXT-Q5G5F3H-QIDHDRE-GKHPTQB-GXZUQSP-U7FR7F7-INP3AAH"; # cspell:disable-line
|
||||
ipad.id = "KI76T3X-SFUGV2L-VSNYTKR-TSIUV5L-SHWD3HE-GQRGRCN-GY4UFMD-CW6Z6AX"; # cspell:disable-line
|
||||
bob.id = "CJIAPEJ-VO74RR4-F75VU6M-QNZAMYG-FYUJG7Y-6AT62HJ-355PRPL-PJFETAZ"; # cspell:disable-line
|
||||
rhapsody-in-green.id = "ASL3KC4-3XEN6PA-7BQBRKE-A7JXLI6-DJT43BY-Q4WPOER-7UALUAZ-VTPQ6Q4"; # cspell:disable-line
|
||||
};
|
||||
};
|
||||
|
||||
@@ -1,7 +0,0 @@
|
||||
{
|
||||
nix.settings = {
|
||||
trusted-substituters = [ "http://cache.tmmworkshop.com" ];
|
||||
substituters = [ "http://cache.tmmworkshop.com/?priority=1&want-mass-query=true" ];
|
||||
trusted-public-keys = [ "cache.tmmworkshop.com:jHffkpgbmEdstQPoihJPYW9TQe6jnQbWR2LqkNGV3iA=" ];
|
||||
};
|
||||
}
|
||||
@@ -4,8 +4,6 @@
|
||||
flags = [ "--accept-flake-config" ];
|
||||
randomizedDelaySec = "1h";
|
||||
persistent = true;
|
||||
flake = "git+https://gitea.tmmworkshop.com/richie/dotfiles?ref=main";
|
||||
allowReboot = true;
|
||||
dates = "Sat *-*-* 06:00:00";
|
||||
flake = "github:RichieCahill/dotfiles";
|
||||
};
|
||||
}
|
||||
|
||||
@@ -1,4 +0,0 @@
|
||||
source "https://rubygems.org"
|
||||
|
||||
# The github-pages gem pins all compatible versions of Jekyll and its plugins
|
||||
gem "github-pages", group: :jekyll_plugins
|
||||
@@ -1,23 +0,0 @@
|
||||
title: "Richie Cahill"
|
||||
description: "ALL THE CHAOS THAT I CANT DO AT WORK"
|
||||
baseurl: "/dotfiles"
|
||||
url: "https://richiecahill.github.io"
|
||||
|
||||
remote_theme: pages-themes/hacker@v0.2.0
|
||||
plugins:
|
||||
- jekyll-feed
|
||||
- jekyll-remote-theme
|
||||
- jekyll-seo-tag
|
||||
- jekyll-sitemap
|
||||
- jekyll-paginate
|
||||
|
||||
paginate: 5
|
||||
paginate_path: "/page:num"
|
||||
|
||||
author:
|
||||
name: "Richie Cahill"
|
||||
email: "richie@tmmworkshop.com"
|
||||
|
||||
social_links:
|
||||
github: "RichieCahill"
|
||||
website: "https://tmmworkshop.com"
|
||||
@@ -1,13 +0,0 @@
|
||||
# The MONOREPO experiment
|
||||
|
||||
Im testing a [MONOREPO](https://en.wikipedia.org/wiki/Monorepo) because Phil said this was a bad idea. To that i say hold my beer.
|
||||
|
||||
In all seriousness, I Think that for a small dev team/solo dev. The simplicity is worth higher barer to entry. One of my most annoying processes was updating my system tools. I had to build my update in a feature branch and then merge it into my main branch. then go to my dotfiles create a feature branch update the system tools merge it into main.
|
||||
|
||||
It will be starting with my Nix Dotfiles Python tools and now my blog.
|
||||
|
||||
I will be reaching ot to phil on 2030-10-31 and 2035-10-31 to give him updates on the progress.
|
||||
|
||||
Known Issues:
|
||||
|
||||
- the python tests are running on the current derivation not the one the derivation im updating to.
|
||||
@@ -1,17 +0,0 @@
|
||||
---
|
||||
layout: default
|
||||
title: "Welcome"
|
||||
---
|
||||
|
||||
Welcome to my build logs, notes, and experiments.
|
||||
|
||||
You can read my latest posts below
|
||||
|
||||
<ul>
|
||||
{% for post in site.posts %}
|
||||
<li>
|
||||
<a href="{{ post.url | relative_url }}">{{ post.title }}</a>
|
||||
<small>— {{ post.date | date: "%Y-%m-%d" }}</small>
|
||||
</li>
|
||||
{% endfor %}
|
||||
</ul>
|
||||
@@ -1,76 +0,0 @@
|
||||
# ZFS failed root import recovery
|
||||
|
||||
## Fast path
|
||||
|
||||
If the machine fails to boot because ZFS refuses to import `root_pool`:
|
||||
|
||||
### GRUB
|
||||
|
||||
1. At the bootloader menu, select the normal NixOS entry.
|
||||
2. Press `e`.
|
||||
3. Find the line that starts with `linux`.
|
||||
4. Append this to the end of that line:
|
||||
|
||||
```text
|
||||
zfs_force=1
|
||||
```
|
||||
|
||||
5. Boot once with `Ctrl+x` or `F10`.
|
||||
|
||||
### systemd-boot
|
||||
|
||||
1. At the bootloader menu, highlight the normal NixOS entry.
|
||||
2. Press `e`.
|
||||
3. Append this to the end of the options line:
|
||||
|
||||
```text
|
||||
zfs_force=1
|
||||
```
|
||||
|
||||
4. Press `Enter` to boot once.
|
||||
|
||||
## After boot
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
sudo zpool status
|
||||
sudo zpool import
|
||||
journalctl -b | rg "ZFS|zfs|import|root_pool"
|
||||
```
|
||||
|
||||
## Expected result
|
||||
|
||||
`sudo zpool status` should show `root_pool` as `ONLINE`.
|
||||
|
||||
## Reboot test
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
sudo reboot
|
||||
```
|
||||
|
||||
Do not add `zfs_force=1` the second time.
|
||||
|
||||
## If it still fails
|
||||
|
||||
Boot once more with:
|
||||
|
||||
```text
|
||||
zfs_force=1
|
||||
```
|
||||
|
||||
Then run:
|
||||
|
||||
```bash
|
||||
sudo zpool status -v
|
||||
sudo zpool history | tail -n 50
|
||||
journalctl -b | rg "ZFS|zfs|import|root_pool"
|
||||
```
|
||||
|
||||
## Notes
|
||||
|
||||
- Root pool name is `root_pool`.
|
||||
- This is a one-time recovery path after disk moves, controller changes, dirty exports, or interrupted imports.
|
||||
- Some hosts also need the LUKS unlock USB key inserted before boot.
|
||||
@@ -1,3 +0,0 @@
|
||||
# esphome
|
||||
/.esphome/
|
||||
/secrets.yaml
|
||||
@@ -1,132 +0,0 @@
|
||||
esphome:
|
||||
name: batteries
|
||||
friendly_name: batteries
|
||||
|
||||
esp32:
|
||||
board: esp32dev
|
||||
framework:
|
||||
type: arduino
|
||||
|
||||
logger:
|
||||
|
||||
api:
|
||||
encryption:
|
||||
key: !secret api_key
|
||||
|
||||
external_components:
|
||||
- source: github://syssi/esphome-jk-bms@main
|
||||
|
||||
ota:
|
||||
- platform: esphome
|
||||
password: !secret ota_password
|
||||
|
||||
wifi:
|
||||
ssid: !secret wifi_ssid
|
||||
password: !secret wifi_password
|
||||
fast_connect: on
|
||||
|
||||
captive_portal:
|
||||
|
||||
esp32_ble_tracker:
|
||||
scan_parameters:
|
||||
interval: 1100ms
|
||||
window: 1100ms
|
||||
active: true
|
||||
|
||||
ble_client:
|
||||
- mac_address: "C8:47:80:29:0F:DB"
|
||||
id: jk_ble0
|
||||
|
||||
jk_bms_ble:
|
||||
- ble_client_id: jk_ble0
|
||||
protocol_version: JK02_32S
|
||||
throttle: 1s
|
||||
id: jk_bms0
|
||||
|
||||
button:
|
||||
- platform: jk_bms_ble
|
||||
retrieve_settings:
|
||||
name: "JK0 retrieve settings"
|
||||
retrieve_device_info:
|
||||
name: "JK0 retrieve device info"
|
||||
|
||||
sensor:
|
||||
- platform: jk_bms_ble
|
||||
jk_bms_ble_id: jk_bms0
|
||||
total_voltage:
|
||||
name: "JK0 Total Voltage"
|
||||
state_of_charge:
|
||||
name: "JK0 SoC"
|
||||
charging_power:
|
||||
name: "JK0 charging power"
|
||||
discharging_power:
|
||||
name: "JK0 discharging power"
|
||||
temperature_sensor_1:
|
||||
name: "JK0 Temp 1"
|
||||
temperature_sensor_2:
|
||||
name: "JK0 Temp 2"
|
||||
balancing:
|
||||
name: "JK0 balancing"
|
||||
total_runtime:
|
||||
name: "JK0 total runtime"
|
||||
balancing_current:
|
||||
name: "JK0 balancing current"
|
||||
delta_cell_voltage:
|
||||
name: "JK0 cell delta voltage"
|
||||
average_cell_voltage:
|
||||
name: "JK0 cell average voltage"
|
||||
cell_voltage_1:
|
||||
name: "JK0 cell voltage 1"
|
||||
cell_voltage_2:
|
||||
name: "JK0 cell voltage 2"
|
||||
cell_voltage_3:
|
||||
name: "JK0 cell voltage 3"
|
||||
cell_voltage_4:
|
||||
name: "JK0 cell voltage 4"
|
||||
cell_voltage_5:
|
||||
name: "JK0 cell voltage 5"
|
||||
cell_voltage_6:
|
||||
name: "JK0 cell voltage 6"
|
||||
cell_voltage_7:
|
||||
name: "JK0 cell voltage 7"
|
||||
cell_voltage_8:
|
||||
name: "JK0 cell voltage 8"
|
||||
cell_resistance_1:
|
||||
name: "JK0 cell resistance 1"
|
||||
cell_resistance_2:
|
||||
name: "JK0 cell resistance 2"
|
||||
cell_resistance_3:
|
||||
name: "JK0 cell resistance 3"
|
||||
cell_resistance_4:
|
||||
name: "JK0 cell resistance 4"
|
||||
cell_resistance_5:
|
||||
name: "JK0 cell resistance 5"
|
||||
cell_resistance_6:
|
||||
name: "JK0 cell resistance 6"
|
||||
cell_resistance_7:
|
||||
name: "JK0 cell resistance 7"
|
||||
cell_resistance_8:
|
||||
name: "JK0 cell resistance 8"
|
||||
total_charging_cycle_capacity:
|
||||
name: "JK0 total charging cycle capacity"
|
||||
|
||||
text_sensor:
|
||||
- platform: jk_bms_ble
|
||||
jk_bms_ble_id: jk_bms0
|
||||
errors:
|
||||
name: "JK0 Errors"
|
||||
|
||||
switch:
|
||||
- platform: jk_bms_ble
|
||||
jk_bms_ble_id: jk_bms0
|
||||
charging:
|
||||
name: "JK0 Charging"
|
||||
discharging:
|
||||
name: "JK0 Discharging"
|
||||
balancer:
|
||||
name: "JK0 Balancing"
|
||||
|
||||
- platform: ble_client
|
||||
ble_client_id: jk_ble0
|
||||
name: "JK0 enable bluetooth connection"
|
||||
id: ble_client_switch0
|
||||
@@ -1,132 +0,0 @@
|
||||
esphome:
|
||||
name: battery1
|
||||
friendly_name: battery1
|
||||
|
||||
esp32:
|
||||
board: esp32dev
|
||||
framework:
|
||||
type: arduino
|
||||
|
||||
logger:
|
||||
|
||||
api:
|
||||
encryption:
|
||||
key: !secret api_key
|
||||
|
||||
external_components:
|
||||
- source: github://syssi/esphome-jk-bms@main
|
||||
|
||||
ota:
|
||||
- platform: esphome
|
||||
password: !secret ota_password
|
||||
|
||||
wifi:
|
||||
ssid: !secret wifi_ssid
|
||||
password: !secret wifi_password
|
||||
fast_connect: on
|
||||
|
||||
captive_portal:
|
||||
|
||||
esp32_ble_tracker:
|
||||
scan_parameters:
|
||||
interval: 1100ms
|
||||
window: 1100ms
|
||||
active: true
|
||||
|
||||
ble_client:
|
||||
- mac_address: "C8:47:80:37:9D:DD"
|
||||
id: jk_ble1
|
||||
|
||||
jk_bms_ble:
|
||||
- ble_client_id: jk_ble1
|
||||
protocol_version: JK02_32S
|
||||
throttle: 1s
|
||||
id: jk_bms1
|
||||
|
||||
button:
|
||||
- platform: jk_bms_ble
|
||||
retrieve_settings:
|
||||
name: "JK1 retrieve settings"
|
||||
retrieve_device_info:
|
||||
name: "JK1 retrieve device info"
|
||||
|
||||
sensor:
|
||||
- platform: jk_bms_ble
|
||||
jk_bms_ble_id: jk_bms1
|
||||
total_voltage:
|
||||
name: "JK1 Total Voltage"
|
||||
state_of_charge:
|
||||
name: "JK1 SoC"
|
||||
charging_power:
|
||||
name: "JK1 charging power"
|
||||
discharging_power:
|
||||
name: "JK1 discharging power"
|
||||
temperature_sensor_1:
|
||||
name: "JK1 Temp 1"
|
||||
temperature_sensor_2:
|
||||
name: "JK1 Temp 2"
|
||||
balancing:
|
||||
name: "JK1 balancing"
|
||||
total_runtime:
|
||||
name: "JK1 total runtime"
|
||||
balancing_current:
|
||||
name: "JK1 balancing current"
|
||||
delta_cell_voltage:
|
||||
name: "JK1 cell delta voltage"
|
||||
average_cell_voltage:
|
||||
name: "JK1 cell average voltage"
|
||||
cell_voltage_1:
|
||||
name: "JK1 cell voltage 1"
|
||||
cell_voltage_2:
|
||||
name: "JK1 cell voltage 2"
|
||||
cell_voltage_3:
|
||||
name: "JK1 cell voltage 3"
|
||||
cell_voltage_4:
|
||||
name: "JK1 cell voltage 4"
|
||||
cell_voltage_5:
|
||||
name: "JK1 cell voltage 5"
|
||||
cell_voltage_6:
|
||||
name: "JK1 cell voltage 6"
|
||||
cell_voltage_7:
|
||||
name: "JK1 cell voltage 7"
|
||||
cell_voltage_8:
|
||||
name: "JK1 cell voltage 8"
|
||||
cell_resistance_1:
|
||||
name: "JK1 cell resistance 1"
|
||||
cell_resistance_2:
|
||||
name: "JK1 cell resistance 2"
|
||||
cell_resistance_3:
|
||||
name: "JK1 cell resistance 3"
|
||||
cell_resistance_4:
|
||||
name: "JK1 cell resistance 4"
|
||||
cell_resistance_5:
|
||||
name: "JK1 cell resistance 5"
|
||||
cell_resistance_6:
|
||||
name: "JK1 cell resistance 6"
|
||||
cell_resistance_7:
|
||||
name: "JK1 cell resistance 7"
|
||||
cell_resistance_8:
|
||||
name: "JK1 cell resistance 8"
|
||||
total_charging_cycle_capacity:
|
||||
name: "JK1 total charging cycle capacity"
|
||||
|
||||
text_sensor:
|
||||
- platform: jk_bms_ble
|
||||
jk_bms_ble_id: jk_bms1
|
||||
errors:
|
||||
name: "JK1 Errors"
|
||||
|
||||
switch:
|
||||
- platform: jk_bms_ble
|
||||
jk_bms_ble_id: jk_bms1
|
||||
charging:
|
||||
name: "JK1 Charging"
|
||||
discharging:
|
||||
name: "JK1 Discharging"
|
||||
balancer:
|
||||
name: "JK1 Balancing"
|
||||
|
||||
- platform: ble_client
|
||||
ble_client_id: jk_ble1
|
||||
name: "JK1 enable bluetooth connection"
|
||||
id: ble_client_switch0
|
||||
@@ -1,48 +0,0 @@
|
||||
esphome:
|
||||
name: "environment"
|
||||
friendly_name: "environment"
|
||||
|
||||
esp32:
|
||||
board: esp32dev
|
||||
framework:
|
||||
type: arduino
|
||||
|
||||
i2c:
|
||||
sda: GPIO21
|
||||
scl: GPIO22
|
||||
scan: True
|
||||
id: bus_a
|
||||
|
||||
sensor:
|
||||
- platform: aht10
|
||||
i2c_id: bus_a
|
||||
address: 0x38
|
||||
variant: AHT20
|
||||
temperature:
|
||||
name: "environment Temperature"
|
||||
id: aht10_temperature
|
||||
humidity:
|
||||
name: "environment Humidity"
|
||||
id: aht10_humidity
|
||||
update_interval: 5s
|
||||
|
||||
web_server:
|
||||
port: 80
|
||||
|
||||
logger:
|
||||
level: DEBUG
|
||||
|
||||
api:
|
||||
encryption:
|
||||
key: !secret api_key
|
||||
|
||||
ota:
|
||||
- platform: esphome
|
||||
password: !secret ota_password
|
||||
|
||||
wifi:
|
||||
ssid: !secret wifi_ssid
|
||||
password: !secret wifi_password
|
||||
fast_connect: on
|
||||
|
||||
captive_portal:
|
||||
Generated
+234
-36
@@ -2,17 +2,18 @@
|
||||
"nodes": {
|
||||
"firefox-addons": {
|
||||
"inputs": {
|
||||
"flake-utils": "flake-utils",
|
||||
"nixpkgs": [
|
||||
"nixpkgs"
|
||||
]
|
||||
},
|
||||
"locked": {
|
||||
"dir": "pkgs/firefox-addons",
|
||||
"lastModified": 1783828963,
|
||||
"narHash": "sha256-eTytzcUJCaDUZ3/9EF0+V3fvlikQMQBwiX1Sx4Gy+No=",
|
||||
"lastModified": 1738382607,
|
||||
"narHash": "sha256-ppR81tMrcQk/wHm8MmKtp3mrtYmMTgF2lxLLXYwRsOM=",
|
||||
"owner": "rycee",
|
||||
"repo": "nur-expressions",
|
||||
"rev": "8d61e9afde605cd6c22dab68b83d7a71f0a6c5b2",
|
||||
"rev": "dc86c8feffa328d9050e039a1286e175af6d76d8",
|
||||
"type": "gitlab"
|
||||
},
|
||||
"original": {
|
||||
@@ -22,6 +23,55 @@
|
||||
"type": "gitlab"
|
||||
}
|
||||
},
|
||||
"flake-compat": {
|
||||
"flake": false,
|
||||
"locked": {
|
||||
"lastModified": 1717312683,
|
||||
"narHash": "sha256-FrlieJH50AuvagamEvWMIE6D2OAnERuDboFDYAED/dE=",
|
||||
"owner": "nix-community",
|
||||
"repo": "flake-compat",
|
||||
"rev": "38fd3954cf65ce6faf3d0d45cd26059e059f07ea",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "nix-community",
|
||||
"repo": "flake-compat",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"flake-utils": {
|
||||
"locked": {
|
||||
"lastModified": 1629284811,
|
||||
"narHash": "sha256-JHgasjPR0/J1J3DRm4KxM4zTyAj4IOJY8vIl75v/kPI=",
|
||||
"owner": "numtide",
|
||||
"repo": "flake-utils",
|
||||
"rev": "c5d161cc0af116a2e17f54316f0bf43f0819785c",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "numtide",
|
||||
"repo": "flake-utils",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"flake-utils_2": {
|
||||
"inputs": {
|
||||
"systems": "systems"
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1731533236,
|
||||
"narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
|
||||
"owner": "numtide",
|
||||
"repo": "flake-utils",
|
||||
"rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "numtide",
|
||||
"repo": "flake-utils",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"home-manager": {
|
||||
"inputs": {
|
||||
"nixpkgs": [
|
||||
@@ -29,11 +79,11 @@
|
||||
]
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1783823409,
|
||||
"narHash": "sha256-OI4IkRjRXa1e7hYmCGJDPDq5H/kPwhsyoS80cNUF9fI=",
|
||||
"lastModified": 1738415006,
|
||||
"narHash": "sha256-ZlLTnqIQQ8OE6AtT+fluB642j2R9tnvxHHtpnmLjSxQ=",
|
||||
"owner": "nix-community",
|
||||
"repo": "home-manager",
|
||||
"rev": "7566825d4652a1b885bd4ce65bd9e8def432fec9",
|
||||
"rev": "8544cd092047a7e92d0dce011108a563de7fc0f2",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -42,16 +92,57 @@
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"nixos-hardware": {
|
||||
"nix-github-actions": {
|
||||
"inputs": {
|
||||
"nixpkgs": "nixpkgs"
|
||||
"nixpkgs": [
|
||||
"system_tools",
|
||||
"poetry2nix",
|
||||
"nixpkgs"
|
||||
]
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1783792734,
|
||||
"narHash": "sha256-50rvY9GdFvpYDcMLcD/4cWSi0hVxArT5wsGlVsHy8eY=",
|
||||
"lastModified": 1729742964,
|
||||
"narHash": "sha256-B4mzTcQ0FZHdpeWcpDYPERtyjJd/NIuaQ9+BV1h+MpA=",
|
||||
"owner": "nix-community",
|
||||
"repo": "nix-github-actions",
|
||||
"rev": "e04df33f62cdcf93d73e9a04142464753a16db67",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "nix-community",
|
||||
"repo": "nix-github-actions",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"nixos-cosmic": {
|
||||
"inputs": {
|
||||
"flake-compat": "flake-compat",
|
||||
"nixpkgs": [
|
||||
"nixpkgs"
|
||||
],
|
||||
"nixpkgs-stable": "nixpkgs-stable"
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1738343111,
|
||||
"narHash": "sha256-y9st4Y0p5ry+6QdlIGeqxAA6rbEIOO1uXdAc5jxV2Bc=",
|
||||
"owner": "lilyinstarlight",
|
||||
"repo": "nixos-cosmic",
|
||||
"rev": "51b9cce097da369550f45ac07879274dc8be81e4",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "lilyinstarlight",
|
||||
"repo": "nixos-cosmic",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"nixos-hardware": {
|
||||
"locked": {
|
||||
"lastModified": 1738391520,
|
||||
"narHash": "sha256-6HI58PKjddsC0RA0gBQlt6ox47oH//jLUHwx05RO8g0=",
|
||||
"owner": "nixos",
|
||||
"repo": "nixos-hardware",
|
||||
"rev": "8efb4337e857949f4cfac86d12ef1066f417f31f",
|
||||
"rev": "34b64e4e1ddb14e3ffc7db8d4a781396dbbab773",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -63,24 +154,27 @@
|
||||
},
|
||||
"nixpkgs": {
|
||||
"locked": {
|
||||
"lastModified": 1767892417,
|
||||
"narHash": "sha256-8bW3q88CEg2u4hSP66Vf4lpbLonHz7hqDNBMcCY7E9U=",
|
||||
"rev": "3497aa5c9457a9d88d71fa93a4a8368816fbeeba",
|
||||
"type": "tarball",
|
||||
"url": "https://releases.nixos.org/nixos/unstable/nixos-26.05pre924538.3497aa5c9457/nixexprs.tar.xz"
|
||||
"lastModified": 1738142207,
|
||||
"narHash": "sha256-NGqpVVxNAHwIicXpgaVqJEJWeyqzoQJ9oc8lnK9+WC4=",
|
||||
"owner": "nixos",
|
||||
"repo": "nixpkgs",
|
||||
"rev": "9d3ae807ebd2981d593cddd0080856873139aa40",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"type": "tarball",
|
||||
"url": "https://channels.nixos.org/nixos-unstable/nixexprs.tar.xz"
|
||||
"owner": "nixos",
|
||||
"ref": "nixos-unstable",
|
||||
"repo": "nixpkgs",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"nixpkgs-master": {
|
||||
"locked": {
|
||||
"lastModified": 1783874024,
|
||||
"narHash": "sha256-Fd8rPvyBv6JjcO/nZxZiFQan6Fww/jAF4TYj0Th/Yfo=",
|
||||
"lastModified": 1738422722,
|
||||
"narHash": "sha256-Q4vhtbLYWBUnjWD4iQb003Lt+N5PuURDad1BngGKdUs=",
|
||||
"owner": "nixos",
|
||||
"repo": "nixpkgs",
|
||||
"rev": "0b4f03c64b236e4ba4252414274e92796c300124",
|
||||
"rev": "102a39bfee444533e6b4e8611d7e92aa39b7bec1",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -91,6 +185,22 @@
|
||||
}
|
||||
},
|
||||
"nixpkgs-stable": {
|
||||
"locked": {
|
||||
"lastModified": 1738163270,
|
||||
"narHash": "sha256-B/7Y1v4y+msFFBW1JAdFjNvVthvNdJKiN6EGRPnqfno=",
|
||||
"owner": "NixOS",
|
||||
"repo": "nixpkgs",
|
||||
"rev": "59e618d90c065f55ae48446f307e8c09565d5ab0",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "NixOS",
|
||||
"ref": "nixos-24.11",
|
||||
"repo": "nixpkgs",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"nixpkgs-stable_2": {
|
||||
"locked": {
|
||||
"lastModified": 1735563628,
|
||||
"narHash": "sha256-OnSAY7XDSx7CtDoqNh8jwVwh4xNL/2HaJxGjryLWzX8=",
|
||||
@@ -106,19 +216,31 @@
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"nixpkgs_2": {
|
||||
"poetry2nix": {
|
||||
"inputs": {
|
||||
"flake-utils": [
|
||||
"system_tools",
|
||||
"flake-utils"
|
||||
],
|
||||
"nix-github-actions": "nix-github-actions",
|
||||
"nixpkgs": [
|
||||
"system_tools",
|
||||
"nixpkgs"
|
||||
],
|
||||
"systems": "systems_2",
|
||||
"treefmt-nix": "treefmt-nix"
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1783776592,
|
||||
"narHash": "sha256-UgCQzxeWI75XM8G+hPrPh+MKzEPjG3SpAj7dtqSbksA=",
|
||||
"owner": "nixos",
|
||||
"repo": "nixpkgs",
|
||||
"rev": "e7a3ca8092b61ff85b6a45bf863ea2b2d6a661b3",
|
||||
"lastModified": 1736884309,
|
||||
"narHash": "sha256-eiCqmKl0BIRiYk5/ZhZozwn4/7Km9CWTbc15Cv+VX5k=",
|
||||
"owner": "nix-community",
|
||||
"repo": "poetry2nix",
|
||||
"rev": "75d0515332b7ca269f6d7abfd2c44c47a7cbca7b",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "nixos",
|
||||
"ref": "nixos-unstable",
|
||||
"repo": "nixpkgs",
|
||||
"owner": "nix-community",
|
||||
"repo": "poetry2nix",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
@@ -126,12 +248,14 @@
|
||||
"inputs": {
|
||||
"firefox-addons": "firefox-addons",
|
||||
"home-manager": "home-manager",
|
||||
"nixos-cosmic": "nixos-cosmic",
|
||||
"nixos-hardware": "nixos-hardware",
|
||||
"nixpkgs": "nixpkgs_2",
|
||||
"nixpkgs": "nixpkgs",
|
||||
"nixpkgs-master": "nixpkgs-master",
|
||||
"nixpkgs-stable": "nixpkgs-stable",
|
||||
"nixpkgs-stable": "nixpkgs-stable_2",
|
||||
"sops-nix": "sops-nix",
|
||||
"systems": "systems"
|
||||
"system_tools": "system_tools",
|
||||
"systems": "systems_3"
|
||||
}
|
||||
},
|
||||
"sops-nix": {
|
||||
@@ -141,11 +265,11 @@
|
||||
]
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1783174389,
|
||||
"narHash": "sha256-aCWC8ngycU7OdJrU2+Je3qf+1a2ykuBvpPhZT/9tXMc=",
|
||||
"lastModified": 1738291974,
|
||||
"narHash": "sha256-wkwYJc8cKmmQWUloyS9KwttBnja2ONRuJQDEsmef320=",
|
||||
"owner": "Mic92",
|
||||
"repo": "sops-nix",
|
||||
"rev": "f1406619a3884cd5c47992a70b8b35c9c0fcb4c9",
|
||||
"rev": "4c1251904d8a08c86ac6bc0d72cc09975e89aef7",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -154,7 +278,59 @@
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"system_tools": {
|
||||
"inputs": {
|
||||
"flake-utils": "flake-utils_2",
|
||||
"nixpkgs": [
|
||||
"nixpkgs"
|
||||
],
|
||||
"poetry2nix": "poetry2nix"
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1738431375,
|
||||
"narHash": "sha256-jk6JrgqNe0dEPxV2xX/pBVsrPDfWaa033LKcyERkHJw=",
|
||||
"owner": "RichieCahill",
|
||||
"repo": "system_tools",
|
||||
"rev": "36764189680c9be26192ee94da1a3f33f890ff0d",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "RichieCahill",
|
||||
"repo": "system_tools",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"systems": {
|
||||
"locked": {
|
||||
"lastModified": 1681028828,
|
||||
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
|
||||
"owner": "nix-systems",
|
||||
"repo": "default",
|
||||
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "nix-systems",
|
||||
"repo": "default",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"systems_2": {
|
||||
"locked": {
|
||||
"lastModified": 1681028828,
|
||||
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
|
||||
"owner": "nix-systems",
|
||||
"repo": "default",
|
||||
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "nix-systems",
|
||||
"repo": "default",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"systems_3": {
|
||||
"locked": {
|
||||
"lastModified": 1689347949,
|
||||
"narHash": "sha256-12tWmuL2zgBgZkdoB6qXZsgJEH9LR3oUgpaQq2RbI80=",
|
||||
@@ -168,6 +344,28 @@
|
||||
"repo": "default-linux",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"treefmt-nix": {
|
||||
"inputs": {
|
||||
"nixpkgs": [
|
||||
"system_tools",
|
||||
"poetry2nix",
|
||||
"nixpkgs"
|
||||
]
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1730120726,
|
||||
"narHash": "sha256-LqHYIxMrl/1p3/kvm2ir925tZ8DkI0KA10djk8wecSk=",
|
||||
"owner": "numtide",
|
||||
"repo": "treefmt-nix",
|
||||
"rev": "9ef337e492a5555d8e17a51c911ff1f02635be15",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "numtide",
|
||||
"repo": "treefmt-nix",
|
||||
"type": "github"
|
||||
}
|
||||
}
|
||||
},
|
||||
"root": "root",
|
||||
|
||||
@@ -4,12 +4,14 @@
|
||||
nixConfig = {
|
||||
extra-substituters = [
|
||||
"https://cache.nixos.org/?priority=2&want-mass-query=true"
|
||||
"https://cache.tmmworkshop.com/?priority=2&want-mass-query=true"
|
||||
"https://nix-community.cachix.org/?priority=10&want-mass-query=true"
|
||||
];
|
||||
extra-trusted-public-keys = [
|
||||
"cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY=" # cspell:disable-line
|
||||
"nix-community.cachix.org-1:mB9FSh9qf2dCimDSUo8Zy7bkq5CX+/rkCWyvRCYg3Fs=" # cspell:disable-line
|
||||
"cache-nix-dot:Od9KN34LXc6Lu7y1ozzV1kIXZa8coClozgth/SYE7dU=" # cspell:disable-line
|
||||
"cache.nixos.org-1:6NCHdD59X431o0gWypbMrAURkbJ16ZPMQFGspcDShjY="
|
||||
"cache.tmmworkshop.com:jHffkpgbmEdstQPoihJPYW9TQe6jnQbWR2LqkNGV3iA="
|
||||
"nix-community.cachix.org-1:mB9FSh9qf2dCimDSUo8Zy7bkq5CX+/rkCWyvRCYg3Fs="
|
||||
"cache-nix-dot:Od9KN34LXc6Lu7y1ozzV1kIXZa8coClozgth/SYE7dU="
|
||||
];
|
||||
};
|
||||
|
||||
@@ -31,82 +33,97 @@
|
||||
inputs.nixpkgs.follows = "nixpkgs";
|
||||
};
|
||||
|
||||
microvm = {
|
||||
url = "github:astro/microvm.nix";
|
||||
inputs.nixpkgs.follows = "nixpkgs";
|
||||
};
|
||||
|
||||
nixos-cosmic = {
|
||||
url = "github:lilyinstarlight/nixos-cosmic";
|
||||
inputs.nixpkgs.follows = "nixpkgs";
|
||||
};
|
||||
|
||||
sops-nix = {
|
||||
url = "github:Mic92/sops-nix";
|
||||
inputs.nixpkgs.follows = "nixpkgs";
|
||||
};
|
||||
system_tools = {
|
||||
url = "github:RichieCahill/system_tools";
|
||||
inputs.nixpkgs.follows = "nixpkgs";
|
||||
};
|
||||
};
|
||||
|
||||
outputs =
|
||||
{
|
||||
self,
|
||||
nixpkgs,
|
||||
home-manager,
|
||||
systems,
|
||||
sops-nix,
|
||||
...
|
||||
}@inputs:
|
||||
let
|
||||
inherit (self) outputs;
|
||||
lib = nixpkgs.lib // home-manager.lib;
|
||||
forEachSystem = f: lib.genAttrs (import systems) (system: f pkgsFor.${system});
|
||||
pkgsFor = lib.genAttrs (import systems) (
|
||||
system:
|
||||
outputs = {
|
||||
self,
|
||||
nixpkgs,
|
||||
home-manager,
|
||||
systems,
|
||||
nixos-cosmic,
|
||||
sops-nix,
|
||||
microvm,
|
||||
...
|
||||
} @ inputs: let
|
||||
inherit (self) outputs;
|
||||
lib = nixpkgs.lib // home-manager.lib;
|
||||
forEachSystem = f: lib.genAttrs (import systems) (system: f pkgsFor.${system});
|
||||
pkgsFor = lib.genAttrs (import systems) (
|
||||
system:
|
||||
import nixpkgs {
|
||||
inherit system;
|
||||
overlays = builtins.attrValues outputs.overlays;
|
||||
config.allowUnfree = true;
|
||||
}
|
||||
);
|
||||
in
|
||||
{
|
||||
inherit lib;
|
||||
overlays = import ./overlays { inherit inputs outputs; };
|
||||
);
|
||||
in {
|
||||
inherit lib;
|
||||
overlays = import ./overlays {inherit inputs outputs;};
|
||||
devShells = forEachSystem (pkgs: import ./shell.nix {inherit pkgs;});
|
||||
formatter = forEachSystem (pkgs: pkgs.alejandra);
|
||||
|
||||
devShells = forEachSystem (pkgs: import ./shell.nix { inherit pkgs; });
|
||||
formatter = forEachSystem (pkgs: pkgs.treefmt);
|
||||
packages = forEachSystem (
|
||||
pkgs:
|
||||
let
|
||||
installer = pkgs.callPackage ./python/installer/package.nix { };
|
||||
installer-nixos = pkgs.callPackage ./python/installer/package.nix { patchElf = false; };
|
||||
in
|
||||
emulated-dev = nixpkgs.lib.nixosSystem {
|
||||
# host system
|
||||
system = "x86_64-linux";
|
||||
modules = let
|
||||
guestSystem = "aarch64-unknown-linux-gnu";
|
||||
# you can use packages in the guest machine with cross system configuration
|
||||
pkgs = import nixpkgs {
|
||||
system = "x86_64-linux";
|
||||
crossSystem.config = guestSystem;
|
||||
};
|
||||
in [
|
||||
{nixpkgs.crossSystem.config = guestSystem;}
|
||||
microvm.nixosModules.microvm
|
||||
{
|
||||
inherit installer installer-nixos;
|
||||
default = installer;
|
||||
}
|
||||
// lib.optionalAttrs (pkgs.stdenv.hostPlatform.system == "x86_64-linux") {
|
||||
iso = self.nixosConfigurations.iso.config.system.build.isoImage;
|
||||
}
|
||||
);
|
||||
apps = forEachSystem (
|
||||
pkgs:
|
||||
let
|
||||
system = pkgs.stdenv.hostPlatform.system;
|
||||
installer = {
|
||||
type = "app";
|
||||
program = "${self.packages.${system}.installer}/bin/nixos-installer";
|
||||
meta.description = "One-file NixOS ZFS installer.";
|
||||
microvm = {
|
||||
# you can choose what CPU will be emulated by qemu
|
||||
cpu = "cortex-a53";
|
||||
hypervisor = "qemu";
|
||||
};
|
||||
in
|
||||
{
|
||||
inherit installer;
|
||||
default = installer;
|
||||
environment.systemPackages = with pkgs; [ cowsay htop ];
|
||||
services.getty.autologinUser = "root";
|
||||
system.stateVersion = "23.11";
|
||||
}
|
||||
);
|
||||
|
||||
nixosConfigurations =
|
||||
let
|
||||
hosts = builtins.attrNames (
|
||||
lib.filterAttrs (_: type: type == "directory") (builtins.readDir ./systems)
|
||||
);
|
||||
mkHost =
|
||||
name:
|
||||
lib.nixosSystem {
|
||||
modules = [ ./systems/${name} ];
|
||||
specialArgs = { inherit inputs outputs; };
|
||||
};
|
||||
in
|
||||
lib.genAttrs hosts mkHost;
|
||||
];
|
||||
};
|
||||
|
||||
nixosConfigurations = {
|
||||
bob = lib.nixosSystem {
|
||||
modules = [
|
||||
./systems/bob
|
||||
];
|
||||
specialArgs = {inherit inputs outputs;};
|
||||
};
|
||||
jeeves = lib.nixosSystem {
|
||||
modules = [
|
||||
./systems/jeeves
|
||||
];
|
||||
specialArgs = {inherit inputs outputs;};
|
||||
};
|
||||
rhapsody-in-green = lib.nixosSystem {
|
||||
modules = [
|
||||
./systems/rhapsody-in-green
|
||||
];
|
||||
specialArgs = {inherit inputs outputs;};
|
||||
};
|
||||
};
|
||||
};
|
||||
}
|
||||
|
||||
+3
-36
@@ -1,49 +1,16 @@
|
||||
{ inputs, ... }:
|
||||
{
|
||||
{inputs, ...}: {
|
||||
# When applied, the stable nixpkgs set (declared in the flake inputs) will be accessible through 'pkgs.stable'
|
||||
stable = final: _prev: {
|
||||
stable = import inputs.nixpkgs-stable {
|
||||
system = final.stdenv.hostPlatform.system;
|
||||
system = final.system;
|
||||
config.allowUnfree = true;
|
||||
};
|
||||
};
|
||||
# When applied, the master nixpkgs set (declared in the flake inputs) will be accessible through 'pkgs.master'
|
||||
master = final: _prev: {
|
||||
master = import inputs.nixpkgs-master {
|
||||
system = final.stdenv.hostPlatform.system;
|
||||
system = final.system;
|
||||
config.allowUnfree = true;
|
||||
};
|
||||
};
|
||||
|
||||
python-env = final: _prev: {
|
||||
my_python = final.python314.withPackages (
|
||||
ps: with ps; [
|
||||
alembic
|
||||
apprise
|
||||
apscheduler
|
||||
fastapi
|
||||
fastapi-cli
|
||||
httpx
|
||||
jinja2
|
||||
mypy
|
||||
pgvector
|
||||
psycopg
|
||||
pydantic
|
||||
pyfakefs
|
||||
pytest
|
||||
pytest-cov
|
||||
pytest-mock
|
||||
pytest-xdist
|
||||
python-multipart
|
||||
pydantic-settings
|
||||
ruff
|
||||
sqlalchemy
|
||||
tenacity
|
||||
tinytuya
|
||||
typer
|
||||
uvicorn
|
||||
websockets
|
||||
]
|
||||
);
|
||||
};
|
||||
}
|
||||
|
||||
-125
@@ -1,125 +0,0 @@
|
||||
[project]
|
||||
name = "system_tools"
|
||||
version = "0.1.0"
|
||||
description = ""
|
||||
authors = [{ name = "Richie Cahill", email = "richie@tmmworkshop.com" }]
|
||||
requires-python = "~=3.14.0"
|
||||
readme = "README.md"
|
||||
license = "MIT"
|
||||
# these dependencies are a best effort and aren't guaranteed to work
|
||||
# for up-to-date dependencies, see overlays/default.nix
|
||||
dependencies = [
|
||||
"alembic",
|
||||
"apprise",
|
||||
"apscheduler",
|
||||
"beautifulsoup4",
|
||||
"bm25s",
|
||||
"ebooklib",
|
||||
"fastapi",
|
||||
"fastapi-cli",
|
||||
"httpx",
|
||||
"jinja2",
|
||||
"pgvector",
|
||||
"polars",
|
||||
"psycopg[binary]",
|
||||
"pydantic",
|
||||
"pydantic-settings",
|
||||
"python-multipart",
|
||||
"sqlalchemy[asyncio]",
|
||||
"tenacity",
|
||||
"tiktoken",
|
||||
"tinytuya",
|
||||
"typer",
|
||||
"uvicorn",
|
||||
"websockets",
|
||||
"yake",
|
||||
]
|
||||
|
||||
[project.scripts]
|
||||
database = "python.database_cli:app"
|
||||
whisper-transcribe = "python.tools.whisper.transcribe:main"
|
||||
|
||||
[dependency-groups]
|
||||
dev = [
|
||||
"aiosqlite",
|
||||
"mypy",
|
||||
"pyfakefs",
|
||||
"pytest-asyncio",
|
||||
"pytest-cov",
|
||||
"pytest-mock",
|
||||
"pytest-xdist",
|
||||
"pytest",
|
||||
"ruff",
|
||||
]
|
||||
|
||||
[tool.ruff]
|
||||
|
||||
target-version = "py314"
|
||||
|
||||
line-length = 120
|
||||
|
||||
lint.select = ["ALL"]
|
||||
lint.ignore = [
|
||||
"G004", # (PERM) This is a performers nit
|
||||
"COM812", # (TEMP) conflicts when used with the formatter
|
||||
"ISC001", # (TEMP) conflicts when used with the formatter
|
||||
"S603", # (PERM) This is known to cause a false positive
|
||||
"S607", # (PERM) This is becoming a consistent annoyance
|
||||
]
|
||||
|
||||
[tool.ruff.lint.per-file-ignores]
|
||||
|
||||
"tests/**" = [
|
||||
"ANN", # (perm) type annotations not needed in tests
|
||||
"D", # (perm) docstrings not needed in tests
|
||||
"PLR2004", # (perm) magic values are fine in test assertions
|
||||
"S101", # (perm) pytest needs asserts
|
||||
]
|
||||
"python/stuff/**" = [
|
||||
"T201", # (perm) I don't care about print statements dir
|
||||
]
|
||||
"python/testing/**" = [
|
||||
"T201", # (perm) I don't care about print statements dir
|
||||
"ERA001", # (perm) I don't care about print statements dir
|
||||
]
|
||||
"python/splendor/**" = [
|
||||
"S311", # (perm) there is no security issue here
|
||||
"T201", # (perm) I don't care about print statements dir
|
||||
"PLR2004", # (temps) need to think about this
|
||||
]
|
||||
"python/orm/**" = [
|
||||
"TC003", # (perm) this creates issues because sqlalchemy uses these at runtime
|
||||
]
|
||||
"python/congress_tracker/**" = [
|
||||
"TC003", # (perm) this creates issues because sqlalchemy uses these at runtime
|
||||
]
|
||||
|
||||
"python/alembic/**" = [
|
||||
"INP001", # (perm) this creates LSP issues for alembic
|
||||
]
|
||||
|
||||
[tool.ruff.lint.pydocstyle]
|
||||
convention = "google"
|
||||
|
||||
[tool.ruff.lint.flake8-builtins]
|
||||
builtins-ignorelist = ["id"]
|
||||
|
||||
[tool.ruff.lint.pylint]
|
||||
max-args = 9
|
||||
|
||||
[tool.coverage.run]
|
||||
source = ["system_tools"]
|
||||
|
||||
[tool.coverage.report]
|
||||
exclude_lines = [
|
||||
"pragma: no cover",
|
||||
"if TYPE_CHECKING:",
|
||||
"raise NotImplementedError",
|
||||
"if __name__ == \"__main__\":",
|
||||
]
|
||||
|
||||
[tool.pytest.ini_options]
|
||||
addopts = "-n auto -ra --ignore=tests/ebook_search"
|
||||
asyncio_mode = "auto"
|
||||
testpaths = ["tests"]
|
||||
# --cov=system_tools --cov-report=term-missing --cov-report=xml --cov-report=html --cov-branch
|
||||
@@ -1 +0,0 @@
|
||||
"""Server Tools."""
|
||||
@@ -1,122 +0,0 @@
|
||||
"""Alembic."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any, Literal
|
||||
|
||||
from alembic import context
|
||||
from alembic.script import write_hooks
|
||||
from sqlalchemy.schema import CreateSchema
|
||||
|
||||
from python.common import bash_wrapper
|
||||
from python.orm.common import get_postgres_engine
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import MutableMapping
|
||||
|
||||
from sqlalchemy.orm import DeclarativeBase
|
||||
|
||||
config = context.config
|
||||
|
||||
base_class: type[DeclarativeBase] = config.attributes.get("base")
|
||||
if base_class is None:
|
||||
error = "No base class provided. Use the database CLI to run alembic commands."
|
||||
raise RuntimeError(error)
|
||||
|
||||
target_metadata = base_class.metadata
|
||||
logging.basicConfig(
|
||||
level="DEBUG",
|
||||
datefmt="%Y-%m-%dT%H:%M:%S%z",
|
||||
format="%(asctime)s %(levelname)s %(filename)s:%(lineno)d - %(message)s",
|
||||
handlers=[logging.StreamHandler(sys.stdout)],
|
||||
)
|
||||
|
||||
|
||||
@write_hooks.register("dynamic_schema")
|
||||
def dynamic_schema(filename: str, _options: dict[Any, Any]) -> None:
|
||||
"""Dynamic schema."""
|
||||
original_file = Path(filename).read_text()
|
||||
schema_name = base_class.schema_name
|
||||
dynamic_schema_file_part1 = original_file.replace(f"schema='{schema_name}'", "schema=schema")
|
||||
dynamic_schema_file = dynamic_schema_file_part1.replace(f"'{schema_name}.", "f'{schema}.")
|
||||
Path(filename).write_text(dynamic_schema_file)
|
||||
|
||||
|
||||
@write_hooks.register("import_postgresql")
|
||||
def import_postgresql(filename: str, _options: dict[Any, Any]) -> None:
|
||||
"""Add postgresql dialect import when postgresql types are used."""
|
||||
content = Path(filename).read_text()
|
||||
if "postgresql." in content and "from sqlalchemy.dialects import postgresql" not in content:
|
||||
content = content.replace(
|
||||
"import sqlalchemy as sa\n",
|
||||
"import sqlalchemy as sa\nfrom sqlalchemy.dialects import postgresql\n",
|
||||
)
|
||||
Path(filename).write_text(content)
|
||||
|
||||
|
||||
@write_hooks.register("ruff")
|
||||
def ruff_check_and_format(filename: str, _options: dict[Any, Any]) -> None:
|
||||
"""Docstring for ruff_check_and_format."""
|
||||
bash_wrapper(f"ruff check --fix {filename}")
|
||||
bash_wrapper(f"ruff format {filename}")
|
||||
|
||||
|
||||
def include_name(
|
||||
name: str | None,
|
||||
type_: Literal["schema", "table", "column", "index", "unique_constraint", "foreign_key_constraint"],
|
||||
_parent_names: MutableMapping[Literal["schema_name", "table_name", "schema_qualified_table_name"], str | None],
|
||||
) -> bool:
|
||||
"""Filter tables to be included in the migration.
|
||||
|
||||
Args:
|
||||
name (str): The name of the table.
|
||||
type_ (str): The type of the table.
|
||||
_parent_names (MutableMapping): The names of the parent tables.
|
||||
|
||||
Returns:
|
||||
bool: True if the table should be included, False otherwise.
|
||||
|
||||
"""
|
||||
if type_ == "schema":
|
||||
# allows a database with multiple schemas to have separate alembic revisions
|
||||
return name == target_metadata.schema
|
||||
return True
|
||||
|
||||
|
||||
def run_migrations_online() -> None:
|
||||
"""Run migrations in 'online' mode.
|
||||
|
||||
In this scenario we need to create an Engine
|
||||
and associate a connection with the context.
|
||||
|
||||
"""
|
||||
env_prefix = config.attributes.get("env_prefix", "POSTGRES")
|
||||
connectable = get_postgres_engine(name=env_prefix)
|
||||
|
||||
with connectable.connect() as connection:
|
||||
schema = base_class.schema_name
|
||||
if not connectable.dialect.has_schema(connection, schema):
|
||||
answer = input(f"Schema {schema!r} does not exist. Create it? [y/N] ")
|
||||
if answer.lower() != "y":
|
||||
error = f"Schema {schema!r} does not exist. Exiting."
|
||||
raise SystemExit(error)
|
||||
connection.execute(CreateSchema(schema))
|
||||
connection.commit()
|
||||
|
||||
context.configure(
|
||||
connection=connection,
|
||||
target_metadata=target_metadata,
|
||||
include_schemas=True,
|
||||
version_table_schema=schema,
|
||||
include_name=include_name,
|
||||
)
|
||||
|
||||
with context.begin_transaction():
|
||||
context.run_migrations()
|
||||
connection.commit()
|
||||
|
||||
|
||||
run_migrations_online()
|
||||
@@ -1,113 +0,0 @@
|
||||
"""created contact api.
|
||||
|
||||
Revision ID: edd7dd61a3d2
|
||||
Revises:
|
||||
Create Date: 2026-01-11 15:45:59.909266
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "edd7dd61a3d2"
|
||||
down_revision: str | None = None
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"contact",
|
||||
sa.Column("name", sa.String(), nullable=False),
|
||||
sa.Column("age", sa.Integer(), nullable=True),
|
||||
sa.Column("bio", sa.String(), nullable=True),
|
||||
sa.Column("current_job", sa.String(), nullable=True),
|
||||
sa.Column("gender", sa.String(), nullable=True),
|
||||
sa.Column("goals", sa.String(), nullable=True),
|
||||
sa.Column("legal_name", sa.String(), nullable=True),
|
||||
sa.Column("profile_pic", sa.String(), nullable=True),
|
||||
sa.Column("safe_conversation_starters", sa.String(), nullable=True),
|
||||
sa.Column("self_sufficiency_score", sa.Integer(), nullable=True),
|
||||
sa.Column("social_structure_style", sa.String(), nullable=True),
|
||||
sa.Column("ssn", sa.String(), nullable=True),
|
||||
sa.Column("suffix", sa.String(), nullable=True),
|
||||
sa.Column("timezone", sa.String(), nullable=True),
|
||||
sa.Column("topics_to_avoid", sa.String(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_contact")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"need",
|
||||
sa.Column("name", sa.String(), nullable=False),
|
||||
sa.Column("description", sa.String(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_need")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"contact_need",
|
||||
sa.Column("contact_id", sa.Integer(), nullable=False),
|
||||
sa.Column("need_id", sa.Integer(), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["contact_id"],
|
||||
[f"{schema}.contact.id"],
|
||||
name=op.f("fk_contact_need_contact_id_contact"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["need_id"], [f"{schema}.need.id"], name=op.f("fk_contact_need_need_id_need"), ondelete="CASCADE"
|
||||
),
|
||||
sa.PrimaryKeyConstraint("contact_id", "need_id", name=op.f("pk_contact_need")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"contact_relationship",
|
||||
sa.Column("contact_id", sa.Integer(), nullable=False),
|
||||
sa.Column("related_contact_id", sa.Integer(), nullable=False),
|
||||
sa.Column("relationship_type", sa.String(length=100), nullable=False),
|
||||
sa.Column("closeness_weight", sa.Integer(), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["contact_id"],
|
||||
[f"{schema}.contact.id"],
|
||||
name=op.f("fk_contact_relationship_contact_id_contact"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["related_contact_id"],
|
||||
[f"{schema}.contact.id"],
|
||||
name=op.f("fk_contact_relationship_related_contact_id_contact"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("contact_id", "related_contact_id", name=op.f("pk_contact_relationship")),
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_table("contact_relationship", schema=schema)
|
||||
op.drop_table("contact_need", schema=schema)
|
||||
op.drop_table("need", schema=schema)
|
||||
op.drop_table("contact", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
-135
@@ -1,135 +0,0 @@
|
||||
"""add congress tracker tables.
|
||||
|
||||
Revision ID: 3f71565e38de
|
||||
Revises: edd7dd61a3d2
|
||||
Create Date: 2026-02-12 16:36:09.457303
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "3f71565e38de"
|
||||
down_revision: str | None = "edd7dd61a3d2"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"bill",
|
||||
sa.Column("congress", sa.Integer(), nullable=False),
|
||||
sa.Column("bill_type", sa.String(), nullable=False),
|
||||
sa.Column("number", sa.Integer(), nullable=False),
|
||||
sa.Column("title", sa.String(), nullable=True),
|
||||
sa.Column("title_short", sa.String(), nullable=True),
|
||||
sa.Column("official_title", sa.String(), nullable=True),
|
||||
sa.Column("status", sa.String(), nullable=True),
|
||||
sa.Column("status_at", sa.Date(), nullable=True),
|
||||
sa.Column("sponsor_bioguide_id", sa.String(), nullable=True),
|
||||
sa.Column("subjects_top_term", sa.String(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_bill")),
|
||||
sa.UniqueConstraint("congress", "bill_type", "number", name="uq_bill_congress_type_number"),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index("ix_bill_congress", "bill", ["congress"], unique=False, schema=schema)
|
||||
op.create_table(
|
||||
"legislator",
|
||||
sa.Column("bioguide_id", sa.Text(), nullable=False),
|
||||
sa.Column("thomas_id", sa.String(), nullable=True),
|
||||
sa.Column("lis_id", sa.String(), nullable=True),
|
||||
sa.Column("govtrack_id", sa.Integer(), nullable=True),
|
||||
sa.Column("opensecrets_id", sa.String(), nullable=True),
|
||||
sa.Column("fec_ids", sa.String(), nullable=True),
|
||||
sa.Column("first_name", sa.String(), nullable=False),
|
||||
sa.Column("last_name", sa.String(), nullable=False),
|
||||
sa.Column("official_full_name", sa.String(), nullable=True),
|
||||
sa.Column("nickname", sa.String(), nullable=True),
|
||||
sa.Column("birthday", sa.Date(), nullable=True),
|
||||
sa.Column("gender", sa.String(), nullable=True),
|
||||
sa.Column("current_party", sa.String(), nullable=True),
|
||||
sa.Column("current_state", sa.String(), nullable=True),
|
||||
sa.Column("current_district", sa.Integer(), nullable=True),
|
||||
sa.Column("current_chamber", sa.String(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_legislator")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index(op.f("ix_legislator_bioguide_id"), "legislator", ["bioguide_id"], unique=True, schema=schema)
|
||||
op.create_table(
|
||||
"vote",
|
||||
sa.Column("congress", sa.Integer(), nullable=False),
|
||||
sa.Column("chamber", sa.String(), nullable=False),
|
||||
sa.Column("session", sa.Integer(), nullable=False),
|
||||
sa.Column("number", sa.Integer(), nullable=False),
|
||||
sa.Column("vote_type", sa.String(), nullable=True),
|
||||
sa.Column("question", sa.String(), nullable=True),
|
||||
sa.Column("result", sa.String(), nullable=True),
|
||||
sa.Column("result_text", sa.String(), nullable=True),
|
||||
sa.Column("vote_date", sa.Date(), nullable=False),
|
||||
sa.Column("yea_count", sa.Integer(), nullable=True),
|
||||
sa.Column("nay_count", sa.Integer(), nullable=True),
|
||||
sa.Column("not_voting_count", sa.Integer(), nullable=True),
|
||||
sa.Column("present_count", sa.Integer(), nullable=True),
|
||||
sa.Column("bill_id", sa.Integer(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(["bill_id"], [f"{schema}.bill.id"], name=op.f("fk_vote_bill_id_bill")),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_vote")),
|
||||
sa.UniqueConstraint("congress", "chamber", "session", "number", name="uq_vote_congress_chamber_session_number"),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index("ix_vote_congress_chamber", "vote", ["congress", "chamber"], unique=False, schema=schema)
|
||||
op.create_index("ix_vote_date", "vote", ["vote_date"], unique=False, schema=schema)
|
||||
op.create_table(
|
||||
"vote_record",
|
||||
sa.Column("vote_id", sa.Integer(), nullable=False),
|
||||
sa.Column("legislator_id", sa.Integer(), nullable=False),
|
||||
sa.Column("position", sa.String(), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["legislator_id"],
|
||||
[f"{schema}.legislator.id"],
|
||||
name=op.f("fk_vote_record_legislator_id_legislator"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["vote_id"], [f"{schema}.vote.id"], name=op.f("fk_vote_record_vote_id_vote"), ondelete="CASCADE"
|
||||
),
|
||||
sa.PrimaryKeyConstraint("vote_id", "legislator_id", name=op.f("pk_vote_record")),
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_table("vote_record", schema=schema)
|
||||
op.drop_index("ix_vote_date", table_name="vote", schema=schema)
|
||||
op.drop_index("ix_vote_congress_chamber", table_name="vote", schema=schema)
|
||||
op.drop_table("vote", schema=schema)
|
||||
op.drop_index(op.f("ix_legislator_bioguide_id"), table_name="legislator", schema=schema)
|
||||
op.drop_table("legislator", schema=schema)
|
||||
op.drop_index("ix_bill_congress", table_name="bill", schema=schema)
|
||||
op.drop_table("bill", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
-58
@@ -1,58 +0,0 @@
|
||||
"""adding SignalDevice for DeviceRegistry for signal bot.
|
||||
|
||||
Revision ID: 4c410c16e39c
|
||||
Revises: 3f71565e38de
|
||||
Create Date: 2026-03-09 14:51:24.228976
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects import postgresql
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "4c410c16e39c"
|
||||
down_revision: str | None = "3f71565e38de"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"signal_device",
|
||||
sa.Column("phone_number", sa.String(length=50), nullable=False),
|
||||
sa.Column("safety_number", sa.String(), nullable=False),
|
||||
sa.Column(
|
||||
"trust_level",
|
||||
postgresql.ENUM("VERIFIED", "UNVERIFIED", "BLOCKED", name="trust_level", schema=schema),
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column("last_seen", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_signal_device")),
|
||||
sa.UniqueConstraint("phone_number", name=op.f("uq_signal_device_phone_number")),
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_table("signal_device", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
@@ -1,41 +0,0 @@
|
||||
"""fixed safety number logic.
|
||||
|
||||
Revision ID: 99fec682516c
|
||||
Revises: 4c410c16e39c
|
||||
Create Date: 2026-03-09 16:25:25.085806
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "99fec682516c"
|
||||
down_revision: str | None = "4c410c16e39c"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.alter_column("signal_device", "safety_number", existing_type=sa.VARCHAR(), nullable=True, schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.alter_column("signal_device", "safety_number", existing_type=sa.VARCHAR(), nullable=False, schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
-54
@@ -1,54 +0,0 @@
|
||||
"""add dead_letter_message table.
|
||||
|
||||
Revision ID: a1b2c3d4e5f6
|
||||
Revises: 99fec682516c
|
||||
Create Date: 2026-03-10 12:00:00.000000
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects import postgresql
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "a1b2c3d4e5f6"
|
||||
down_revision: str | None = "99fec682516c"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
op.create_table(
|
||||
"dead_letter_message",
|
||||
sa.Column("source", sa.String(), nullable=False),
|
||||
sa.Column("message", sa.Text(), nullable=False),
|
||||
sa.Column("received_at", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column(
|
||||
"status",
|
||||
postgresql.ENUM("UNPROCESSED", "PROCESSED", name="message_status", schema=schema),
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_dead_letter_message")),
|
||||
schema=schema,
|
||||
)
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
op.drop_table("dead_letter_message", schema=schema)
|
||||
op.execute(sa.text(f"DROP TYPE IF EXISTS {schema}.message_status"))
|
||||
-66
@@ -1,66 +0,0 @@
|
||||
"""adding roles to signal devices.
|
||||
|
||||
Revision ID: 2ef7ba690159
|
||||
Revises: a1b2c3d4e5f6
|
||||
Create Date: 2026-03-16 19:22:38.020350
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "2ef7ba690159"
|
||||
down_revision: str | None = "a1b2c3d4e5f6"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"role",
|
||||
sa.Column("name", sa.String(length=50), nullable=False),
|
||||
sa.Column("id", sa.SmallInteger(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_role")),
|
||||
sa.UniqueConstraint("name", name=op.f("uq_role_name")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"device_role",
|
||||
sa.Column("device_id", sa.Integer(), nullable=False),
|
||||
sa.Column("role_id", sa.SmallInteger(), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["device_id"], [f"{schema}.signal_device.id"], name=op.f("fk_device_role_device_id_signal_device")
|
||||
),
|
||||
sa.ForeignKeyConstraint(["role_id"], [f"{schema}.role.id"], name=op.f("fk_device_role_role_id_role")),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_device_role")),
|
||||
sa.UniqueConstraint("device_id", "role_id", name="uq_device_role_device_role"),
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_table("device_role", schema=schema)
|
||||
op.drop_table("role", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
-171
@@ -1,171 +0,0 @@
|
||||
"""seprating signal_bot database.
|
||||
|
||||
Revision ID: 6b275323f435
|
||||
Revises: 2ef7ba690159
|
||||
Create Date: 2026-03-18 08:34:28.785885
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects import postgresql
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "6b275323f435"
|
||||
down_revision: str | None = "2ef7ba690159"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_table("device_role", schema=schema)
|
||||
op.drop_table("signal_device", schema=schema)
|
||||
op.drop_table("role", schema=schema)
|
||||
op.drop_table("dead_letter_message", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"dead_letter_message",
|
||||
sa.Column("source", sa.VARCHAR(), autoincrement=False, nullable=False),
|
||||
sa.Column("message", sa.TEXT(), autoincrement=False, nullable=False),
|
||||
sa.Column("received_at", postgresql.TIMESTAMP(timezone=True), autoincrement=False, nullable=False),
|
||||
sa.Column(
|
||||
"status",
|
||||
postgresql.ENUM("UNPROCESSED", "PROCESSED", name="message_status", schema=schema),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
|
||||
sa.Column(
|
||||
"created",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column(
|
||||
"updated",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_dead_letter_message")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"role",
|
||||
sa.Column("name", sa.VARCHAR(length=50), autoincrement=False, nullable=False),
|
||||
sa.Column(
|
||||
"id",
|
||||
sa.SMALLINT(),
|
||||
server_default=sa.text(f"nextval('{schema}.role_id_seq'::regclass)"),
|
||||
autoincrement=True,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column(
|
||||
"created",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column(
|
||||
"updated",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_role")),
|
||||
sa.UniqueConstraint(
|
||||
"name", name=op.f("uq_role_name"), postgresql_include=[], postgresql_nulls_not_distinct=False
|
||||
),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"signal_device",
|
||||
sa.Column("phone_number", sa.VARCHAR(length=50), autoincrement=False, nullable=False),
|
||||
sa.Column("safety_number", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column(
|
||||
"trust_level",
|
||||
postgresql.ENUM("VERIFIED", "UNVERIFIED", "BLOCKED", name="trust_level", schema=schema),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column("last_seen", postgresql.TIMESTAMP(timezone=True), autoincrement=False, nullable=False),
|
||||
sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
|
||||
sa.Column(
|
||||
"created",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column(
|
||||
"updated",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_signal_device")),
|
||||
sa.UniqueConstraint(
|
||||
"phone_number",
|
||||
name=op.f("uq_signal_device_phone_number"),
|
||||
postgresql_include=[],
|
||||
postgresql_nulls_not_distinct=False,
|
||||
),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"device_role",
|
||||
sa.Column("device_id", sa.INTEGER(), autoincrement=False, nullable=False),
|
||||
sa.Column("role_id", sa.SMALLINT(), autoincrement=False, nullable=False),
|
||||
sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
|
||||
sa.Column(
|
||||
"created",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column(
|
||||
"updated",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["device_id"], [f"{schema}.signal_device.id"], name=op.f("fk_device_role_device_id_signal_device")
|
||||
),
|
||||
sa.ForeignKeyConstraint(["role_id"], [f"{schema}.role.id"], name=op.f("fk_device_role_role_id_role")),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_device_role")),
|
||||
sa.UniqueConstraint(
|
||||
"device_id",
|
||||
"role_id",
|
||||
name=op.f("uq_device_role_device_role"),
|
||||
postgresql_include=[],
|
||||
postgresql_nulls_not_distinct=False,
|
||||
),
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
-187
@@ -1,187 +0,0 @@
|
||||
"""removed ds table from richie DB.
|
||||
|
||||
Revision ID: c8a794340928
|
||||
Revises: 6b275323f435
|
||||
Create Date: 2026-03-29 15:29:23.643146
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects import postgresql
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "c8a794340928"
|
||||
down_revision: str | None = "6b275323f435"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_table("vote_record", schema=schema)
|
||||
op.drop_index(op.f("ix_vote_congress_chamber"), table_name="vote", schema=schema)
|
||||
op.drop_index(op.f("ix_vote_date"), table_name="vote", schema=schema)
|
||||
op.drop_index(op.f("ix_legislator_bioguide_id"), table_name="legislator", schema=schema)
|
||||
op.drop_table("legislator", schema=schema)
|
||||
op.drop_table("vote", schema=schema)
|
||||
op.drop_index(op.f("ix_bill_congress"), table_name="bill", schema=schema)
|
||||
op.drop_table("bill", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"vote",
|
||||
sa.Column("congress", sa.INTEGER(), autoincrement=False, nullable=False),
|
||||
sa.Column("chamber", sa.VARCHAR(), autoincrement=False, nullable=False),
|
||||
sa.Column("session", sa.INTEGER(), autoincrement=False, nullable=False),
|
||||
sa.Column("number", sa.INTEGER(), autoincrement=False, nullable=False),
|
||||
sa.Column("vote_type", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("question", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("result", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("result_text", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("vote_date", sa.DATE(), autoincrement=False, nullable=False),
|
||||
sa.Column("yea_count", sa.INTEGER(), autoincrement=False, nullable=True),
|
||||
sa.Column("nay_count", sa.INTEGER(), autoincrement=False, nullable=True),
|
||||
sa.Column("not_voting_count", sa.INTEGER(), autoincrement=False, nullable=True),
|
||||
sa.Column("present_count", sa.INTEGER(), autoincrement=False, nullable=True),
|
||||
sa.Column("bill_id", sa.INTEGER(), autoincrement=False, nullable=True),
|
||||
sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
|
||||
sa.Column(
|
||||
"created",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column(
|
||||
"updated",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.ForeignKeyConstraint(["bill_id"], [f"{schema}.bill.id"], name=op.f("fk_vote_bill_id_bill")),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_vote")),
|
||||
sa.UniqueConstraint(
|
||||
"congress",
|
||||
"chamber",
|
||||
"session",
|
||||
"number",
|
||||
name=op.f("uq_vote_congress_chamber_session_number"),
|
||||
postgresql_include=[],
|
||||
postgresql_nulls_not_distinct=False,
|
||||
),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index(op.f("ix_vote_date"), "vote", ["vote_date"], unique=False, schema=schema)
|
||||
op.create_index(op.f("ix_vote_congress_chamber"), "vote", ["congress", "chamber"], unique=False, schema=schema)
|
||||
op.create_table(
|
||||
"vote_record",
|
||||
sa.Column("vote_id", sa.INTEGER(), autoincrement=False, nullable=False),
|
||||
sa.Column("legislator_id", sa.INTEGER(), autoincrement=False, nullable=False),
|
||||
sa.Column("position", sa.VARCHAR(), autoincrement=False, nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["legislator_id"],
|
||||
[f"{schema}.legislator.id"],
|
||||
name=op.f("fk_vote_record_legislator_id_legislator"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["vote_id"], [f"{schema}.vote.id"], name=op.f("fk_vote_record_vote_id_vote"), ondelete="CASCADE"
|
||||
),
|
||||
sa.PrimaryKeyConstraint("vote_id", "legislator_id", name=op.f("pk_vote_record")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"legislator",
|
||||
sa.Column("bioguide_id", sa.TEXT(), autoincrement=False, nullable=False),
|
||||
sa.Column("thomas_id", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("lis_id", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("govtrack_id", sa.INTEGER(), autoincrement=False, nullable=True),
|
||||
sa.Column("opensecrets_id", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("fec_ids", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("first_name", sa.VARCHAR(), autoincrement=False, nullable=False),
|
||||
sa.Column("last_name", sa.VARCHAR(), autoincrement=False, nullable=False),
|
||||
sa.Column("official_full_name", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("nickname", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("birthday", sa.DATE(), autoincrement=False, nullable=True),
|
||||
sa.Column("gender", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("current_party", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("current_state", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("current_district", sa.INTEGER(), autoincrement=False, nullable=True),
|
||||
sa.Column("current_chamber", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
|
||||
sa.Column(
|
||||
"created",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column(
|
||||
"updated",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_legislator")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index(op.f("ix_legislator_bioguide_id"), "legislator", ["bioguide_id"], unique=True, schema=schema)
|
||||
op.create_table(
|
||||
"bill",
|
||||
sa.Column("congress", sa.INTEGER(), autoincrement=False, nullable=False),
|
||||
sa.Column("bill_type", sa.VARCHAR(), autoincrement=False, nullable=False),
|
||||
sa.Column("number", sa.INTEGER(), autoincrement=False, nullable=False),
|
||||
sa.Column("title", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("title_short", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("official_title", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("status", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("status_at", sa.DATE(), autoincrement=False, nullable=True),
|
||||
sa.Column("sponsor_bioguide_id", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("subjects_top_term", sa.VARCHAR(), autoincrement=False, nullable=True),
|
||||
sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
|
||||
sa.Column(
|
||||
"created",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.Column(
|
||||
"updated",
|
||||
postgresql.TIMESTAMP(timezone=True),
|
||||
server_default=sa.text("now()"),
|
||||
autoincrement=False,
|
||||
nullable=False,
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_bill")),
|
||||
sa.UniqueConstraint(
|
||||
"congress",
|
||||
"bill_type",
|
||||
"number",
|
||||
name=op.f("uq_bill_congress_type_number"),
|
||||
postgresql_include=[],
|
||||
postgresql_nulls_not_distinct=False,
|
||||
),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index(op.f("ix_bill_congress"), "bill", ["congress"], unique=False, schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
-93
@@ -1,93 +0,0 @@
|
||||
"""adding audiobook libreary metadata.
|
||||
|
||||
Revision ID: d7864d1ffc17
|
||||
Revises: c8a794340928
|
||||
Create Date: 2026-06-03 20:24:09.200837
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "d7864d1ffc17"
|
||||
down_revision: str | None = "c8a794340928"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"audiobook_author",
|
||||
sa.Column("name", sa.String(), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_audiobook_author")),
|
||||
sa.UniqueConstraint("name", name=op.f("uq_audiobook_author_name")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"audiobook_series",
|
||||
sa.Column("name", sa.String(), nullable=False),
|
||||
sa.Column("author_id", sa.Integer(), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["author_id"],
|
||||
[f"{schema}.audiobook_author.id"],
|
||||
name=op.f("fk_audiobook_series_author_id_audiobook_author"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_audiobook_series")),
|
||||
sa.UniqueConstraint("author_id", "name", name=op.f("uq_audiobook_series_author_id")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"audiobook",
|
||||
sa.Column("title", sa.String(), nullable=False),
|
||||
sa.Column("author_id", sa.Integer(), nullable=False),
|
||||
sa.Column("series_id", sa.Integer(), nullable=True),
|
||||
sa.Column("series_index", sa.Integer(), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["author_id"],
|
||||
[f"{schema}.audiobook_author.id"],
|
||||
name=op.f("fk_audiobook_author_id_audiobook_author"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["series_id"],
|
||||
[f"{schema}.audiobook_series.id"],
|
||||
name=op.f("fk_audiobook_series_id_audiobook_series"),
|
||||
ondelete="SET NULL",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_audiobook")),
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_table("audiobook", schema=schema)
|
||||
op.drop_table("audiobook_series", schema=schema)
|
||||
op.drop_table("audiobook_author", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
@@ -1,200 +0,0 @@
|
||||
"""add ebook search tables.
|
||||
|
||||
Revision ID: 2db132cace1a
|
||||
Revises: b3c60cc5beb5
|
||||
Create Date: 2026-06-10 22:10:54.379159
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import pgvector
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "2db132cace1a"
|
||||
down_revision: str | None = "b3c60cc5beb5"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"ebook_embedding_model",
|
||||
sa.Column("name", sa.String(), nullable=False),
|
||||
sa.Column("dimension", sa.Integer(), nullable=False),
|
||||
sa.Column("is_default", sa.Boolean(), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_ebook_embedding_model")),
|
||||
sa.UniqueConstraint("name", name=op.f("uq_ebook_embedding_model_name")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"ebook_source",
|
||||
sa.Column("title", sa.String(), nullable=False),
|
||||
sa.Column("author", sa.String(), nullable=True),
|
||||
sa.Column("language", sa.String(), nullable=True),
|
||||
sa.Column("publisher", sa.String(), nullable=True),
|
||||
sa.Column("identifier", sa.String(), nullable=True),
|
||||
sa.Column("file_path", sa.String(), nullable=False),
|
||||
sa.Column("file_sha256", sa.String(length=64), nullable=False),
|
||||
sa.Column("file_mtime", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("file_size", sa.BigInteger(), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_ebook_source")),
|
||||
sa.UniqueConstraint("file_path", name=op.f("uq_ebook_source_file_path")),
|
||||
sa.UniqueConstraint("file_sha256", name=op.f("uq_ebook_source_file_sha256")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"ebook_chapter",
|
||||
sa.Column("source_id", sa.Integer(), nullable=False),
|
||||
sa.Column("spine_index", sa.Integer(), nullable=False),
|
||||
sa.Column("title", sa.String(), nullable=True),
|
||||
sa.Column("href", sa.String(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["source_id"],
|
||||
[f"{schema}.ebook_source.id"],
|
||||
name=op.f("fk_ebook_chapter_source_id_ebook_source"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_ebook_chapter")),
|
||||
sa.UniqueConstraint("source_id", "spine_index", name=op.f("uq_ebook_chapter_source_id")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"ebook_chunk",
|
||||
sa.Column("source_id", sa.Integer(), nullable=False),
|
||||
sa.Column("chapter_id", sa.Integer(), nullable=True),
|
||||
sa.Column("chunk_index", sa.Integer(), nullable=False),
|
||||
sa.Column("text", sa.String(), nullable=False),
|
||||
sa.Column("token_start", sa.Integer(), nullable=False),
|
||||
sa.Column("token_count", sa.Integer(), nullable=False),
|
||||
sa.Column("page_label", sa.String(), nullable=True),
|
||||
sa.Column("content_sha256", sa.String(length=64), nullable=False),
|
||||
sa.Column("search_text", sa.String(), nullable=False),
|
||||
sa.Column("id", sa.BigInteger(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["chapter_id"],
|
||||
[f"{schema}.ebook_chapter.id"],
|
||||
name=op.f("fk_ebook_chunk_chapter_id_ebook_chapter"),
|
||||
ondelete="SET NULL",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["source_id"],
|
||||
[f"{schema}.ebook_source.id"],
|
||||
name=op.f("fk_ebook_chunk_source_id_ebook_source"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_ebook_chunk")),
|
||||
sa.UniqueConstraint("source_id", "chunk_index", name="uq_ebook_chunk_source_id_chunk_index"),
|
||||
sa.UniqueConstraint("source_id", "content_sha256", name="uq_ebook_chunk_source_id_content_sha256"),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"ebook_chunk_embedding_1024",
|
||||
sa.Column("chunk_id", sa.BigInteger(), nullable=False),
|
||||
sa.Column("model_id", sa.Integer(), nullable=False),
|
||||
sa.Column("embedding", pgvector.sqlalchemy.vector.VECTOR(dim=1024), nullable=False),
|
||||
sa.Column("id", sa.BigInteger(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["chunk_id"],
|
||||
[f"{schema}.ebook_chunk.id"],
|
||||
name=op.f("fk_ebook_chunk_embedding_1024_chunk_id_ebook_chunk"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["model_id"],
|
||||
[f"{schema}.ebook_embedding_model.id"],
|
||||
name=op.f("fk_ebook_chunk_embedding_1024_model_id_ebook_embedding_model"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_ebook_chunk_embedding_1024")),
|
||||
sa.UniqueConstraint("chunk_id", "model_id", name=op.f("uq_ebook_chunk_embedding_1024_chunk_id")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"ebook_chunk_embedding_2560",
|
||||
sa.Column("chunk_id", sa.BigInteger(), nullable=False),
|
||||
sa.Column("model_id", sa.Integer(), nullable=False),
|
||||
sa.Column("embedding", pgvector.sqlalchemy.vector.VECTOR(dim=2560), nullable=False),
|
||||
sa.Column("id", sa.BigInteger(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["chunk_id"],
|
||||
[f"{schema}.ebook_chunk.id"],
|
||||
name=op.f("fk_ebook_chunk_embedding_2560_chunk_id_ebook_chunk"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["model_id"],
|
||||
[f"{schema}.ebook_embedding_model.id"],
|
||||
name=op.f("fk_ebook_chunk_embedding_2560_model_id_ebook_embedding_model"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_ebook_chunk_embedding_2560")),
|
||||
sa.UniqueConstraint("chunk_id", "model_id", name=op.f("uq_ebook_chunk_embedding_2560_chunk_id")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"ebook_chunk_embedding_4096",
|
||||
sa.Column("chunk_id", sa.BigInteger(), nullable=False),
|
||||
sa.Column("model_id", sa.Integer(), nullable=False),
|
||||
sa.Column("embedding", pgvector.sqlalchemy.vector.VECTOR(dim=4096), nullable=False),
|
||||
sa.Column("id", sa.BigInteger(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["chunk_id"],
|
||||
[f"{schema}.ebook_chunk.id"],
|
||||
name=op.f("fk_ebook_chunk_embedding_4096_chunk_id_ebook_chunk"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["model_id"],
|
||||
[f"{schema}.ebook_embedding_model.id"],
|
||||
name=op.f("fk_ebook_chunk_embedding_4096_model_id_ebook_embedding_model"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_ebook_chunk_embedding_4096")),
|
||||
sa.UniqueConstraint("chunk_id", "model_id", name=op.f("uq_ebook_chunk_embedding_4096_chunk_id")),
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_table("ebook_chunk_embedding_4096", schema=schema)
|
||||
op.drop_table("ebook_chunk_embedding_2560", schema=schema)
|
||||
op.drop_table("ebook_chunk_embedding_1024", schema=schema)
|
||||
op.drop_table("ebook_chunk", schema=schema)
|
||||
op.drop_table("ebook_chapter", schema=schema)
|
||||
op.drop_table("ebook_source", schema=schema)
|
||||
op.drop_table("ebook_embedding_model", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
-63
@@ -1,63 +0,0 @@
|
||||
"""updated series_index to float and added UniqueConstraint to audiobook and audiobook_author.
|
||||
|
||||
Revision ID: b3c60cc5beb5
|
||||
Revises: d7864d1ffc17
|
||||
Create Date: 2026-06-10 20:02:43.073725
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "b3c60cc5beb5"
|
||||
down_revision: str | None = "d7864d1ffc17"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.alter_column(
|
||||
"audiobook",
|
||||
"series_index",
|
||||
existing_type=sa.INTEGER(),
|
||||
type_=sa.Float(),
|
||||
existing_nullable=False,
|
||||
schema=schema,
|
||||
)
|
||||
op.create_unique_constraint(
|
||||
op.f("uq_audiobook_author_id"),
|
||||
"audiobook",
|
||||
["author_id", "series_id", "title"],
|
||||
schema=schema,
|
||||
postgresql_nulls_not_distinct=True,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_constraint(op.f("uq_audiobook_author_id"), "audiobook", schema=schema, type_="unique")
|
||||
op.alter_column(
|
||||
"audiobook",
|
||||
"series_index",
|
||||
existing_type=sa.Float(),
|
||||
type_=sa.INTEGER(),
|
||||
existing_nullable=False,
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
-54
@@ -1,54 +0,0 @@
|
||||
"""add 1024 ebook embedding cosine index.
|
||||
|
||||
Revision ID: c460105682d2
|
||||
Revises: 2db132cace1a
|
||||
Create Date: 2026-06-13 19:53:45.680289
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "c460105682d2"
|
||||
down_revision: str | None = "2db132cace1a"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_index(
|
||||
"ix_ebook_chunk_embedding_1024_embedding_cosine",
|
||||
"ebook_chunk_embedding_1024",
|
||||
["embedding"],
|
||||
unique=False,
|
||||
schema=schema,
|
||||
postgresql_using="hnsw",
|
||||
postgresql_ops={"embedding": "vector_cosine_ops"},
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_index(
|
||||
"ix_ebook_chunk_embedding_1024_embedding_cosine",
|
||||
table_name="ebook_chunk_embedding_1024",
|
||||
schema=schema,
|
||||
postgresql_using="hnsw",
|
||||
postgresql_ops={"embedding": "vector_cosine_ops"},
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
@@ -1,103 +0,0 @@
|
||||
"""adding haproxy data.
|
||||
|
||||
Revision ID: 96d72c748c24
|
||||
Revises: c460105682d2
|
||||
Create Date: 2026-06-23 16:37:17.768851
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "96d72c748c24"
|
||||
down_revision: str | None = "c460105682d2"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"haproxy_request",
|
||||
sa.Column("line_hash", sa.String(), nullable=False),
|
||||
sa.Column("requested_at", sa.DateTime(timezone=True), nullable=False),
|
||||
sa.Column("client_ip", sa.String(), nullable=False),
|
||||
sa.Column("client_port", sa.Integer(), nullable=False),
|
||||
sa.Column("frontend", sa.String(), nullable=False),
|
||||
sa.Column("ssl", sa.Boolean(), nullable=False),
|
||||
sa.Column("backend", sa.String(), nullable=False),
|
||||
sa.Column("server", sa.String(), nullable=False),
|
||||
sa.Column("time_request", sa.Integer(), nullable=False),
|
||||
sa.Column("time_queue", sa.Integer(), nullable=False),
|
||||
sa.Column("time_connect", sa.Integer(), nullable=False),
|
||||
sa.Column("time_response", sa.Integer(), nullable=False),
|
||||
sa.Column("time_total", sa.Integer(), nullable=False),
|
||||
sa.Column("status_code", sa.Integer(), nullable=False),
|
||||
sa.Column("bytes_read", sa.BigInteger(), nullable=False),
|
||||
sa.Column("termination_state", sa.String(), nullable=False),
|
||||
sa.Column("active_connections", sa.Integer(), nullable=False),
|
||||
sa.Column("frontend_connections", sa.Integer(), nullable=False),
|
||||
sa.Column("backend_connections", sa.Integer(), nullable=False),
|
||||
sa.Column("server_connections", sa.Integer(), nullable=False),
|
||||
sa.Column("retries", sa.Integer(), nullable=False),
|
||||
sa.Column("server_queue", sa.Integer(), nullable=False),
|
||||
sa.Column("backend_queue", sa.Integer(), nullable=False),
|
||||
sa.Column("host", sa.String(), nullable=True),
|
||||
sa.Column("user_agent", sa.String(), nullable=True),
|
||||
sa.Column("method", sa.String(), nullable=False),
|
||||
sa.Column("target", sa.String(), nullable=False),
|
||||
sa.Column("path", sa.String(), nullable=False),
|
||||
sa.Column("query", sa.String(), nullable=True),
|
||||
sa.Column("http_version", sa.String(), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_haproxy_request")),
|
||||
sa.UniqueConstraint("line_hash", name=op.f("uq_haproxy_request_line_hash")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index(op.f("ix_haproxy_request_backend"), "haproxy_request", ["backend"], unique=False, schema=schema)
|
||||
op.create_index(op.f("ix_haproxy_request_client_ip"), "haproxy_request", ["client_ip"], unique=False, schema=schema)
|
||||
op.create_index(op.f("ix_haproxy_request_host"), "haproxy_request", ["host"], unique=False, schema=schema)
|
||||
op.create_index(op.f("ix_haproxy_request_path"), "haproxy_request", ["path"], unique=False, schema=schema)
|
||||
op.create_index(
|
||||
op.f("ix_haproxy_request_requested_at"), "haproxy_request", ["requested_at"], unique=False, schema=schema
|
||||
)
|
||||
op.create_index(
|
||||
op.f("ix_haproxy_request_status_code"), "haproxy_request", ["status_code"], unique=False, schema=schema
|
||||
)
|
||||
op.create_index(
|
||||
op.f("ix_haproxy_request_time_response"), "haproxy_request", ["time_response"], unique=False, schema=schema
|
||||
)
|
||||
op.create_index(
|
||||
op.f("ix_haproxy_request_user_agent"), "haproxy_request", ["user_agent"], unique=False, schema=schema
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_index(op.f("ix_haproxy_request_user_agent"), table_name="haproxy_request", schema=schema)
|
||||
op.drop_index(op.f("ix_haproxy_request_time_response"), table_name="haproxy_request", schema=schema)
|
||||
op.drop_index(op.f("ix_haproxy_request_status_code"), table_name="haproxy_request", schema=schema)
|
||||
op.drop_index(op.f("ix_haproxy_request_requested_at"), table_name="haproxy_request", schema=schema)
|
||||
op.drop_index(op.f("ix_haproxy_request_path"), table_name="haproxy_request", schema=schema)
|
||||
op.drop_index(op.f("ix_haproxy_request_host"), table_name="haproxy_request", schema=schema)
|
||||
op.drop_index(op.f("ix_haproxy_request_client_ip"), table_name="haproxy_request", schema=schema)
|
||||
op.drop_index(op.f("ix_haproxy_request_backend"), table_name="haproxy_request", schema=schema)
|
||||
op.drop_table("haproxy_request", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
-206
@@ -1,206 +0,0 @@
|
||||
"""adding Phrase metadata tables.
|
||||
|
||||
Revision ID: dddee09eddcc
|
||||
Revises: 96d72c748c24
|
||||
Create Date: 2026-06-29 00:49:07.344159
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects import postgresql
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "dddee09eddcc"
|
||||
down_revision: str | None = "96d72c748c24"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"candidate_phrases",
|
||||
sa.Column("book_id", sa.Integer(), nullable=False),
|
||||
sa.Column("series_id", sa.Integer(), nullable=True),
|
||||
sa.Column("phrase_text", sa.Text(), nullable=False),
|
||||
sa.Column("phrase_norm", sa.Text(), nullable=False),
|
||||
sa.Column("token_count", sa.Integer(), nullable=False),
|
||||
sa.Column("source_raw_ngram", sa.Boolean(), nullable=False),
|
||||
sa.Column("source_yake", sa.Boolean(), nullable=False),
|
||||
sa.Column("source_spacy_ner", sa.Boolean(), nullable=False),
|
||||
sa.Column("source_spacy_noun_chunk", sa.Boolean(), nullable=False),
|
||||
sa.Column("source_capitalized", sa.Boolean(), nullable=False),
|
||||
sa.Column("source_metadata", sa.Boolean(), nullable=False),
|
||||
sa.Column("spacy_label", sa.String(), nullable=True),
|
||||
sa.Column("raw_count", sa.Integer(), nullable=False),
|
||||
sa.Column("chapter_count", sa.Integer(), nullable=False),
|
||||
sa.Column("yake_score", sa.Float(), nullable=True),
|
||||
sa.Column("candidate_score", sa.Float(), nullable=False),
|
||||
sa.Column(
|
||||
"sample_contexts",
|
||||
sa.JSON().with_variant(postgresql.JSONB(astext_type=sa.Text()), "postgresql"),
|
||||
nullable=True,
|
||||
),
|
||||
sa.Column("llm_judged", sa.Boolean(), nullable=False),
|
||||
sa.Column("llm_keep", sa.Boolean(), nullable=True),
|
||||
sa.Column("llm_confidence", sa.Float(), nullable=True),
|
||||
sa.Column("llm_category", sa.String(), nullable=True),
|
||||
sa.Column("llm_reason", sa.Text(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["book_id"],
|
||||
[f"{schema}.ebook_source.id"],
|
||||
name=op.f("fk_candidate_phrases_book_id_ebook_source"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_candidate_phrases")),
|
||||
sa.UniqueConstraint("book_id", "phrase_norm", name="uq_candidate_phrases_book_id_phrase_norm"),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index(
|
||||
"candidate_phrases_book_norm_idx", "candidate_phrases", ["book_id", "phrase_norm"], unique=False, schema=schema
|
||||
)
|
||||
op.create_index(
|
||||
"candidate_phrases_book_score_idx",
|
||||
"candidate_phrases",
|
||||
["book_id", "candidate_score"],
|
||||
unique=False,
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"protected_phrases",
|
||||
sa.Column("book_id", sa.Integer(), nullable=True),
|
||||
sa.Column("series_id", sa.Integer(), nullable=True),
|
||||
sa.Column("phrase_text", sa.Text(), nullable=False),
|
||||
sa.Column("phrase_norm", sa.Text(), nullable=False),
|
||||
sa.Column("canonical_id", sa.String(), nullable=False),
|
||||
sa.Column("phrase_type", sa.String(), nullable=True),
|
||||
sa.Column("token_count", sa.Integer(), nullable=False),
|
||||
sa.Column("confidence", sa.Float(), nullable=False),
|
||||
sa.Column("importance", sa.Float(), nullable=False),
|
||||
sa.Column("allow_nested", sa.Boolean(), nullable=False),
|
||||
sa.Column("suppress_children", sa.Boolean(), nullable=False),
|
||||
sa.Column("source_candidate_id", sa.Integer(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["book_id"],
|
||||
[f"{schema}.ebook_source.id"],
|
||||
name=op.f("fk_protected_phrases_book_id_ebook_source"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["source_candidate_id"],
|
||||
[f"{schema}.candidate_phrases.id"],
|
||||
name=op.f("fk_protected_phrases_source_candidate_id_candidate_phrases"),
|
||||
ondelete="SET NULL",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_protected_phrases")),
|
||||
sa.UniqueConstraint("book_id", "phrase_norm", name="uq_protected_phrases_book_id_phrase_norm"),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index(
|
||||
"protected_phrases_book_norm_idx", "protected_phrases", ["book_id", "phrase_norm"], unique=False, schema=schema
|
||||
)
|
||||
op.create_index("protected_phrases_norm_idx", "protected_phrases", ["phrase_norm"], unique=False, schema=schema)
|
||||
op.create_index(
|
||||
"protected_phrases_series_norm_idx",
|
||||
"protected_phrases",
|
||||
["series_id", "phrase_norm"],
|
||||
unique=False,
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"chunk_phrase_mentions",
|
||||
sa.Column("chunk_id", sa.BigInteger(), nullable=False),
|
||||
sa.Column("phrase_id", sa.Integer(), nullable=False),
|
||||
sa.Column("book_id", sa.Integer(), nullable=True),
|
||||
sa.Column("series_id", sa.Integer(), nullable=True),
|
||||
sa.Column("start_char", sa.Integer(), nullable=False),
|
||||
sa.Column("end_char", sa.Integer(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["book_id"],
|
||||
[f"{schema}.ebook_source.id"],
|
||||
name=op.f("fk_chunk_phrase_mentions_book_id_ebook_source"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["chunk_id"],
|
||||
[f"{schema}.ebook_chunk.id"],
|
||||
name=op.f("fk_chunk_phrase_mentions_chunk_id_ebook_chunk"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.ForeignKeyConstraint(
|
||||
["phrase_id"],
|
||||
[f"{schema}.protected_phrases.id"],
|
||||
name=op.f("fk_chunk_phrase_mentions_phrase_id_protected_phrases"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_chunk_phrase_mentions")),
|
||||
sa.UniqueConstraint("chunk_id", "phrase_id", "start_char", name="uq_chunk_phrase_mentions_chunk_phrase_start"),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index(
|
||||
"chunk_phrase_mentions_chunk_idx", "chunk_phrase_mentions", ["chunk_id"], unique=False, schema=schema
|
||||
)
|
||||
op.create_index(
|
||||
"chunk_phrase_mentions_phrase_idx", "chunk_phrase_mentions", ["phrase_id"], unique=False, schema=schema
|
||||
)
|
||||
op.create_table(
|
||||
"phrase_aliases",
|
||||
sa.Column("phrase_id", sa.Integer(), nullable=False),
|
||||
sa.Column("alias_text", sa.Text(), nullable=False),
|
||||
sa.Column("alias_norm", sa.Text(), nullable=False),
|
||||
sa.Column("confidence", sa.Float(), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(
|
||||
["phrase_id"],
|
||||
[f"{schema}.protected_phrases.id"],
|
||||
name=op.f("fk_phrase_aliases_phrase_id_protected_phrases"),
|
||||
ondelete="CASCADE",
|
||||
),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_phrase_aliases")),
|
||||
sa.UniqueConstraint("phrase_id", "alias_norm", name="uq_phrase_aliases_phrase_id_alias_norm"),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_index("phrase_aliases_norm_idx", "phrase_aliases", ["alias_norm"], unique=False, schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_index("phrase_aliases_norm_idx", table_name="phrase_aliases", schema=schema)
|
||||
op.drop_table("phrase_aliases", schema=schema)
|
||||
op.drop_index("chunk_phrase_mentions_phrase_idx", table_name="chunk_phrase_mentions", schema=schema)
|
||||
op.drop_index("chunk_phrase_mentions_chunk_idx", table_name="chunk_phrase_mentions", schema=schema)
|
||||
op.drop_table("chunk_phrase_mentions", schema=schema)
|
||||
op.drop_index("protected_phrases_series_norm_idx", table_name="protected_phrases", schema=schema)
|
||||
op.drop_index("protected_phrases_norm_idx", table_name="protected_phrases", schema=schema)
|
||||
op.drop_index("protected_phrases_book_norm_idx", table_name="protected_phrases", schema=schema)
|
||||
op.drop_table("protected_phrases", schema=schema)
|
||||
op.drop_index("candidate_phrases_book_score_idx", table_name="candidate_phrases", schema=schema)
|
||||
op.drop_index("candidate_phrases_book_norm_idx", table_name="candidate_phrases", schema=schema)
|
||||
op.drop_table("candidate_phrases", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
@@ -1,55 +0,0 @@
|
||||
"""remove spaCy-ner.
|
||||
|
||||
Revision ID: 751260fc3228
|
||||
Revises: dddee09eddcc
|
||||
Create Date: 2026-07-09 23:03:39.554083
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import RichieBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "751260fc3228"
|
||||
down_revision: str | None = "dddee09eddcc"
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = RichieBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_column("candidate_phrases", "source_spacy_noun_chunk", schema=schema)
|
||||
op.drop_column("candidate_phrases", "source_spacy_ner", schema=schema)
|
||||
op.drop_column("candidate_phrases", "spacy_label", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.add_column(
|
||||
"candidate_phrases", sa.Column("spacy_label", sa.VARCHAR(), autoincrement=False, nullable=True), schema=schema
|
||||
)
|
||||
op.add_column(
|
||||
"candidate_phrases",
|
||||
sa.Column("source_spacy_ner", sa.BOOLEAN(), autoincrement=False, nullable=False),
|
||||
schema=schema,
|
||||
)
|
||||
op.add_column(
|
||||
"candidate_phrases",
|
||||
sa.Column("source_spacy_noun_chunk", sa.BOOLEAN(), autoincrement=False, nullable=False),
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
@@ -1,36 +0,0 @@
|
||||
"""${message}.
|
||||
|
||||
Revision ID: ${up_revision}
|
||||
Revises: ${down_revision | comma,n}
|
||||
Create Date: ${create_date}
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
|
||||
from alembic import op
|
||||
from python.orm import ${config.attributes["base"].__name__}
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = ${repr(up_revision)}
|
||||
down_revision: str | None = ${repr(down_revision)}
|
||||
branch_labels: str | Sequence[str] | None = ${repr(branch_labels)}
|
||||
depends_on: str | Sequence[str] | None = ${repr(depends_on)}
|
||||
|
||||
schema=${config.attributes["base"].__name__}.schema_name
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
${upgrades if upgrades else "pass"}
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
${downgrades if downgrades else "pass"}
|
||||
-80
@@ -1,80 +0,0 @@
|
||||
"""starting van invintory.
|
||||
|
||||
Revision ID: 15e733499804
|
||||
Revises:
|
||||
Create Date: 2026-03-08 00:18:20.759720
|
||||
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
from python.orm import VanInventoryBase
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
# revision identifiers, used by Alembic.
|
||||
revision: str = "15e733499804"
|
||||
down_revision: str | None = None
|
||||
branch_labels: str | Sequence[str] | None = None
|
||||
depends_on: str | Sequence[str] | None = None
|
||||
|
||||
schema = VanInventoryBase.schema_name
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
"""Upgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.create_table(
|
||||
"items",
|
||||
sa.Column("name", sa.String(), nullable=False),
|
||||
sa.Column("quantity", sa.Float(), nullable=False),
|
||||
sa.Column("unit", sa.String(), nullable=False),
|
||||
sa.Column("category", sa.String(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_items")),
|
||||
sa.UniqueConstraint("name", name=op.f("uq_items_name")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"meals",
|
||||
sa.Column("name", sa.String(), nullable=False),
|
||||
sa.Column("instructions", sa.String(), nullable=True),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_meals")),
|
||||
sa.UniqueConstraint("name", name=op.f("uq_meals_name")),
|
||||
schema=schema,
|
||||
)
|
||||
op.create_table(
|
||||
"meal_ingredients",
|
||||
sa.Column("meal_id", sa.Integer(), nullable=False),
|
||||
sa.Column("item_id", sa.Integer(), nullable=False),
|
||||
sa.Column("quantity_needed", sa.Float(), nullable=False),
|
||||
sa.Column("id", sa.Integer(), nullable=False),
|
||||
sa.Column("created", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.Column("updated", sa.DateTime(timezone=True), server_default=sa.text("now()"), nullable=False),
|
||||
sa.ForeignKeyConstraint(["item_id"], [f"{schema}.items.id"], name=op.f("fk_meal_ingredients_item_id_items")),
|
||||
sa.ForeignKeyConstraint(["meal_id"], [f"{schema}.meals.id"], name=op.f("fk_meal_ingredients_meal_id_meals")),
|
||||
sa.PrimaryKeyConstraint("id", name=op.f("pk_meal_ingredients")),
|
||||
sa.UniqueConstraint("meal_id", "item_id", name=op.f("uq_meal_ingredients_meal_id")),
|
||||
schema=schema,
|
||||
)
|
||||
# ### end Alembic commands ###
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
"""Downgrade."""
|
||||
# ### commands auto generated by Alembic - please adjust! ###
|
||||
op.drop_table("meal_ingredients", schema=schema)
|
||||
op.drop_table("meals", schema=schema)
|
||||
op.drop_table("items", schema=schema)
|
||||
# ### end Alembic commands ###
|
||||
@@ -1,47 +0,0 @@
|
||||
"""common."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
from subprocess import PIPE, Popen
|
||||
|
||||
from python.logging_config import configure_logger as _configure_logger
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def get_repo_dir() -> Path:
|
||||
"""Return the repository root directory."""
|
||||
return Path(__file__).resolve().parents[1]
|
||||
|
||||
|
||||
def configure_logger(level: str = "INFO") -> None:
|
||||
"""Configure the logger."""
|
||||
_configure_logger(level)
|
||||
|
||||
|
||||
def bash_wrapper(command: str) -> tuple[str, int]:
|
||||
"""Execute a bash command and capture the output.
|
||||
|
||||
Args:
|
||||
command (str): The bash command to be executed.
|
||||
|
||||
Returns:
|
||||
Tuple[str, int]: A tuple containing the output of the command (stdout) as a string,
|
||||
the error output (stderr) as a string (optional), and the return code as an integer.
|
||||
"""
|
||||
# This is a acceptable risk
|
||||
process = Popen(command.split(), stdout=PIPE, stderr=PIPE)
|
||||
output, error = process.communicate()
|
||||
if error:
|
||||
logger.error(f"{error=}")
|
||||
return error.decode(), process.returncode
|
||||
|
||||
return output.decode(), process.returncode
|
||||
|
||||
|
||||
def utcnow() -> datetime:
|
||||
"""Get the current UTC time."""
|
||||
return datetime.now(tz=UTC)
|
||||
@@ -1,59 +0,0 @@
|
||||
"""database."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from sqlalchemy import inspect
|
||||
from sqlalchemy.exc import NoInspectionAvailable
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def safe_insert(orm_objects: Sequence[object], session: Session) -> list[tuple[Exception, object]]:
|
||||
"""Safer insert at allows for partial rollbacks.
|
||||
|
||||
Args:
|
||||
orm_objects (Sequence[object]): Tables to insert.
|
||||
session (Session): Database session.
|
||||
"""
|
||||
if unmapped := [orm_object for orm_object in orm_objects if not _is_mapped_instance(orm_object)]:
|
||||
error = f"safe_insert expects ORM-mapped instances {unmapped}"
|
||||
raise TypeError(error)
|
||||
return _safe_insert(orm_objects, session)
|
||||
|
||||
|
||||
def _safe_insert(objects: Sequence[object], session: Session) -> list[tuple[Exception, object]]:
|
||||
exceptions: list[tuple[Exception, object]] = []
|
||||
try:
|
||||
session.add_all(objects)
|
||||
session.commit()
|
||||
|
||||
except Exception as error:
|
||||
session.rollback()
|
||||
|
||||
objects_len = len(objects)
|
||||
if objects_len == 1:
|
||||
logger.exception(objects)
|
||||
return [(error, objects[0])]
|
||||
|
||||
middle = objects_len // 2
|
||||
exceptions.extend(_safe_insert(objects=objects[:middle], session=session))
|
||||
exceptions.extend(_safe_insert(objects=objects[middle:], session=session))
|
||||
return exceptions
|
||||
|
||||
|
||||
def _is_mapped_instance(obj: object) -> bool:
|
||||
"""Return True if `obj` is a SQLAlchemy ORM-mapped instance."""
|
||||
try:
|
||||
inspect(obj) # raises NoInspectionAvailable if not mapped
|
||||
except NoInspectionAvailable:
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
@@ -1,103 +0,0 @@
|
||||
"""CLI wrapper around alembic for multi-database support.
|
||||
|
||||
Usage:
|
||||
database <db_name> <command> [args...]
|
||||
|
||||
Examples:
|
||||
database richie check
|
||||
database richie upgrade head
|
||||
database richie downgrade head-1
|
||||
database richie revision --autogenerate -m "add meals table"
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from importlib import import_module
|
||||
from typing import TYPE_CHECKING, Annotated
|
||||
|
||||
import typer
|
||||
from alembic.config import CommandLine, Config
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from sqlalchemy.orm import DeclarativeBase
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class DatabaseConfig:
|
||||
"""Configuration for a database."""
|
||||
|
||||
env_prefix: str
|
||||
version_location: str
|
||||
base_module: str
|
||||
base_class_name: str
|
||||
models_module: str
|
||||
script_location: str = "python/alembic"
|
||||
file_template: str = "%%(year)d_%%(month).2d_%%(day).2d-%%(slug)s_%%(rev)s"
|
||||
|
||||
def get_base(self) -> type[DeclarativeBase]:
|
||||
"""Import and return the Base class."""
|
||||
module = import_module(self.base_module)
|
||||
return getattr(module, self.base_class_name)
|
||||
|
||||
def import_models(self) -> None:
|
||||
"""Import ORM models so alembic autogenerate can detect them."""
|
||||
import_module(self.models_module)
|
||||
|
||||
def alembic_config(self) -> Config:
|
||||
"""Build an alembic Config for this database."""
|
||||
cfg = Config()
|
||||
cfg.set_main_option("script_location", self.script_location)
|
||||
cfg.set_main_option("file_template", self.file_template)
|
||||
cfg.set_main_option("prepend_sys_path", ".")
|
||||
cfg.set_main_option("version_path_separator", "os")
|
||||
cfg.set_main_option("version_locations", self.version_location)
|
||||
cfg.set_main_option("revision_environment", "true")
|
||||
cfg.set_section_option("post_write_hooks", "hooks", "dynamic_schema,import_postgresql,ruff")
|
||||
cfg.set_section_option("post_write_hooks", "dynamic_schema.type", "dynamic_schema")
|
||||
cfg.set_section_option("post_write_hooks", "import_postgresql.type", "import_postgresql")
|
||||
cfg.set_section_option("post_write_hooks", "ruff.type", "ruff")
|
||||
cfg.attributes["base"] = self.get_base()
|
||||
cfg.attributes["env_prefix"] = self.env_prefix
|
||||
self.import_models()
|
||||
return cfg
|
||||
|
||||
|
||||
DATABASES: dict[str, DatabaseConfig] = {
|
||||
"richie": DatabaseConfig(
|
||||
env_prefix="RICHIE",
|
||||
version_location="python/alembic/richie/versions",
|
||||
base_module="python.orm.richie.base",
|
||||
base_class_name="RichieBase",
|
||||
models_module="python.orm.richie",
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
app = typer.Typer(help="Multi-database alembic wrapper.")
|
||||
|
||||
|
||||
@app.command(
|
||||
context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
|
||||
)
|
||||
def main(
|
||||
ctx: typer.Context,
|
||||
db_name: Annotated[str, typer.Argument(help=f"Database name. Options: {', '.join(DATABASES)}")],
|
||||
command: Annotated[str, typer.Argument(help="Alembic command (upgrade, downgrade, revision, check, etc.)")],
|
||||
) -> None:
|
||||
"""Run an alembic command against the specified database."""
|
||||
db_config = DATABASES.get(db_name)
|
||||
if not db_config:
|
||||
typer.echo(f"Unknown database: {db_name!r}. Available: {', '.join(DATABASES)}", err=True)
|
||||
raise typer.Exit(code=1)
|
||||
|
||||
alembic_cfg = db_config.alembic_config()
|
||||
|
||||
cmd_line = CommandLine()
|
||||
options = cmd_line.parser.parse_args([command, *ctx.args])
|
||||
cmd_line.run_cmd(alembic_cfg, options)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
app()
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
"""EPUB search package."""
|
||||
@@ -1,50 +0,0 @@
|
||||
"""Grounded answer generation."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from python.ebook_search.llm_interface import request_chat_completion
|
||||
from python.ebook_search.prompts import load_prompt
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import httpx
|
||||
|
||||
from python.ebook_search.config import EbookSearchConfig
|
||||
from python.ebook_search.search import SearchResult
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
async def answer_query(
|
||||
client: httpx.AsyncClient,
|
||||
query: str,
|
||||
results: list[SearchResult],
|
||||
config: EbookSearchConfig,
|
||||
) -> str:
|
||||
"""Answer a question using only retrieved chunks."""
|
||||
if not config.answer_enabled:
|
||||
logger.info("ebook_answer_skipped_disabled")
|
||||
return "Answer generation is disabled. Source chunks are shown below."
|
||||
|
||||
if not results:
|
||||
logger.info("ebook_answer_skipped_no_results")
|
||||
return "No relevant sources were found."
|
||||
|
||||
logger.info(
|
||||
f"ebook_answer_request_start {config.vllm_base_url=} {config.chat_model=} sources={len(results)} "
|
||||
f"query_length={len(query)}"
|
||||
)
|
||||
context = "\n\n".join(
|
||||
f"[{index}] {result.source_title}{' - ' + result.chapter_title if result.chapter_title else ''}\n{result.text}"
|
||||
for index, result in enumerate(results, start=1)
|
||||
)
|
||||
content = await request_chat_completion(
|
||||
client,
|
||||
config,
|
||||
load_prompt("answer").messages(query=query, context=context),
|
||||
)
|
||||
|
||||
logger.info(f"ebook_answer_request_complete {config.chat_model=} answer_length={len(content)}")
|
||||
return content or "The model returned an empty answer."
|
||||
@@ -1 +0,0 @@
|
||||
"""Web and external API adapters for EPUB search."""
|
||||
@@ -1,70 +0,0 @@
|
||||
"""Background BM25 refresh tasks for the web app.
|
||||
|
||||
The refresh is scheduled on the event loop instead of a thread because the async psycopg
|
||||
driver only works from the loop; a bare thread cannot open a session on the async engine.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from python.ebook_search.bm25_corpus import load_bm25_corpus, refresh_bm25_corpus
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from fastapi import FastAPI
|
||||
from sqlalchemy.ext.asyncio import AsyncEngine
|
||||
|
||||
from python.ebook_search.config import EbookSearchConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def schedule_bm25_refresh(app: FastAPI) -> None:
|
||||
"""Schedule a delayed BM25 corpus refresh, replacing any pending refresh.
|
||||
|
||||
Only called from route handlers, so a running event loop is guaranteed.
|
||||
"""
|
||||
cancel_bm25_refresh(app)
|
||||
|
||||
loop = asyncio.get_running_loop()
|
||||
|
||||
def start_refresh() -> None:
|
||||
app.state.bm25_refresh_task = loop.create_task(refresh_bm25_for_app(app))
|
||||
|
||||
app.state.bm25_refresh_timer = loop.call_later(app.state.config.bm25_refresh_delay_seconds, start_refresh)
|
||||
logger.info(f"ebook_bm25_refresh_scheduled {app.state.config.bm25_refresh_delay_seconds=}")
|
||||
|
||||
|
||||
def cancel_bm25_refresh(app: FastAPI) -> None:
|
||||
"""Cancel any pending BM25 corpus refresh timer and in-flight refresh task."""
|
||||
existing_timer = getattr(app.state, "bm25_refresh_timer", None)
|
||||
if existing_timer is not None:
|
||||
existing_timer.cancel()
|
||||
app.state.bm25_refresh_timer = None
|
||||
logger.info("ebook_bm25_refresh_cancelled")
|
||||
|
||||
existing_task = getattr(app.state, "bm25_refresh_task", None)
|
||||
if existing_task is not None:
|
||||
if not existing_task.done():
|
||||
existing_task.cancel()
|
||||
app.state.bm25_refresh_task = None
|
||||
|
||||
|
||||
async def refresh_bm25_for_app(app: FastAPI) -> None:
|
||||
"""Refresh the BM25 corpus using the app engine and config."""
|
||||
try:
|
||||
await refresh_bm25_for_engine(app.state.engine, app.state.config)
|
||||
except Exception:
|
||||
logger.exception("ebook_bm25_refresh_failed")
|
||||
|
||||
|
||||
async def refresh_bm25_for_engine(engine: AsyncEngine, config: EbookSearchConfig) -> None:
|
||||
"""Refresh the BM25 corpus using an async SQLAlchemy engine."""
|
||||
async with AsyncSession(engine) as session:
|
||||
await refresh_bm25_corpus(session, config)
|
||||
load_bm25_corpus.cache_clear()
|
||||
logger.info("ebook_bm25_corpus_cache_cleared_after_refresh")
|
||||
@@ -1,24 +0,0 @@
|
||||
"""FastAPI dependencies for the EPUB search app."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Annotated
|
||||
|
||||
import httpx
|
||||
from fastapi import Depends, Request
|
||||
|
||||
from python.ebook_search.config import EbookSearchConfig
|
||||
|
||||
|
||||
def get_config(request: Request) -> EbookSearchConfig:
|
||||
"""Get the loaded search config from app state."""
|
||||
return request.app.state.config
|
||||
|
||||
|
||||
def get_http_client(request: Request) -> httpx.AsyncClient:
|
||||
"""Get the shared LLM HTTP client from app state."""
|
||||
return request.app.state.http_client
|
||||
|
||||
|
||||
AppConfig = Annotated[EbookSearchConfig, Depends(get_config)]
|
||||
AppHttpClient = Annotated[httpx.AsyncClient, Depends(get_http_client)]
|
||||
@@ -1,127 +0,0 @@
|
||||
"""Background phrase-judging tasks for the web app.
|
||||
|
||||
Judging a book sends one LLM request per candidate phrase, which can take minutes, so it must
|
||||
not run inside the request where it would block the UI. Judgments run as async FastAPI
|
||||
background tasks, awaited on the event loop after the response is sent, and are tracked per
|
||||
book in app state so a second judge request for a book that is already being judged is
|
||||
rejected instead of doubling the work.
|
||||
|
||||
State is loop-confined: every read and mutation happens on the event loop (async route
|
||||
handlers and async background tasks) and no critical section contains an ``await``, so each
|
||||
mutation is atomic per loop iteration and no locking is needed.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from dataclasses import dataclass, field
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from python.ebook_search.protected_phrases.judge_ngrams import judge_candidate_phrases_for_books
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from fastapi import BackgroundTasks, FastAPI
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass
|
||||
class JudgeTaskState:
|
||||
"""Running book judgments and last outcome messages, keyed by book id."""
|
||||
|
||||
running_book_ids: set[int] = field(default_factory=set)
|
||||
outcome_messages: dict[int, str] = field(default_factory=dict)
|
||||
|
||||
|
||||
def get_judge_task_state(app: FastAPI) -> JudgeTaskState:
|
||||
"""Return the app's judge task state, creating it on first use.
|
||||
|
||||
Args:
|
||||
app (FastAPI): App whose state holds the judge task registry.
|
||||
|
||||
Returns:
|
||||
JudgeTaskState: The shared judge task state for this app.
|
||||
"""
|
||||
state = getattr(app.state, "judge_tasks", None)
|
||||
if state is None:
|
||||
state = JudgeTaskState()
|
||||
app.state.judge_tasks = state
|
||||
return state
|
||||
|
||||
|
||||
def start_book_phrase_judgment(app: FastAPI, background_tasks: BackgroundTasks, source_id: int) -> bool:
|
||||
"""Queue judging of one book's candidate phrases as a FastAPI background task.
|
||||
|
||||
The book is claimed before the response returns, so a repeated judge request cannot queue
|
||||
a second run while one is pending or running.
|
||||
|
||||
Args:
|
||||
app (FastAPI): App supplying the engine, config, and judge task state.
|
||||
background_tasks (BackgroundTasks): Request's background tasks to queue the judgment on.
|
||||
source_id (int): Book to judge candidates for.
|
||||
|
||||
Returns:
|
||||
bool: True when a judgment was queued, False when one is already running for this book.
|
||||
"""
|
||||
state = get_judge_task_state(app)
|
||||
if source_id in state.running_book_ids:
|
||||
logger.info(f"ebook_book_phrase_judgment_already_running {source_id=}")
|
||||
return False
|
||||
state.running_book_ids.add(source_id)
|
||||
state.outcome_messages.pop(source_id, None)
|
||||
background_tasks.add_task(judge_book_phrases_for_app, app, source_id)
|
||||
logger.info(f"ebook_book_phrase_judgment_queued {source_id=}")
|
||||
return True
|
||||
|
||||
|
||||
async def judge_book_phrases_for_app(app: FastAPI, source_id: int) -> None:
|
||||
"""Judge one book using the app engine and config, recording the outcome message.
|
||||
|
||||
Args:
|
||||
app (FastAPI): App supplying the engine, config, and judge task state.
|
||||
source_id (int): Book to judge candidates for.
|
||||
"""
|
||||
state = get_judge_task_state(app)
|
||||
try:
|
||||
result = await judge_candidate_phrases_for_books(app.state.engine, app.state.config, source_ids=[source_id])
|
||||
logger.info(
|
||||
f"ebook_book_phrase_judgment_complete {source_id=} {result.candidates_judged=} {result.protected_phrases=} "
|
||||
f"{result.phrase_mentions=} {result.books_failed=}"
|
||||
)
|
||||
if result.books_failed:
|
||||
message = "Judging failed; see server logs for details"
|
||||
else:
|
||||
message = (
|
||||
f"Judged {result.candidates_judged} candidates; {result.protected_phrases} protected phrases promoted"
|
||||
)
|
||||
except Exception:
|
||||
logger.exception(f"ebook_book_phrase_judgment_task_failed {source_id=}")
|
||||
message = "Judging failed; see server logs for details"
|
||||
state.running_book_ids.discard(source_id)
|
||||
state.outcome_messages[source_id] = message
|
||||
|
||||
|
||||
def is_judging_book(app: FastAPI, source_id: int) -> bool:
|
||||
"""Report whether a judgment is currently queued or running for one book.
|
||||
|
||||
Args:
|
||||
app (FastAPI): App supplying the judge task state.
|
||||
source_id (int): Book to check.
|
||||
|
||||
Returns:
|
||||
bool: True while the book's judgment is pending or running.
|
||||
"""
|
||||
return source_id in get_judge_task_state(app).running_book_ids
|
||||
|
||||
|
||||
def pop_book_judgment_outcome(app: FastAPI, source_id: int) -> str | None:
|
||||
"""Return and clear the outcome message from one book's last finished judgment.
|
||||
|
||||
Args:
|
||||
app (FastAPI): App supplying the judge task state.
|
||||
source_id (int): Book to fetch the outcome for.
|
||||
|
||||
Returns:
|
||||
str | None: The outcome message, or None when there is nothing new to report.
|
||||
"""
|
||||
return get_judge_task_state(app).outcome_messages.pop(source_id, None)
|
||||
@@ -1,91 +0,0 @@
|
||||
"""FastAPI HTMX app for EPUB search."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from contextlib import asynccontextmanager
|
||||
from typing import TYPE_CHECKING, Annotated
|
||||
|
||||
import httpx
|
||||
import typer
|
||||
import uvicorn
|
||||
from fastapi import FastAPI
|
||||
from fastapi.staticfiles import StaticFiles
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from python.common import configure_logger
|
||||
from python.ebook_search.api.bm25_tasks import cancel_bm25_refresh
|
||||
from python.ebook_search.api.routes import admin_router, health_router, page_router, search_router
|
||||
from python.ebook_search.api.web import STATIC_DIR
|
||||
from python.ebook_search.bm25_corpus import ensure_bm25_corpus
|
||||
from python.ebook_search.config import load_config
|
||||
from python.ebook_search.protected_phrases.pool import shutdown_extraction_pool
|
||||
from python.fastapi_tools import ZstdMiddleware
|
||||
from python.orm.common import get_async_postgres_engine
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import AsyncIterator
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@asynccontextmanager
|
||||
async def lifespan(app: FastAPI) -> AsyncIterator[None]:
|
||||
"""Manage application startup and shutdown resources."""
|
||||
logger.info("ebook_search_startup")
|
||||
config = load_config()
|
||||
app.state.config = config
|
||||
logger.info(
|
||||
f"ebook_search_config_loaded {config.top_k=} {config.embedding_model=} {config.embedding_base_url=} "
|
||||
f"{config.vllm_base_url=} {config.rerank.enabled=} {config.phrase_matching_enabled=} {config.answer_enabled=} "
|
||||
f"library_paths={len(config.library_paths)}"
|
||||
)
|
||||
if not config.library_paths:
|
||||
logger.warning("ebook_search_no_library_paths_configured")
|
||||
# Concurrent phrase judging opens one session per book worker on this engine, so size the pool
|
||||
# to cover those plus headroom for ordinary web requests.
|
||||
app.state.engine = get_async_postgres_engine(
|
||||
name="RICHIE",
|
||||
vector_engine=True,
|
||||
pool_size=config.phrase_judge_book_workers + 10,
|
||||
)
|
||||
app.state.http_client = httpx.AsyncClient()
|
||||
async with AsyncSession(app.state.engine, expire_on_commit=False) as session:
|
||||
await ensure_bm25_corpus(session, config)
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
logger.info("ebook_search_shutdown")
|
||||
cancel_bm25_refresh(app)
|
||||
shutdown_extraction_pool()
|
||||
await app.state.http_client.aclose()
|
||||
await app.state.engine.dispose()
|
||||
|
||||
|
||||
def create_app() -> FastAPI:
|
||||
"""Create the EPUB search web app."""
|
||||
app = FastAPI(title="EPUB Search", lifespan=lifespan)
|
||||
app.add_middleware(ZstdMiddleware)
|
||||
app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")
|
||||
|
||||
app.include_router(admin_router)
|
||||
app.include_router(health_router)
|
||||
app.include_router(page_router)
|
||||
app.include_router(search_router)
|
||||
|
||||
return app
|
||||
|
||||
|
||||
def serve(
|
||||
host: Annotated[str, typer.Option("--host", "-h", help="Host to bind to")] = "127.0.0.1",
|
||||
port: Annotated[int, typer.Option("--port", "-p", help="Port to bind to")] = 8070,
|
||||
log_level: Annotated[str, typer.Option("--log-level", "-l", help="Log level")] = "INFO",
|
||||
) -> None:
|
||||
"""Start the EPUB search server."""
|
||||
configure_logger(log_level)
|
||||
uvicorn.run(create_app(), host=host, port=port)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
typer.run(serve)
|
||||
@@ -1,13 +0,0 @@
|
||||
"""EPUB search web route modules."""
|
||||
|
||||
from python.ebook_search.api.routes.admin import router as admin_router
|
||||
from python.ebook_search.api.routes.health import router as health_router
|
||||
from python.ebook_search.api.routes.page import router as page_router
|
||||
from python.ebook_search.api.routes.search import router as search_router
|
||||
|
||||
__all__ = [
|
||||
"admin_router",
|
||||
"health_router",
|
||||
"page_router",
|
||||
"search_router",
|
||||
]
|
||||
@@ -1,204 +0,0 @@
|
||||
"""Admin routes for the EPUB search web UI."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
|
||||
from fastapi import APIRouter, Request
|
||||
from fastapi.responses import HTMLResponse
|
||||
|
||||
from python.ebook_search.api.bm25_tasks import schedule_bm25_refresh
|
||||
from python.ebook_search.api.dependencies import ( # noqa: TC001 FastAPI resolves these annotated dependencies at runtime
|
||||
AppConfig,
|
||||
AppHttpClient,
|
||||
)
|
||||
from python.ebook_search.api.web import error_response, templates
|
||||
from python.ebook_search.embeddings import embed_missing_chunks, embedding_model_stats
|
||||
from python.ebook_search.ingest import ingest_configured_paths
|
||||
from python.ebook_search.protected_phrases.generate_ngrams import generate_candidate_phrases_for_books
|
||||
from python.ebook_search.protected_phrases.judge_ngrams import judge_candidate_phrases_for_books
|
||||
from python.ebook_search.protected_phrases.store import book_ids_pending_first_judgment, corpus_phrase_stats
|
||||
from python.fastapi_tools import ( # noqa: TC001 FastAPI resolves these annotated dependencies at runtime
|
||||
AppAsyncEngine,
|
||||
AsyncDbSession,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/admin")
|
||||
|
||||
|
||||
@router.get("", response_class=HTMLResponse)
|
||||
async def admin(request: Request, config: AppConfig, session: AsyncDbSession) -> HTMLResponse:
|
||||
"""Render the admin page."""
|
||||
stats = await embedding_model_stats(session)
|
||||
phrase_stats = await corpus_phrase_stats(session)
|
||||
logger.info(
|
||||
f"ebook_admin_page_loaded models={len(stats)} {phrase_stats.candidate_phrases=} "
|
||||
f"{phrase_stats.protected_phrases=}"
|
||||
)
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"admin.html",
|
||||
{"config": config, "stats": stats, "phrase_stats": phrase_stats},
|
||||
)
|
||||
|
||||
|
||||
@router.post("/scan", response_class=HTMLResponse)
|
||||
async def scan_library(request: Request, config: AppConfig, session: AsyncDbSession) -> HTMLResponse:
|
||||
"""Scan configured library paths for EPUB changes."""
|
||||
try:
|
||||
count = await ingest_configured_paths(session, config)
|
||||
await session.commit()
|
||||
except Exception as error:
|
||||
logger.exception("ebook_admin_scan_failed")
|
||||
return error_response(request, error)
|
||||
|
||||
logger.info(f"ebook_admin_scan_complete {count=}")
|
||||
if count > 0:
|
||||
schedule_bm25_refresh(request.app)
|
||||
return templates.TemplateResponse(request, "partials/admin_status.html", {"message": f"Indexed {count} EPUBs"})
|
||||
|
||||
|
||||
@router.post("/phrases/generate-all", response_class=HTMLResponse)
|
||||
async def generate_all_phrases(request: Request, config: AppConfig, engine: AppAsyncEngine) -> HTMLResponse:
|
||||
"""Regenerate candidate phrases for every indexed book without LLM judging."""
|
||||
try:
|
||||
result = await generate_candidate_phrases_for_books(engine, config)
|
||||
except Exception as error:
|
||||
logger.exception("ebook_admin_generate_phrases_failed")
|
||||
return error_response(request, error)
|
||||
|
||||
logger.info(
|
||||
f"ebook_admin_generate_phrases_complete {result.books_seen=} {result.books_built=} {result.candidate_phrases=}"
|
||||
)
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"partials/admin_status.html",
|
||||
{
|
||||
"message": (
|
||||
f"Generated phrases for {result.books_built} of {result.books_seen} books; "
|
||||
f"{result.candidate_phrases} candidates stored"
|
||||
)
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
@router.post("/phrases/judge-all", response_class=HTMLResponse)
|
||||
async def judge_all_phrases(request: Request, engine: AppAsyncEngine, config: AppConfig) -> HTMLResponse:
|
||||
"""Judge unjudged candidate phrases across every indexed book."""
|
||||
return await run_phrase_judgment(request, engine, config, source_ids=None)
|
||||
|
||||
|
||||
@router.post("/phrases/judge-missing", response_class=HTMLResponse)
|
||||
async def judge_missing_phrases(
|
||||
request: Request,
|
||||
engine: AppAsyncEngine,
|
||||
config: AppConfig,
|
||||
session: AsyncDbSession,
|
||||
) -> HTMLResponse:
|
||||
"""Judge candidate phrases only for books where judging has never run."""
|
||||
source_ids = await book_ids_pending_first_judgment(session)
|
||||
if not source_ids:
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"partials/admin_status.html",
|
||||
{"message": "All books with candidate phrases have been judged"},
|
||||
)
|
||||
return await run_phrase_judgment(request, engine, config, source_ids=source_ids)
|
||||
|
||||
|
||||
async def run_phrase_judgment(
|
||||
request: Request,
|
||||
engine: AppAsyncEngine,
|
||||
config: AppConfig,
|
||||
*,
|
||||
source_ids: list[int] | None,
|
||||
) -> HTMLResponse:
|
||||
"""Run LLM judging for candidate phrases and render the outcome as an admin status partial.
|
||||
|
||||
Args:
|
||||
request (Request): Current request, for template rendering.
|
||||
engine (AppAsyncEngine): Engine used to open per-book judging sessions.
|
||||
config (AppConfig): Runtime phrase-tuning settings.
|
||||
source_ids (list[int] | None): Books to judge; ``None`` judges every indexed book.
|
||||
|
||||
Returns:
|
||||
HTMLResponse: Status partial describing the judging outcome.
|
||||
"""
|
||||
try:
|
||||
result = await judge_candidate_phrases_for_books(engine, config, source_ids=source_ids)
|
||||
except Exception as error:
|
||||
logger.exception("ebook_admin_judge_phrases_failed")
|
||||
return error_response(request, error)
|
||||
|
||||
logger.info(
|
||||
f"ebook_admin_judge_phrases_complete {result.books_seen=} {result.books_judged=} {result.books_failed=} "
|
||||
f"{result.candidates_judged=} {result.protected_phrases=} {result.phrase_mentions=}"
|
||||
)
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"partials/admin_status.html",
|
||||
{
|
||||
"message": (
|
||||
f"Judged {result.candidates_judged} candidates across {result.books_judged} of "
|
||||
f"{result.books_seen} books; {result.protected_phrases} protected phrases, "
|
||||
f"{result.phrase_mentions} mentions"
|
||||
+ (f"; {result.books_failed} books failed" if result.books_failed else "")
|
||||
)
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
@router.post("/embed-missing", response_class=HTMLResponse)
|
||||
async def embed_missing(
|
||||
request: Request,
|
||||
config: AppConfig,
|
||||
session: AsyncDbSession,
|
||||
client: AppHttpClient,
|
||||
) -> HTMLResponse:
|
||||
"""Embed chunks missing vectors for the configured model."""
|
||||
try:
|
||||
count = await embed_missing_chunks(session, client, config)
|
||||
await session.commit()
|
||||
except Exception as error:
|
||||
logger.exception("ebook_admin_embed_missing_failed")
|
||||
return error_response(request, error)
|
||||
|
||||
logger.info(f"ebook_admin_embed_missing_complete {count=}")
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"partials/admin_status.html",
|
||||
{"message": f"Embedded {count} chunks"},
|
||||
)
|
||||
|
||||
|
||||
@router.post("/embed-all", response_class=HTMLResponse)
|
||||
async def embed_all(
|
||||
request: Request,
|
||||
config: AppConfig,
|
||||
session: AsyncDbSession,
|
||||
client: AppHttpClient,
|
||||
) -> HTMLResponse:
|
||||
"""Embed all chunks missing vectors in fixed-size batches."""
|
||||
total = 0
|
||||
batches = 0
|
||||
try:
|
||||
while True:
|
||||
count = await embed_missing_chunks(session, client, config)
|
||||
if count == 0:
|
||||
break
|
||||
await session.commit()
|
||||
total += count
|
||||
batches += 1
|
||||
logger.info(f"ebook_admin_embed_all_batch_complete {batches=} {count=} {total=}")
|
||||
except Exception as error:
|
||||
logger.exception(f"ebook_admin_embed_all_failed {batches=} {total=}")
|
||||
return error_response(request, f"Embed all failed after {total} chunks in {batches} batches: {error}")
|
||||
|
||||
logger.info(f"ebook_admin_embed_all_complete {batches=} {total=}")
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"partials/admin_status.html",
|
||||
{"message": f"Embedded {total} chunks in {batches} batches of {config.embedding_batch_size}"},
|
||||
)
|
||||
@@ -1,92 +0,0 @@
|
||||
"""Liveness and readiness routes for the EPUB search service."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from http import HTTPStatus
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from fastapi import APIRouter
|
||||
from fastapi.responses import JSONResponse
|
||||
from sqlalchemy import literal, select
|
||||
from sqlalchemy.exc import SQLAlchemyError
|
||||
|
||||
from python.ebook_search.api.dependencies import ( # noqa: TC001 FastAPI resolves these annotated dependencies at runtime
|
||||
AppConfig,
|
||||
AppHttpClient,
|
||||
)
|
||||
from python.ebook_search.bm25_corpus import bm25_index_exists, bm25_index_path, read_bm25_manifest
|
||||
from python.ebook_search.llm_interface import check_chat_endpoint, check_embedding_endpoint
|
||||
from python.fastapi_tools import AsyncDbSession # noqa: TC001 FastAPI resolves this annotated dependency at runtime
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import httpx
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from python.ebook_search.config import EbookSearchConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.get("/health")
|
||||
async def health() -> dict[str, str]:
|
||||
"""Liveness probe that returns ok without touching dependencies."""
|
||||
return {"status": "ok"}
|
||||
|
||||
|
||||
@router.get("/ready")
|
||||
async def ready(config: AppConfig, session: AsyncDbSession, client: AppHttpClient) -> JSONResponse:
|
||||
"""Readiness probe reporting database, embedding endpoint, and BM25 index status."""
|
||||
database_ok = await check_database(session)
|
||||
embedding_ok = await check_embedding_endpoint(client, config)
|
||||
chat_status = await chat_endpoint_status(client, config)
|
||||
bm25_status = check_bm25_status(config)
|
||||
|
||||
checks = {
|
||||
"database": "ok" if database_ok else "fail",
|
||||
"embedding": "ok" if embedding_ok else "fail",
|
||||
"chat": chat_status,
|
||||
"bm25": bm25_status,
|
||||
}
|
||||
if not database_ok:
|
||||
status = "unavailable"
|
||||
status_code = HTTPStatus.SERVICE_UNAVAILABLE
|
||||
elif not embedding_ok or chat_status == "fail" or bm25_status == "missing":
|
||||
status = "degraded"
|
||||
status_code = HTTPStatus.OK
|
||||
else:
|
||||
status = "ready"
|
||||
status_code = HTTPStatus.OK
|
||||
|
||||
logger.info(f"ebook_ready_check {status=} {database_ok=} {embedding_ok=} {chat_status=} {bm25_status=}")
|
||||
return JSONResponse(content={"status": status, "checks": checks}, status_code=status_code)
|
||||
|
||||
|
||||
async def chat_endpoint_status(client: httpx.AsyncClient, config: EbookSearchConfig) -> str:
|
||||
"""Return the answering chat endpoint status, or disabled when answers are off."""
|
||||
if not config.answer_enabled:
|
||||
return "disabled"
|
||||
return "ok" if await check_chat_endpoint(client, config) else "fail"
|
||||
|
||||
|
||||
async def check_database(session: AsyncSession) -> bool:
|
||||
"""Return whether the database answers a trivial query."""
|
||||
try:
|
||||
await session.execute(select(literal(1)))
|
||||
except SQLAlchemyError as error:
|
||||
logger.warning(f"ebook_ready_database_unavailable {error=}")
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def check_bm25_status(config: EbookSearchConfig) -> str:
|
||||
"""Return the persisted BM25 index status without loading it into memory."""
|
||||
index_path = bm25_index_path(config)
|
||||
manifest = read_bm25_manifest(index_path)
|
||||
if manifest is None or not bm25_index_exists(index_path, manifest):
|
||||
return "missing"
|
||||
if manifest.chunk_count == 0:
|
||||
return "empty"
|
||||
return "ok"
|
||||
@@ -1,187 +0,0 @@
|
||||
"""Page routes for the EPUB search web UI."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from fastapi import APIRouter, BackgroundTasks, HTTPException, Request
|
||||
from fastapi.responses import HTMLResponse, RedirectResponse
|
||||
from sqlalchemy import func, select
|
||||
|
||||
from python.ebook_search.api.dependencies import (
|
||||
AppConfig, # noqa: TC001 FastAPI resolves this annotated dependency at runtime
|
||||
)
|
||||
from python.ebook_search.api.judge_tasks import is_judging_book, pop_book_judgment_outcome, start_book_phrase_judgment
|
||||
from python.ebook_search.api.web import templates
|
||||
from python.ebook_search.protected_phrases.generate_ngrams import recalculate_candidate_phrases_for_book
|
||||
from python.ebook_search.protected_phrases.store import count_protected_phrases
|
||||
from python.fastapi_tools import AsyncDbSession # noqa: TC001 FastAPI resolves this annotated dependency at runtime
|
||||
from python.orm.richie import EbookCandidatePhrase, EbookChapter, EbookChunk, EbookProtectedPhrase, EbookSource
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.get("/", response_class=HTMLResponse)
|
||||
async def index(request: Request, config: AppConfig) -> HTMLResponse:
|
||||
"""Render the search page."""
|
||||
return templates.TemplateResponse(request, "search.html", {"config": config})
|
||||
|
||||
|
||||
@router.get("/books", response_class=HTMLResponse)
|
||||
async def books(request: Request, session: AsyncDbSession) -> HTMLResponse:
|
||||
"""Render the indexed books page."""
|
||||
sources = list((await session.scalars(select(EbookSource).order_by(EbookSource.title))).all())
|
||||
logger.info(f"ebook_books_page_loaded count={len(sources)}")
|
||||
return templates.TemplateResponse(request, "books.html", {"sources": sources})
|
||||
|
||||
|
||||
async def get_chapter_count(session: AsyncSession, book_id: int) -> int:
|
||||
"""Return the number of indexed chapters for one book."""
|
||||
return await session.scalar(select(func.count(EbookChapter.id)).where(EbookChapter.source_id == book_id)) or 0
|
||||
|
||||
|
||||
async def get_chunk_count(session: AsyncSession, book_id: int) -> int:
|
||||
"""Return the number of indexed chunks for one book."""
|
||||
return await session.scalar(select(func.count(EbookChunk.id)).where(EbookChunk.source_id == book_id)) or 0
|
||||
|
||||
|
||||
async def get_candidate_count(session: AsyncSession, book_id: int) -> int:
|
||||
"""Return the number of indexed candidates for one book."""
|
||||
return (
|
||||
await session.scalar(select(func.count(EbookCandidatePhrase.id)).where(EbookCandidatePhrase.book_id == book_id))
|
||||
or 0
|
||||
)
|
||||
|
||||
|
||||
async def get_judged_candidate_count(session: AsyncSession, book_id: int) -> int:
|
||||
"""Return the number of judged candidates for one book."""
|
||||
return (
|
||||
await session.scalar(
|
||||
select(func.count(EbookCandidatePhrase.id)).where(
|
||||
EbookCandidatePhrase.book_id == book_id,
|
||||
EbookCandidatePhrase.llm_judged.is_(True),
|
||||
)
|
||||
)
|
||||
or 0
|
||||
)
|
||||
|
||||
|
||||
async def get_candidates(session: AsyncSession, book_id: int) -> list[EbookCandidatePhrase]:
|
||||
"""Return the indexed candidates for one book."""
|
||||
return list(
|
||||
await session.scalars(
|
||||
select(EbookCandidatePhrase)
|
||||
.where(EbookCandidatePhrase.book_id == book_id)
|
||||
.order_by(EbookCandidatePhrase.candidate_score.desc())
|
||||
.limit(100)
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
async def get_protected_phrases(session: AsyncSession, book_id: int) -> list[EbookProtectedPhrase]:
|
||||
"""Return the protected phrases for one book."""
|
||||
return list(
|
||||
await session.scalars(
|
||||
select(EbookProtectedPhrase)
|
||||
.where(EbookProtectedPhrase.book_id == book_id)
|
||||
.order_by(EbookProtectedPhrase.importance.desc())
|
||||
.limit(100)
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@router.get("/books/{source_id}", response_class=HTMLResponse)
|
||||
async def book_detail(source_id: int, request: Request, session: AsyncDbSession) -> HTMLResponse:
|
||||
"""Render details for one indexed book."""
|
||||
source = await session.get(EbookSource, source_id)
|
||||
phrase_status_message = None
|
||||
recalculated = request.query_params.get("phrases_recalculated")
|
||||
if recalculated is not None:
|
||||
phrase_status_message = f"Recalculated phrases; {recalculated} candidates generated"
|
||||
judgment_outcome = pop_book_judgment_outcome(request.app, source_id)
|
||||
if judgment_outcome is not None:
|
||||
phrase_status_message = judgment_outcome
|
||||
judging_in_progress = is_judging_book(request.app, source_id)
|
||||
if judging_in_progress:
|
||||
phrase_status_message = "Judging candidate phrases in the background; refresh to see progress"
|
||||
if source is not None:
|
||||
chapter_count = await get_chapter_count(session, source.id)
|
||||
chunk_count = await get_chunk_count(session, source.id)
|
||||
candidate_count = await get_candidate_count(session, source.id)
|
||||
judged_candidate_count = await get_judged_candidate_count(session, source.id)
|
||||
protected_count = await count_protected_phrases(session, source.id)
|
||||
candidates = await get_candidates(session, source.id)
|
||||
protected_phrases = await get_protected_phrases(session, source.id)
|
||||
else:
|
||||
chapter_count = 0
|
||||
chunk_count = 0
|
||||
candidate_count = 0
|
||||
judged_candidate_count = 0
|
||||
protected_count = 0
|
||||
candidates = []
|
||||
protected_phrases = []
|
||||
logger.info(
|
||||
f"ebook_book_detail_loaded {source_id=} found={source is not None} {chapter_count=} {chunk_count=} "
|
||||
f"{candidate_count=} {judged_candidate_count=} {protected_count=}"
|
||||
)
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"book_detail.html",
|
||||
{
|
||||
"candidate_count": candidate_count,
|
||||
"candidates": candidates,
|
||||
"chapter_count": chapter_count,
|
||||
"chunk_count": chunk_count,
|
||||
"judged_candidate_count": judged_candidate_count,
|
||||
"judging_in_progress": judging_in_progress,
|
||||
"protected_count": protected_count,
|
||||
"protected_phrases": protected_phrases,
|
||||
"phrase_status_message": phrase_status_message,
|
||||
"source": source,
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
@router.post("/books/{source_id}/recalculate-phrases")
|
||||
async def recalculate_book_phrases(source_id: int, config: AppConfig, session: AsyncDbSession) -> RedirectResponse:
|
||||
"""Clear and regenerate candidate phrases for one indexed book."""
|
||||
source = await session.get(EbookSource, source_id)
|
||||
if source is None:
|
||||
raise HTTPException(status_code=404, detail="Book not found")
|
||||
|
||||
try:
|
||||
result = await recalculate_candidate_phrases_for_book(session, source, config)
|
||||
except ValueError as error:
|
||||
raise HTTPException(status_code=409, detail=str(error)) from error
|
||||
logger.info(
|
||||
f"ebook_book_phrase_recalculation_complete {source_id=} {result.candidate_phrases=} "
|
||||
f"{result.deleted_candidates=} {result.deleted_protected_phrases=} {result.deleted_aliases=} "
|
||||
f"{result.deleted_mentions=}"
|
||||
)
|
||||
return RedirectResponse(
|
||||
url=f"/books/{source_id}?phrases_recalculated={result.candidate_phrases}",
|
||||
status_code=303,
|
||||
)
|
||||
|
||||
|
||||
@router.post("/books/{source_id}/judge-phrases")
|
||||
async def judge_book_phrases(
|
||||
source_id: int,
|
||||
request: Request,
|
||||
background_tasks: BackgroundTasks,
|
||||
session: AsyncDbSession,
|
||||
) -> RedirectResponse:
|
||||
"""Queue background judging of one book's candidate phrases and return immediately."""
|
||||
source = await session.get(EbookSource, source_id)
|
||||
if source is None:
|
||||
raise HTTPException(status_code=404, detail="Book not found")
|
||||
|
||||
started = start_book_phrase_judgment(request.app, background_tasks, source.id)
|
||||
logger.info(f"ebook_book_phrase_judgment_requested {source_id=} {started=}")
|
||||
return RedirectResponse(url=f"/books/{source_id}", status_code=303)
|
||||
@@ -1,123 +0,0 @@
|
||||
"""Search routes for the EPUB search web UI."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from dataclasses import replace
|
||||
from time import perf_counter
|
||||
from typing import TYPE_CHECKING, Annotated
|
||||
|
||||
from fastapi import APIRouter, Form, Request
|
||||
from fastapi.responses import HTMLResponse
|
||||
|
||||
from python.ebook_search.answer import answer_query
|
||||
from python.ebook_search.api.dependencies import ( # noqa: TC001 FastAPI resolves these annotated dependencies at runtime
|
||||
AppConfig,
|
||||
AppHttpClient,
|
||||
)
|
||||
from python.ebook_search.api.web import error_response, templates
|
||||
from python.ebook_search.guardrails import (
|
||||
CitationReport,
|
||||
is_confident,
|
||||
retrieval_confidence,
|
||||
validate_citations,
|
||||
)
|
||||
from python.ebook_search.search import SearchResponse, search_ebooks
|
||||
from python.ebook_search.timing import runtime_step_from_start
|
||||
from python.fastapi_tools import AppAsyncEngine # noqa: TC001 FastAPI resolves this annotated dependency at runtime
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import httpx
|
||||
|
||||
from python.ebook_search.config import EbookSearchConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
async def build_answer(
|
||||
client: httpx.AsyncClient,
|
||||
query: str,
|
||||
response: SearchResponse,
|
||||
config: EbookSearchConfig,
|
||||
) -> tuple[str, bool, CitationReport | None]:
|
||||
"""Generate the answer for a search, returning ``(answer, low_confidence, citation_report)``."""
|
||||
if not config.answer_enabled:
|
||||
logger.info("ebook_answer_skipped_disabled")
|
||||
return "Answer generation is disabled. Source chunks are shown below.", False, None
|
||||
|
||||
if not is_confident(response.results, config):
|
||||
logger.info(
|
||||
f"ebook_answer_low_confidence confidence={retrieval_confidence(response.results):.4f} "
|
||||
f"{config.min_retrieval_confidence=:.4f}"
|
||||
)
|
||||
answer = (
|
||||
"Retrieval confidence is low for this query, so answer generation was skipped. "
|
||||
"Source chunks are shown below."
|
||||
)
|
||||
return answer, True, None
|
||||
|
||||
try:
|
||||
answer = await answer_query(client, query, response.results, config)
|
||||
except RuntimeError as error:
|
||||
logger.warning(f"ebook_answer_request_failed_falling_back {error=}")
|
||||
return "Answer generation failed. Source chunks are still shown below.", False, None
|
||||
|
||||
citation_report = None
|
||||
if config.validate_citations_enabled and response.results:
|
||||
citation_report = validate_citations(answer, len(response.results))
|
||||
if citation_report.invalid or not citation_report.grounded:
|
||||
logger.warning(f"ebook_answer_citation_issue {citation_report.invalid=} {citation_report.grounded=}")
|
||||
return answer, False, citation_report
|
||||
|
||||
|
||||
@router.post("/search", response_class=HTMLResponse)
|
||||
async def search(
|
||||
request: Request,
|
||||
config: AppConfig,
|
||||
engine: AppAsyncEngine,
|
||||
client: AppHttpClient,
|
||||
query: Annotated[str, Form()],
|
||||
*,
|
||||
rerank: Annotated[bool, Form()] = False,
|
||||
phrase_matching: Annotated[bool, Form()] = False,
|
||||
) -> HTMLResponse:
|
||||
"""Run a search and render HTMX results."""
|
||||
try:
|
||||
response = await search_ebooks(
|
||||
engine,
|
||||
client,
|
||||
query,
|
||||
config,
|
||||
rerank=rerank,
|
||||
phrase_matching=phrase_matching,
|
||||
)
|
||||
except Exception as error:
|
||||
logger.exception("ebook_search_request_failed")
|
||||
return error_response(request, error)
|
||||
|
||||
answer_start = perf_counter()
|
||||
answer, low_confidence, citation_report = await build_answer(client, query, response, config)
|
||||
answer_step_name = "Answer generation" if config.answer_enabled else "Answer skipped"
|
||||
response = replace(
|
||||
response,
|
||||
timings=(*response.timings, runtime_step_from_start(answer_step_name, answer_start)),
|
||||
)
|
||||
|
||||
for step in response.timings:
|
||||
logger.info(f"ebook_search_timing {step.name=} {step.duration_ms=:.1f}")
|
||||
logger.info(
|
||||
f"ebook_search_request_complete results={len(response.results)} {response.rank_label=} "
|
||||
f"{response.total_runtime_ms=:.1f}"
|
||||
)
|
||||
return templates.TemplateResponse(
|
||||
request,
|
||||
"partials/results.html",
|
||||
{
|
||||
"answer": answer,
|
||||
"response": response,
|
||||
"low_confidence": low_confidence,
|
||||
"citation_report": citation_report,
|
||||
},
|
||||
)
|
||||
@@ -1,447 +0,0 @@
|
||||
:root {
|
||||
--bg: #f4f5f7;
|
||||
--surface: #ffffff;
|
||||
--border: #e3e5ea;
|
||||
--text: #1c1f24;
|
||||
--muted: #6b7280;
|
||||
--accent: #4f46e5;
|
||||
--accent-soft: #eef0fe;
|
||||
--danger: #b42318;
|
||||
--warn-bg: #fff8eb;
|
||||
--warn-border: #e0a92e;
|
||||
--warn-text: #7a5008;
|
||||
--radius: 12px;
|
||||
--shadow: 0 1px 2px rgba(16, 24, 40, 0.04), 0 1px 3px rgba(16, 24, 40, 0.08);
|
||||
}
|
||||
|
||||
html.theme-dark {
|
||||
--bg: #0f1117;
|
||||
--surface: #1a1d25;
|
||||
--border: #2b303b;
|
||||
--text: #e6e8ec;
|
||||
--muted: #9aa1ad;
|
||||
--accent: #818cf8;
|
||||
--accent-soft: #262b45;
|
||||
--danger: #f97066;
|
||||
--warn-bg: #2a2410;
|
||||
--warn-border: #b9881f;
|
||||
--warn-text: #e8c97a;
|
||||
--shadow: 0 1px 2px rgba(0, 0, 0, 0.3), 0 1px 3px rgba(0, 0, 0, 0.4);
|
||||
color-scheme: dark;
|
||||
}
|
||||
|
||||
* {
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
body {
|
||||
margin: 0;
|
||||
background: var(--bg);
|
||||
color: var(--text);
|
||||
font-family: system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
|
||||
line-height: 1.55;
|
||||
}
|
||||
|
||||
main {
|
||||
max-width: 820px;
|
||||
margin: 0 auto;
|
||||
padding: 32px 20px 64px;
|
||||
}
|
||||
|
||||
/* Header / nav */
|
||||
.site-header {
|
||||
background: var(--surface);
|
||||
border-bottom: 1px solid var(--border);
|
||||
position: sticky;
|
||||
top: 0;
|
||||
z-index: 10;
|
||||
}
|
||||
|
||||
.site-nav {
|
||||
max-width: 820px;
|
||||
margin: 0 auto;
|
||||
padding: 12px 20px;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 20px;
|
||||
}
|
||||
|
||||
.brand {
|
||||
font-weight: 700;
|
||||
font-size: 1.05rem;
|
||||
color: var(--text);
|
||||
text-decoration: none;
|
||||
}
|
||||
|
||||
.nav-links {
|
||||
display: flex;
|
||||
gap: 6px;
|
||||
margin-right: auto;
|
||||
}
|
||||
|
||||
.nav-links a {
|
||||
padding: 6px 12px;
|
||||
border-radius: 8px;
|
||||
color: var(--muted);
|
||||
text-decoration: none;
|
||||
font-size: 0.94rem;
|
||||
transition: background 0.15s, color 0.15s;
|
||||
}
|
||||
|
||||
.nav-links a:hover {
|
||||
background: var(--accent-soft);
|
||||
color: var(--accent);
|
||||
}
|
||||
|
||||
.dev-toggle {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
gap: 6px;
|
||||
font-size: 0.85rem;
|
||||
color: var(--muted);
|
||||
cursor: pointer;
|
||||
user-select: none;
|
||||
}
|
||||
|
||||
.theme-toggle {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
width: 34px;
|
||||
height: 34px;
|
||||
padding: 0;
|
||||
font-size: 1rem;
|
||||
line-height: 1;
|
||||
color: var(--text);
|
||||
background: var(--bg);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 8px;
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
.theme-toggle:hover {
|
||||
border-color: var(--accent);
|
||||
filter: none;
|
||||
}
|
||||
|
||||
h1 {
|
||||
font-size: 1.6rem;
|
||||
margin: 0 0 20px;
|
||||
}
|
||||
|
||||
h2 {
|
||||
font-size: 1.15rem;
|
||||
margin: 0 0 8px;
|
||||
}
|
||||
|
||||
/* Cards */
|
||||
.card {
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius);
|
||||
box-shadow: var(--shadow);
|
||||
padding: 20px;
|
||||
}
|
||||
|
||||
/* Search form */
|
||||
form {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
label {
|
||||
font-weight: 600;
|
||||
font-size: 0.92rem;
|
||||
}
|
||||
|
||||
textarea {
|
||||
display: block;
|
||||
width: 100%;
|
||||
margin: 8px 0 16px;
|
||||
padding: 12px 14px;
|
||||
font: inherit;
|
||||
color: var(--text);
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 10px;
|
||||
resize: vertical;
|
||||
transition: border-color 0.15s, box-shadow 0.15s;
|
||||
}
|
||||
|
||||
textarea:focus {
|
||||
outline: none;
|
||||
border-color: var(--accent);
|
||||
box-shadow: 0 0 0 3px var(--accent-soft);
|
||||
}
|
||||
|
||||
.form-row {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
.search-toggles {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
gap: 14px;
|
||||
}
|
||||
|
||||
button {
|
||||
padding: 10px 20px;
|
||||
font: inherit;
|
||||
font-weight: 600;
|
||||
color: #fff;
|
||||
background: var(--accent);
|
||||
border: none;
|
||||
border-radius: 10px;
|
||||
cursor: pointer;
|
||||
transition: filter 0.15s;
|
||||
}
|
||||
|
||||
button:hover {
|
||||
filter: brightness(1.08);
|
||||
}
|
||||
|
||||
.check {
|
||||
display: inline-flex;
|
||||
gap: 8px;
|
||||
align-items: center;
|
||||
font-weight: 500;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.actions {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
gap: 12px;
|
||||
margin-bottom: 24px;
|
||||
}
|
||||
|
||||
.actions-grid {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(2, max-content);
|
||||
}
|
||||
|
||||
/* Answer + results */
|
||||
#results {
|
||||
display: block;
|
||||
margin-top: 28px;
|
||||
}
|
||||
|
||||
.rank-label {
|
||||
font-size: 0.82rem;
|
||||
font-weight: 600;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 0.04em;
|
||||
color: var(--muted);
|
||||
margin-bottom: 16px;
|
||||
}
|
||||
|
||||
.answer {
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius);
|
||||
box-shadow: var(--shadow);
|
||||
padding: 20px;
|
||||
margin-bottom: 24px;
|
||||
}
|
||||
|
||||
.answer p:last-child {
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
.results {
|
||||
list-style: none;
|
||||
padding: 0;
|
||||
margin: 0;
|
||||
display: grid;
|
||||
gap: 16px;
|
||||
}
|
||||
|
||||
.results > li {
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius);
|
||||
box-shadow: var(--shadow);
|
||||
padding: 18px 20px;
|
||||
}
|
||||
|
||||
.results h2 {
|
||||
font-size: 1.05rem;
|
||||
}
|
||||
|
||||
.results h2 a {
|
||||
color: var(--text);
|
||||
text-decoration: none;
|
||||
}
|
||||
|
||||
.results h2 a:hover {
|
||||
color: var(--accent);
|
||||
}
|
||||
|
||||
.meta {
|
||||
color: var(--muted);
|
||||
font-size: 0.88rem;
|
||||
margin: 0 0 10px;
|
||||
}
|
||||
|
||||
.scores {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
gap: 8px;
|
||||
margin: 14px 0 0;
|
||||
}
|
||||
|
||||
.scores div {
|
||||
display: inline-flex;
|
||||
gap: 6px;
|
||||
align-items: baseline;
|
||||
padding: 3px 10px;
|
||||
background: var(--bg);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 999px;
|
||||
font-size: 0.78rem;
|
||||
}
|
||||
|
||||
.scores dt {
|
||||
font-weight: 600;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.scores dd {
|
||||
margin: 0;
|
||||
font-variant-numeric: tabular-nums;
|
||||
}
|
||||
|
||||
.phrase-matches {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
gap: 8px;
|
||||
align-items: baseline;
|
||||
margin: 10px 0 0;
|
||||
font-size: 0.78rem;
|
||||
}
|
||||
|
||||
.phrase-matches-label {
|
||||
color: var(--muted);
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
.phrase-match {
|
||||
padding: 3px 10px;
|
||||
background: var(--bg);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 999px;
|
||||
color: var(--accent);
|
||||
}
|
||||
|
||||
/* Runtime — developer diagnostics, hidden unless dev mode is on */
|
||||
.runtime {
|
||||
display: none;
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius);
|
||||
box-shadow: var(--shadow);
|
||||
padding: 18px 20px;
|
||||
margin-bottom: 24px;
|
||||
}
|
||||
|
||||
html.dev .runtime {
|
||||
display: block;
|
||||
}
|
||||
|
||||
.timing-chart {
|
||||
display: grid;
|
||||
gap: 8px;
|
||||
padding: 0;
|
||||
margin: 12px 0 0;
|
||||
list-style: none;
|
||||
}
|
||||
|
||||
.timing-chart li {
|
||||
display: grid;
|
||||
grid-template-columns: minmax(150px, 1fr) minmax(160px, 2fr) auto auto;
|
||||
gap: 10px;
|
||||
align-items: center;
|
||||
font-size: 0.85rem;
|
||||
}
|
||||
|
||||
.timing-bar {
|
||||
height: 8px;
|
||||
overflow: hidden;
|
||||
background: var(--bg);
|
||||
border-radius: 999px;
|
||||
}
|
||||
|
||||
.timing-bar span {
|
||||
display: block;
|
||||
height: 100%;
|
||||
background: var(--accent);
|
||||
border-radius: 999px;
|
||||
}
|
||||
|
||||
.timing-value,
|
||||
.timing-remaining {
|
||||
color: var(--muted);
|
||||
font-variant-numeric: tabular-nums;
|
||||
text-align: right;
|
||||
}
|
||||
|
||||
/* Tables */
|
||||
table {
|
||||
width: 100%;
|
||||
border-collapse: collapse;
|
||||
background: var(--surface);
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius);
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
th,
|
||||
td {
|
||||
padding: 10px 14px;
|
||||
border-bottom: 1px solid var(--border);
|
||||
text-align: left;
|
||||
font-size: 0.9rem;
|
||||
}
|
||||
|
||||
th {
|
||||
font-weight: 600;
|
||||
color: var(--muted);
|
||||
background: var(--bg);
|
||||
}
|
||||
|
||||
tbody tr:last-child td {
|
||||
border-bottom: none;
|
||||
}
|
||||
|
||||
dl dt {
|
||||
font-weight: 600;
|
||||
color: var(--muted);
|
||||
font-size: 0.85rem;
|
||||
}
|
||||
|
||||
dl dd {
|
||||
margin: 0 0 12px;
|
||||
}
|
||||
|
||||
/* States */
|
||||
.error {
|
||||
color: var(--danger);
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
.notice {
|
||||
margin: 12px 0;
|
||||
padding: 10px 14px;
|
||||
border-left: 3px solid var(--warn-border);
|
||||
border-radius: 6px;
|
||||
background: var(--warn-bg);
|
||||
color: var(--warn-text);
|
||||
font-weight: 500;
|
||||
}
|
||||
|
||||
.status {
|
||||
color: var(--muted);
|
||||
}
|
||||
@@ -1,103 +0,0 @@
|
||||
{% extends "base.html" %} {% block title %}EPUB Admin{% endblock %} {% block
|
||||
head %}
|
||||
<script src="https://unpkg.com/htmx.org@2.0.4"></script>
|
||||
{% endblock %} {% block content %}
|
||||
<h1>Admin</h1>
|
||||
<section id="admin-status"></section>
|
||||
<section class="actions">
|
||||
<form hx-post="/admin/scan" hx-target="#admin-status" hx-swap="innerHTML">
|
||||
<button type="submit">Scan</button>
|
||||
</form>
|
||||
</section>
|
||||
<section>
|
||||
<h2>Embeddings</h2>
|
||||
<section class="actions">
|
||||
<form
|
||||
hx-post="/admin/embed-missing"
|
||||
hx-target="#admin-status"
|
||||
hx-swap="innerHTML"
|
||||
>
|
||||
<button type="submit">Embed</button>
|
||||
</form>
|
||||
<form
|
||||
hx-post="/admin/embed-all"
|
||||
hx-target="#admin-status"
|
||||
hx-swap="innerHTML"
|
||||
>
|
||||
<button type="submit">Embed all</button>
|
||||
</form>
|
||||
</section>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Model</th>
|
||||
<th>Dimensions</th>
|
||||
<th>Embedded</th>
|
||||
<th>Missing</th>
|
||||
<th>Total chunks</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
{% for item in stats %}
|
||||
<tr>
|
||||
<td>{{ item.model_name }}</td>
|
||||
<td>{{ item.dimension }}</td>
|
||||
<td>{{ item.embedded_chunks }}</td>
|
||||
<td>{{ item.missing_chunks }}</td>
|
||||
<td>{{ item.total_chunks }}</td>
|
||||
</tr>
|
||||
{% endfor %}
|
||||
</tbody>
|
||||
</table>
|
||||
</section>
|
||||
<section>
|
||||
<h2>Protected phrases</h2>
|
||||
<section class="actions actions-grid">
|
||||
<form
|
||||
hx-post="/admin/phrases/generate-all"
|
||||
hx-target="#admin-status"
|
||||
hx-swap="innerHTML"
|
||||
>
|
||||
<button type="submit">Regenerate all phrases</button>
|
||||
</form>
|
||||
<form
|
||||
hx-post="/admin/phrases/judge-all"
|
||||
hx-target="#admin-status"
|
||||
hx-swap="innerHTML"
|
||||
>
|
||||
<button type="submit">Judge all phrases</button>
|
||||
</form>
|
||||
<form
|
||||
hx-post="/admin/phrases/judge-missing"
|
||||
hx-target="#admin-status"
|
||||
hx-swap="innerHTML"
|
||||
>
|
||||
<button type="submit">Judge missing phrases</button>
|
||||
</form>
|
||||
</section>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Candidates</th>
|
||||
<th>Judged</th>
|
||||
<th>Unjudged</th>
|
||||
<th>Protected</th>
|
||||
<th>Books indexed</th>
|
||||
<th>Books generated</th>
|
||||
<th>Books fully judged</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td>{{ phrase_stats.candidate_phrases }}</td>
|
||||
<td>{{ phrase_stats.judged_candidates }}</td>
|
||||
<td>{{ phrase_stats.unjudged_candidates }}</td>
|
||||
<td>{{ phrase_stats.protected_phrases }}</td>
|
||||
<td>{{ phrase_stats.total_books }}</td>
|
||||
<td>{{ phrase_stats.books_with_candidates }}</td>
|
||||
<td>{{ phrase_stats.books_fully_judged }}</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</section>
|
||||
{% endblock %}
|
||||
@@ -1,71 +0,0 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>{% block title %}EPUB Search{% endblock %}</title>
|
||||
{% block head %}{% endblock %}
|
||||
<link rel="stylesheet" href="/static/style.css?v={{ static_version('style.css') }}">
|
||||
<script>
|
||||
// Apply theme and dev mode before paint to avoid a flash of unstyled/wrong content.
|
||||
(function () {
|
||||
var stored = localStorage.getItem("ebook-theme");
|
||||
var prefersDark = window.matchMedia("(prefers-color-scheme: dark)").matches;
|
||||
var theme = stored || (prefersDark ? "dark" : "light");
|
||||
document.documentElement.classList.add("theme-" + theme);
|
||||
if (localStorage.getItem("ebook-dev-mode") === "on") {
|
||||
document.documentElement.classList.add("dev");
|
||||
}
|
||||
})();
|
||||
</script>
|
||||
</head>
|
||||
<body>
|
||||
<header class="site-header">
|
||||
<nav class="site-nav">
|
||||
<a class="brand" href="/">EPUB Search</a>
|
||||
<div class="nav-links">
|
||||
<a href="/">Search</a>
|
||||
<a href="/books">Books</a>
|
||||
<a href="/admin">Admin</a>
|
||||
</div>
|
||||
<button type="button" id="theme-toggle" class="theme-toggle" title="Toggle light / dark theme" aria-label="Toggle theme"></button>
|
||||
<label class="dev-toggle" title="Show developer diagnostics">
|
||||
<input type="checkbox" id="dev-mode-toggle">
|
||||
<span>Dev</span>
|
||||
</label>
|
||||
</nav>
|
||||
</header>
|
||||
<main>
|
||||
{% block content %}{% endblock %}
|
||||
</main>
|
||||
<script>
|
||||
(function () {
|
||||
var toggle = document.getElementById("dev-mode-toggle");
|
||||
if (toggle) {
|
||||
toggle.checked = document.documentElement.classList.contains("dev");
|
||||
toggle.addEventListener("change", function () {
|
||||
document.documentElement.classList.toggle("dev", toggle.checked);
|
||||
localStorage.setItem("ebook-dev-mode", toggle.checked ? "on" : "off");
|
||||
});
|
||||
}
|
||||
|
||||
var themeButton = document.getElementById("theme-toggle");
|
||||
if (themeButton) {
|
||||
var root = document.documentElement;
|
||||
var sync = function () {
|
||||
var isDark = root.classList.contains("theme-dark");
|
||||
themeButton.textContent = isDark ? "☀️" : "🌙";
|
||||
};
|
||||
sync();
|
||||
themeButton.addEventListener("click", function () {
|
||||
var next = root.classList.contains("theme-dark") ? "light" : "dark";
|
||||
root.classList.remove("theme-dark", "theme-light");
|
||||
root.classList.add("theme-" + next);
|
||||
localStorage.setItem("ebook-theme", next);
|
||||
sync();
|
||||
});
|
||||
}
|
||||
})();
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -1,109 +0,0 @@
|
||||
{% extends "base.html" %}
|
||||
|
||||
{% block title %}{% if source %}{{ source.title }}{% else %}Book not found{% endif %}{% endblock %}
|
||||
|
||||
{% block content %}
|
||||
{% if source %}
|
||||
<h1>{{ source.title }}</h1>
|
||||
<p class="meta">{{ source.author or "Unknown author" }}</p>
|
||||
{% if phrase_status_message %}
|
||||
<p class="status">{{ phrase_status_message }}</p>
|
||||
{% endif %}
|
||||
<dl class="card">
|
||||
<dt>File</dt>
|
||||
<dd>{{ source.file_path }}</dd>
|
||||
<dt>Chapters</dt>
|
||||
<dd>{{ chapter_count }}</dd>
|
||||
<dt>Chunks</dt>
|
||||
<dd>{{ chunk_count }}</dd>
|
||||
<dt>Candidates</dt>
|
||||
<dd>{{ candidate_count }}</dd>
|
||||
<dt>Judged</dt>
|
||||
<dd>{{ judged_candidate_count }}</dd>
|
||||
<dt>Protected</dt>
|
||||
<dd>{{ protected_count }}</dd>
|
||||
</dl>
|
||||
<form
|
||||
method="post"
|
||||
action="/books/{{ source.id }}/recalculate-phrases"
|
||||
onsubmit="return confirm('Remove old phrases for this book and generate new candidates?');"
|
||||
>
|
||||
<button type="submit">Recalculate phrases</button>
|
||||
</form>
|
||||
<form
|
||||
method="post"
|
||||
action="/books/{{ source.id }}/judge-phrases"
|
||||
onsubmit="return confirm('Judge candidate phrases for this book with the LLM?');"
|
||||
>
|
||||
<button type="submit"{% if judging_in_progress %} disabled{% endif %}>
|
||||
{% if judging_in_progress %}Judging…{% else %}Judge phrases{% endif %}
|
||||
</button>
|
||||
</form>
|
||||
|
||||
<section>
|
||||
<h2>Candidate n-grams</h2>
|
||||
{% if candidates %}
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Phrase</th>
|
||||
<th>Status</th>
|
||||
<th>Score</th>
|
||||
<th>Count</th>
|
||||
<th>Chapters</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
{% for candidate in candidates %}
|
||||
<tr>
|
||||
<td>{{ candidate.phrase_text }}</td>
|
||||
<td>
|
||||
{% if candidate.llm_judged %}
|
||||
{% if candidate.llm_keep %}Kept{% else %}Rejected{% endif %}
|
||||
{% else %}
|
||||
Candidate
|
||||
{% endif %}
|
||||
</td>
|
||||
<td>{{ "%.2f"|format(candidate.candidate_score) }}</td>
|
||||
<td>{{ candidate.raw_count }}</td>
|
||||
<td>{{ candidate.chapter_count }}</td>
|
||||
</tr>
|
||||
{% endfor %}
|
||||
</tbody>
|
||||
</table>
|
||||
{% else %}
|
||||
<p>No candidate n-grams.</p>
|
||||
{% endif %}
|
||||
</section>
|
||||
|
||||
<section>
|
||||
<h2>Protected phrases</h2>
|
||||
{% if protected_phrases %}
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Phrase</th>
|
||||
<th>Type</th>
|
||||
<th>Confidence</th>
|
||||
<th>Importance</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
{% for phrase in protected_phrases %}
|
||||
<tr>
|
||||
<td>{{ phrase.phrase_text }}</td>
|
||||
<td>{{ phrase.phrase_type or "phrase" }}</td>
|
||||
<td>{{ "%.2f"|format(phrase.confidence) }}</td>
|
||||
<td>{{ "%.2f"|format(phrase.importance) }}</td>
|
||||
</tr>
|
||||
{% endfor %}
|
||||
</tbody>
|
||||
</table>
|
||||
{% else %}
|
||||
<p>No protected phrases.</p>
|
||||
{% endif %}
|
||||
</section>
|
||||
{% else %}
|
||||
<h1>Book not found</h1>
|
||||
{% endif %}
|
||||
{% endblock %}
|
||||
@@ -1,19 +0,0 @@
|
||||
{% extends "base.html" %}
|
||||
|
||||
{% block title %}EPUB Books{% endblock %}
|
||||
|
||||
{% block content %}
|
||||
<h1>Books</h1>
|
||||
{% if sources %}
|
||||
<ol class="results">
|
||||
{% for source in sources %}
|
||||
<li>
|
||||
<h2><a href="/books/{{ source.id }}">{{ source.title }}</a></h2>
|
||||
<p class="meta">{{ source.author or "Unknown author" }}</p>
|
||||
</li>
|
||||
{% endfor %}
|
||||
</ol>
|
||||
{% else %}
|
||||
<p>No EPUBs indexed.</p>
|
||||
{% endif %}
|
||||
{% endblock %}
|
||||
@@ -1 +0,0 @@
|
||||
<p class="status">{{ message }}</p>
|
||||
@@ -1 +0,0 @@
|
||||
<p class="error">{{ message }}</p>
|
||||
@@ -1,98 +0,0 @@
|
||||
<div class="rank-label">{{ response.rank_label }}</div>
|
||||
{% if response.timings %}
|
||||
<section class="runtime">
|
||||
<h2>Runtime</h2>
|
||||
<p class="meta">Total {{ "%.1f"|format(response.total_runtime_ms) }} ms</p>
|
||||
<ol class="timing-chart">
|
||||
{% set total = response.total_runtime_ms %}
|
||||
{% set ns = namespace(remaining=total) %}
|
||||
{% for step in response.timings %}
|
||||
{% set width = (step.duration_ms / total * 100) if total else 0 %}
|
||||
{% if step.counts_toward_total %}
|
||||
{% set ns.remaining = ns.remaining - step.duration_ms %}
|
||||
{% endif %}
|
||||
<li>
|
||||
<span class="timing-label">{{ step.name }}</span>
|
||||
<span class="timing-bar"><span style="width: {{ "%.2f"|format(width) }}%"></span></span>
|
||||
<span class="timing-value">{{ "%.1f"|format(step.duration_ms) }} ms</span>
|
||||
<span class="timing-remaining">{{ "%.1f"|format([ns.remaining, 0]|max) }} ms left</span>
|
||||
</li>
|
||||
{% endfor %}
|
||||
</ol>
|
||||
</section>
|
||||
{% endif %}
|
||||
<section class="answer">
|
||||
<h2>Answer</h2>
|
||||
{% if low_confidence|default(false) %}
|
||||
<p class="notice">Low retrieval confidence — answer generation was skipped.</p>
|
||||
{% endif %}
|
||||
{% set report = citation_report|default(none) %}
|
||||
{% if report is not none and not report.grounded %}
|
||||
<p class="notice">Unverified — no source citations were found in this answer.</p>
|
||||
{% endif %}
|
||||
{% if report is not none and report.invalid %}
|
||||
<p class="notice">Invalid citations: {{ report.invalid|join(", ") }} (no matching source).</p>
|
||||
{% endif %}
|
||||
<p>{{ answer }}</p>
|
||||
</section>
|
||||
{% if response.results %}
|
||||
<ol class="results">
|
||||
{% for result in response.results %}
|
||||
<li>
|
||||
<h2>
|
||||
{% if result.source_id %}
|
||||
<a href="/books/{{ result.source_id }}">{{ result.source_title }}</a>
|
||||
{% else %}
|
||||
{{ result.source_title }}
|
||||
{% endif %}
|
||||
</h2>
|
||||
<p class="meta">
|
||||
{% if result.source_author %}{{ result.source_author }}{% endif %}
|
||||
{% if result.chapter_title %} · {{ result.chapter_title }}{% endif %}
|
||||
{% if result.page_label %} · page {{ result.page_label }}{% endif %}
|
||||
</p>
|
||||
<p>{{ result.text }}</p>
|
||||
<dl class="scores">
|
||||
<div>
|
||||
<dt>final</dt>
|
||||
<dd>{{ "%.3f"|format(result.score) }}</dd>
|
||||
</div>
|
||||
{% if result.rerank_score is not none %}
|
||||
<div>
|
||||
<dt>rerank</dt>
|
||||
<dd>{{ "%.3f"|format(result.rerank_score) }}</dd>
|
||||
</div>
|
||||
{% endif %}
|
||||
{% if result.vector_score is not none %}
|
||||
<div>
|
||||
<dt>vector cosine</dt>
|
||||
<dd>{{ "%.3f"|format(result.vector_score) }}</dd>
|
||||
</div>
|
||||
{% endif %}
|
||||
{% if result.bm25_score is not none %}
|
||||
<div>
|
||||
<dt>BM25</dt>
|
||||
<dd>{{ "%.6f"|format(result.bm25_score) }}</dd>
|
||||
</div>
|
||||
{% endif %}
|
||||
{% if result.fused_score is not none %}
|
||||
<div>
|
||||
<dt>RRF</dt>
|
||||
<dd>{{ "%.3f"|format(result.fused_score) }}</dd>
|
||||
</div>
|
||||
{% endif %}
|
||||
</dl>
|
||||
{% if result.matched_phrases %}
|
||||
<p class="phrase-matches">
|
||||
<span class="phrase-matches-label">boosted by</span>
|
||||
{% for phrase in result.matched_phrases %}
|
||||
<span class="phrase-match">{{ phrase }}</span>
|
||||
{% endfor %}
|
||||
</p>
|
||||
{% endif %}
|
||||
</li>
|
||||
{% endfor %}
|
||||
</ol>
|
||||
{% else %}
|
||||
<p>No results.</p>
|
||||
{% endif %}
|
||||
@@ -1,32 +0,0 @@
|
||||
{% extends "base.html" %}
|
||||
|
||||
{% block title %}EPUB Search{% endblock %}
|
||||
{% block head %}<script src="https://unpkg.com/htmx.org@2.0.4"></script>{% endblock %}
|
||||
|
||||
{% block content %}
|
||||
<h1>Search</h1>
|
||||
<form class="card" hx-post="/search" hx-target="#results" hx-swap="innerHTML">
|
||||
<label for="query">What are you looking for?</label>
|
||||
<textarea id="query" name="query" rows="4" placeholder="Ask a question or paste a passage…" required
|
||||
onkeydown="if (event.key === 'Enter' && !event.shiftKey) { event.preventDefault(); this.form.requestSubmit(); }"></textarea>
|
||||
<div class="form-row">
|
||||
<div class="search-toggles">
|
||||
<label class="check">
|
||||
<input type="checkbox" name="rerank" value="true" {% if config.rerank.enabled %}checked{% endif %}>
|
||||
Rerank
|
||||
</label>
|
||||
<label class="check">
|
||||
<input
|
||||
type="checkbox"
|
||||
name="phrase_matching"
|
||||
value="true"
|
||||
{% if config.phrase_matching_enabled %}checked{% endif %}
|
||||
>
|
||||
Phrase matching
|
||||
</label>
|
||||
</div>
|
||||
<button type="submit">Search</button>
|
||||
</div>
|
||||
</form>
|
||||
<section id="results"></section>
|
||||
{% endblock %}
|
||||
@@ -1,33 +0,0 @@
|
||||
"""Shared web UI resources for EPUB search."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from fastapi.templating import Jinja2Templates
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from fastapi import Request
|
||||
from fastapi.responses import HTMLResponse
|
||||
|
||||
PACKAGE_DIR = Path(__file__).resolve().parent
|
||||
TEMPLATE_DIR = PACKAGE_DIR / "templates"
|
||||
STATIC_DIR = PACKAGE_DIR / "static"
|
||||
|
||||
|
||||
def static_version(filename: str) -> int:
|
||||
"""Return a cache-busting token for a static file based on its modification time."""
|
||||
try:
|
||||
return int((STATIC_DIR / filename).stat().st_mtime)
|
||||
except OSError:
|
||||
return 0
|
||||
|
||||
|
||||
templates = Jinja2Templates(directory=TEMPLATE_DIR)
|
||||
templates.env.globals["static_version"] = static_version
|
||||
|
||||
|
||||
def error_response(request: Request, message: object) -> HTMLResponse:
|
||||
"""Render the shared error partial for a failed UI request."""
|
||||
return templates.TemplateResponse(request, "partials/error.html", {"message": str(message)}, status_code=500)
|
||||
@@ -1,274 +0,0 @@
|
||||
"""Persisted BM25 corpus management."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import shutil
|
||||
from dataclasses import dataclass
|
||||
from datetime import UTC, datetime
|
||||
from functools import cache
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import bm25s
|
||||
from sqlalchemy import func, select, union_all
|
||||
|
||||
from python.ebook_search.chunk_records import CHUNK_RECORD_COLUMNS
|
||||
from python.orm.richie import EbookChapter, EbookChunk, EbookSource
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from python.ebook_search.config import EbookSearchConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
MANIFEST_NAME = "manifest.json"
|
||||
REQUIRED_INDEX_FILES = frozenset(
|
||||
{
|
||||
"data.csc.index.npy",
|
||||
"indices.csc.index.npy",
|
||||
"indptr.csc.index.npy",
|
||||
"params.index.json",
|
||||
"vocab.index.json",
|
||||
"corpus.jsonl",
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BM25Manifest:
|
||||
"""Metadata describing a persisted BM25 corpus."""
|
||||
|
||||
created_at: datetime
|
||||
db_updated_at: datetime | None
|
||||
chunk_count: int
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BM25Corpus:
|
||||
"""Loaded persisted BM25 corpus and retriever."""
|
||||
|
||||
retriever: object | None
|
||||
records: tuple[dict[str, object], ...]
|
||||
manifest: BM25Manifest
|
||||
|
||||
|
||||
class BM25CorpusUnavailableError(RuntimeError):
|
||||
"""Raised when the persisted BM25 corpus cannot be loaded."""
|
||||
|
||||
|
||||
def bm25_index_path(config: EbookSearchConfig) -> Path:
|
||||
"""Return the configured BM25 index root path relative to the current working directory."""
|
||||
path = Path(config.bm25_index_dir).expanduser()
|
||||
if path.is_absolute():
|
||||
return path
|
||||
return Path.cwd() / path
|
||||
|
||||
|
||||
def get_current_bm25_index(index_path: Path) -> Path:
|
||||
"""Return the live BM25 index directory."""
|
||||
current_path = index_path / "current"
|
||||
if current_path.exists() or current_path.is_symlink():
|
||||
return current_path
|
||||
return index_path
|
||||
|
||||
|
||||
async def ensure_bm25_corpus(session: AsyncSession, config: EbookSearchConfig) -> None:
|
||||
"""Create or refresh the persisted BM25 corpus when it is missing or stale."""
|
||||
index_path = bm25_index_path(config)
|
||||
manifest = read_bm25_manifest(index_path)
|
||||
db_updated_at = await corpus_last_updated_at(session)
|
||||
if not bm25_index_exists(index_path, manifest):
|
||||
logger.info(f"ebook_bm25_index_missing {index_path=}")
|
||||
await refresh_bm25_corpus(session, config, db_updated_at=db_updated_at)
|
||||
return
|
||||
if db_updated_at is not None and manifest is not None and manifest.created_at < db_updated_at:
|
||||
logger.info(
|
||||
f"ebook_bm25_index_stale {index_path=} created_at={manifest.created_at.isoformat()} "
|
||||
f"db_updated_at={db_updated_at.isoformat()}"
|
||||
)
|
||||
await refresh_bm25_corpus(session, config, db_updated_at=db_updated_at)
|
||||
return
|
||||
logger.info(
|
||||
f"ebook_bm25_index_current {index_path=} chunks={manifest.chunk_count if manifest else 0} "
|
||||
f"created_at={manifest.created_at.isoformat() if manifest else None}"
|
||||
)
|
||||
|
||||
|
||||
async def refresh_bm25_corpus(
|
||||
session: AsyncSession,
|
||||
config: EbookSearchConfig,
|
||||
*,
|
||||
db_updated_at: datetime | None = None,
|
||||
) -> BM25Manifest:
|
||||
"""Rebuild and persist the BM25 corpus from the current database chunks.
|
||||
|
||||
The index build is CPU and disk work, so it runs in a worker thread.
|
||||
"""
|
||||
index_path = bm25_index_path(config)
|
||||
records, texts = await fetch_bm25_corpus_records(session)
|
||||
manifest = BM25Manifest(
|
||||
created_at=datetime.now(tz=UTC),
|
||||
db_updated_at=db_updated_at if db_updated_at is not None else await corpus_last_updated_at(session),
|
||||
chunk_count=len(records),
|
||||
)
|
||||
await asyncio.to_thread(write_bm25_corpus, index_path, records, texts, manifest)
|
||||
logger.info(
|
||||
f"ebook_bm25_index_refreshed {index_path=} {manifest.chunk_count=} created_at={manifest.created_at.isoformat()}"
|
||||
)
|
||||
return manifest
|
||||
|
||||
|
||||
@cache
|
||||
def load_bm25_corpus(config: EbookSearchConfig) -> BM25Corpus:
|
||||
"""Load the BM25 corpus into memory once per process.
|
||||
|
||||
Background refresh tasks clear this cache after rebuilding the on-disk corpus.
|
||||
"""
|
||||
index_path = bm25_index_path(config)
|
||||
active_index_path = get_current_bm25_index(index_path)
|
||||
logger.info(f"ebook_bm25_corpus_cache_load {index_path=} {active_index_path=}")
|
||||
manifest = read_bm25_manifest(index_path)
|
||||
if manifest is None or not bm25_index_exists(index_path, manifest):
|
||||
msg = f"BM25 corpus is not available: {index_path}"
|
||||
raise BM25CorpusUnavailableError(msg)
|
||||
if manifest.chunk_count == 0:
|
||||
return BM25Corpus(retriever=None, records=(), manifest=manifest)
|
||||
|
||||
retriever = bm25s.BM25.load(active_index_path, load_corpus=True, mmap=True)
|
||||
records = tuple(dict(record) for record in retriever.corpus)
|
||||
return BM25Corpus(retriever=retriever, records=records, manifest=manifest)
|
||||
|
||||
|
||||
def score_bm25_corpus(query: str, corpus: BM25Corpus, *, limit: int) -> list[tuple[dict[str, object], float]]:
|
||||
"""Score a query against a loaded BM25 corpus."""
|
||||
if corpus.retriever is None or not corpus.records:
|
||||
return []
|
||||
k = min(limit, len(corpus.records))
|
||||
documents, scores = corpus.retriever.retrieve(
|
||||
bm25s.tokenize(query, show_progress=False),
|
||||
corpus=list(corpus.records),
|
||||
k=k,
|
||||
show_progress=False,
|
||||
)
|
||||
results: list[tuple[dict[str, object], float]] = []
|
||||
for document, score in zip(documents[0], scores[0], strict=True):
|
||||
score_value = float(score)
|
||||
if score_value <= 0:
|
||||
continue
|
||||
results.append((dict(document), score_value))
|
||||
return results
|
||||
|
||||
|
||||
async def fetch_bm25_corpus_records(session: AsyncSession) -> tuple[list[dict[str, object]], list[str]]:
|
||||
"""Fetch persistable BM25 corpus records and their matching index texts from the database.
|
||||
|
||||
search_text is only needed to build the index, so it is returned separately instead of
|
||||
being persisted into the corpus records, which would double the corpus size.
|
||||
"""
|
||||
statement = (
|
||||
select(
|
||||
*CHUNK_RECORD_COLUMNS,
|
||||
EbookChunk.search_text.label("bm25_text"),
|
||||
)
|
||||
.select_from(EbookChunk)
|
||||
.join(EbookSource, EbookSource.id == EbookChunk.source_id)
|
||||
.outerjoin(EbookChapter, EbookChapter.id == EbookChunk.chapter_id)
|
||||
.order_by(EbookChunk.id)
|
||||
)
|
||||
records: list[dict[str, object]] = []
|
||||
texts: list[str] = []
|
||||
for row in (await session.execute(statement)).mappings():
|
||||
record = dict(row)
|
||||
texts.append(str(record.pop("bm25_text")))
|
||||
records.append(record)
|
||||
return records, texts
|
||||
|
||||
|
||||
async def corpus_last_updated_at(session: AsyncSession) -> datetime | None:
|
||||
"""Return the latest source/chapter/chunk update timestamp relevant to BM25 text."""
|
||||
update_times = union_all(
|
||||
select(func.max(EbookSource.updated).label("updated")),
|
||||
select(func.max(EbookChapter.updated).label("updated")),
|
||||
select(func.max(EbookChunk.updated).label("updated")),
|
||||
).subquery()
|
||||
return await session.scalar(select(func.max(update_times.c.updated)))
|
||||
|
||||
|
||||
def write_bm25_corpus(
|
||||
index_path: Path,
|
||||
records: list[dict[str, object]],
|
||||
texts: list[str],
|
||||
manifest: BM25Manifest,
|
||||
) -> None:
|
||||
"""Write a BM25 corpus generation and publish it through the current symlink."""
|
||||
index_path.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
generations_path = index_path / "generations"
|
||||
generations_path.mkdir(exist_ok=True)
|
||||
|
||||
generation_path = next_bm25_generation_path(generations_path, manifest.created_at)
|
||||
current_path = index_path / "current"
|
||||
next_current_path = index_path / f".current.{generation_path.name}.tmp"
|
||||
try:
|
||||
generation_path.mkdir()
|
||||
|
||||
# Empty corpora publish a manifest-only generation so startup succeeds before any chunks exist.
|
||||
if records:
|
||||
retriever = bm25s.BM25()
|
||||
retriever.index(bm25s.tokenize(texts, show_progress=False), show_progress=False)
|
||||
retriever.save(generation_path, corpus=records, show_progress=False)
|
||||
write_bm25_manifest(generation_path, manifest)
|
||||
next_current_path.unlink(missing_ok=True)
|
||||
next_current_path.symlink_to(generation_path, target_is_directory=True)
|
||||
next_current_path.replace(current_path)
|
||||
except Exception:
|
||||
next_current_path.unlink(missing_ok=True)
|
||||
shutil.rmtree(generation_path, ignore_errors=True)
|
||||
raise
|
||||
|
||||
|
||||
def read_bm25_manifest(index_path: Path) -> BM25Manifest | None:
|
||||
"""Read the BM25 manifest if it exists and is valid."""
|
||||
manifest_path = get_current_bm25_index(index_path) / MANIFEST_NAME
|
||||
if not manifest_path.exists():
|
||||
return None
|
||||
body = json.loads(manifest_path.read_text(encoding="utf-8"))
|
||||
return BM25Manifest(
|
||||
created_at=datetime.fromisoformat(str(body["created_at"])),
|
||||
db_updated_at=datetime.fromisoformat(str(body["db_updated_at"])) if body.get("db_updated_at") else None,
|
||||
chunk_count=int(body["chunk_count"]),
|
||||
)
|
||||
|
||||
|
||||
def write_bm25_manifest(index_path: Path, manifest: BM25Manifest) -> None:
|
||||
"""Write the BM25 manifest to an index directory."""
|
||||
body = {
|
||||
"created_at": manifest.created_at.isoformat(),
|
||||
"db_updated_at": manifest.db_updated_at.isoformat() if manifest.db_updated_at else None,
|
||||
"chunk_count": manifest.chunk_count,
|
||||
}
|
||||
(index_path / MANIFEST_NAME).write_text(json.dumps(body, indent=2, sort_keys=True), encoding="utf-8")
|
||||
|
||||
|
||||
def bm25_index_exists(index_path: Path, manifest: BM25Manifest | None) -> bool:
|
||||
"""Return whether a usable persisted BM25 index exists."""
|
||||
active_index_path = get_current_bm25_index(index_path)
|
||||
if manifest is None or not active_index_path.is_dir():
|
||||
return False
|
||||
if manifest.chunk_count == 0:
|
||||
return True
|
||||
return all((active_index_path / file_name).exists() for file_name in REQUIRED_INDEX_FILES)
|
||||
|
||||
|
||||
def next_bm25_generation_path(generations_path: Path, created_at: datetime) -> Path:
|
||||
"""Return an unused dated BM25 generation path."""
|
||||
base_name = created_at.astimezone(UTC).strftime("%Y%m%dT%H%M%S.%fZ")
|
||||
generation_path = generations_path / base_name
|
||||
suffix = 1
|
||||
while generation_path.exists():
|
||||
generation_path = generations_path / f"{base_name}.{suffix}"
|
||||
suffix += 1
|
||||
return generation_path
|
||||
@@ -1,13 +0,0 @@
|
||||
"""Shared database columns used to build search-result records."""
|
||||
|
||||
from python.orm.richie import EbookChapter, EbookChunk, EbookSource
|
||||
|
||||
CHUNK_RECORD_COLUMNS = (
|
||||
EbookChunk.id.label("chunk_id"),
|
||||
EbookChunk.text.label("text"),
|
||||
EbookSource.id.label("source_id"),
|
||||
EbookSource.title.label("source_title"),
|
||||
EbookSource.author.label("source_author"),
|
||||
EbookChapter.title.label("chapter_title"),
|
||||
EbookChunk.page_label.label("page_label"),
|
||||
)
|
||||
@@ -1,145 +0,0 @@
|
||||
"""Configuration for the EPUB search app."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Annotated, Self
|
||||
|
||||
from pydantic import AliasChoices, Field, field_validator, model_validator
|
||||
from pydantic_settings import BaseSettings, NoDecode, SettingsConfigDict
|
||||
|
||||
|
||||
def normalize_embedding_alias(model: str) -> str:
|
||||
"""Normalize a supported embedding alias to its provider model name."""
|
||||
aliases = {
|
||||
"Qwen3-Embedding-0.6B": "qwen3-embedding-0.6b",
|
||||
"Qwen3-Embedding-4B": "qwen3-embedding-4b",
|
||||
"Qwen3-Embedding-8B": "qwen3-embedding-8b",
|
||||
"Qwen/Qwen3-Embedding-0.6B": "qwen3-embedding-0.6b",
|
||||
"Qwen/Qwen3-Embedding-4B": "qwen3-embedding-4b",
|
||||
"Qwen/Qwen3-Embedding-8B": "qwen3-embedding-8b",
|
||||
"qwen3-embedding:0.6b": "qwen3-embedding-0.6b",
|
||||
"qwen3-embedding:4b": "qwen3-embedding-4b",
|
||||
"qwen3-embedding:8b": "qwen3-embedding-8b",
|
||||
"qwen3-embedding-0.6b": "qwen3-embedding-0.6b",
|
||||
"qwen3-embedding-4b": "qwen3-embedding-4b",
|
||||
"qwen3-embedding-8b": "qwen3-embedding-8b",
|
||||
}
|
||||
standard_model = aliases.get(model)
|
||||
if standard_model is None:
|
||||
error = f"Embedding model {model} is not supported. Supported models are {aliases.keys()}"
|
||||
raise ValueError(error)
|
||||
return standard_model
|
||||
|
||||
|
||||
class RerankConfig(BaseSettings):
|
||||
"""vLLM reranker settings."""
|
||||
|
||||
model_config = SettingsConfigDict(env_prefix="EBOOK_SEARCH_RERANK_", frozen=True, protected_namespaces=())
|
||||
|
||||
enabled: bool = True
|
||||
base_url: str = "http://192.168.90.25:8001"
|
||||
model: str = "qwen3-reranker-06b"
|
||||
candidates: int = 24
|
||||
timeout_seconds: float = 30.0
|
||||
score_weight: float = 0.7
|
||||
hybrid_weight: float = 0.3
|
||||
|
||||
|
||||
class EbookSearchConfig(BaseSettings):
|
||||
"""Runtime settings for EPUB search."""
|
||||
|
||||
model_config = SettingsConfigDict(
|
||||
env_prefix="EBOOK_SEARCH_",
|
||||
frozen=True,
|
||||
populate_by_name=True,
|
||||
protected_namespaces=(),
|
||||
)
|
||||
|
||||
rerank: RerankConfig = Field(default_factory=RerankConfig)
|
||||
top_k: int = 12
|
||||
library_paths: Annotated[tuple[str, ...], NoDecode] = ()
|
||||
chunk_tokens: int = 700
|
||||
chunk_overlap: int = 100
|
||||
vllm_base_url: str = "https://ollama.com/v1"
|
||||
vllm_api_key: str = Field(
|
||||
default="not-needed",
|
||||
validation_alias=AliasChoices("EBOOK_SEARCH_VLLM_API_KEY", "OLLAMA_API_KEY"),
|
||||
)
|
||||
chat_model: str = "deepseek-v4-flash"
|
||||
answer_enabled: bool = True
|
||||
embedding_base_url: str = "http://192.168.90.25:8000/v1"
|
||||
embedding_api_key: str = "not-needed"
|
||||
embedding_model: str = "qwen3-embedding-0.6b"
|
||||
embedding_batch_size: int = 32
|
||||
embedding_timeout_seconds: float = 60.0
|
||||
chat_timeout_seconds: float = 60.0
|
||||
vector_candidate_multiplier: int = 4
|
||||
bm25_candidate_limit: int = 120
|
||||
rrf_rank_constant: int = 60
|
||||
min_retrieval_confidence: float = 0.0
|
||||
validate_citations_enabled: bool = True
|
||||
bm25_index_dir: str = ".ebook_search_bm25"
|
||||
bm25_refresh_delay_seconds: int = 60
|
||||
protected_phrase_max_candidates_per_book: int = 5000
|
||||
protected_phrase_llm_candidates_per_book: int = 500
|
||||
protected_phrase_extraction_workers: int = 16
|
||||
phrase_judge_book_workers: int = 20
|
||||
phrase_judge_phrase_workers: int = 100
|
||||
protected_phrase_confidence_threshold: float = 0.80
|
||||
phrase_matching_enabled: bool = True
|
||||
phrase_hit_boost: float = 0.25
|
||||
phrase_min_tokens: int = 2
|
||||
phrase_max_tokens: int = 5
|
||||
phrase_max_entity_tokens: int = 8
|
||||
phrase_yake_top_k: int = 1000
|
||||
phrase_yake_dedup_limit: float = 0.85
|
||||
phrase_raw_ngram_min_count: int = 2
|
||||
phrase_raw_count_score_threshold: int = 3
|
||||
phrase_raw_count_high_score_threshold: int = 10
|
||||
phrase_chapter_count_score_threshold: int = 2
|
||||
phrase_chapter_count_high_score_threshold: int = 5
|
||||
phrase_target_protected_per_book: int = 100
|
||||
phrase_default_allow_nested: bool = False
|
||||
phrase_default_suppress_children: bool = True
|
||||
phrase_bad_start_score_penalty: float = 10.0
|
||||
phrase_bad_end_score_penalty: float = 10.0
|
||||
phrase_multi_source_score_bonus: float = 2.0
|
||||
phrase_multi_source_min_sources: int = 2
|
||||
|
||||
@field_validator("library_paths", mode="before")
|
||||
@classmethod
|
||||
def split_library_paths(cls, value: object) -> object:
|
||||
"""Split a colon-separated library path string into a tuple of paths."""
|
||||
if isinstance(value, str):
|
||||
return tuple(path for path in value.split(":") if path)
|
||||
return value
|
||||
|
||||
@field_validator("embedding_model")
|
||||
@classmethod
|
||||
def normalize_embedding(cls, value: str) -> str:
|
||||
"""Normalize the configured embedding alias to its provider model name."""
|
||||
return normalize_embedding_alias(value)
|
||||
|
||||
@model_validator(mode="after")
|
||||
def validate_runtime_consistency(self) -> Self:
|
||||
"""Reject configurations that cannot serve the features they enable."""
|
||||
if not self.embedding_base_url.strip():
|
||||
msg = "embedding_base_url must be set"
|
||||
raise ValueError(msg)
|
||||
if self.answer_enabled and (not self.vllm_base_url.strip() or not self.chat_model.strip()):
|
||||
msg = "answer_enabled requires vllm_base_url and chat_model to be set"
|
||||
raise ValueError(msg)
|
||||
if self.rerank.enabled and not self.rerank.base_url.strip():
|
||||
msg = "rerank.enabled requires rerank.base_url to be set"
|
||||
raise ValueError(msg)
|
||||
return self
|
||||
|
||||
|
||||
def load_rerank_config() -> RerankConfig:
|
||||
"""Load reranker config from environment variables."""
|
||||
return RerankConfig()
|
||||
|
||||
|
||||
def load_config() -> EbookSearchConfig:
|
||||
"""Load EPUB search config from environment variables."""
|
||||
return EbookSearchConfig()
|
||||
@@ -1,54 +0,0 @@
|
||||
FROM python:3.14-slim AS base
|
||||
|
||||
COPY --from=ghcr.io/astral-sh/uv:0.11.26 /uv /uvx /bin/
|
||||
|
||||
ENV PYTHONDONTWRITEBYTECODE=1 \
|
||||
PYTHONUNBUFFERED=1 \
|
||||
APP_DIR=/home/richie/dotfiles \
|
||||
UV_PROJECT_ENVIRONMENT=/opt/venv \
|
||||
UV_PYTHON_DOWNLOADS=never \
|
||||
UV_NO_CACHE=1
|
||||
|
||||
# Separate ENV instruction so ${APP_DIR} and ${PATH} from above resolve.
|
||||
ENV PYTHONPATH=${APP_DIR} \
|
||||
PATH=/opt/venv/bin:${PATH}
|
||||
|
||||
WORKDIR ${APP_DIR}
|
||||
|
||||
RUN apt-get update \
|
||||
&& apt-get install -y --no-install-recommends build-essential curl \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
COPY python/ebook_search/docker/pyproject.toml python/ebook_search/docker/uv.lock ./
|
||||
|
||||
RUN uv sync --locked --no-dev
|
||||
|
||||
|
||||
FROM base AS test
|
||||
|
||||
RUN uv sync --locked
|
||||
|
||||
COPY python ./python
|
||||
COPY tests/__init__.py ./tests/__init__.py
|
||||
COPY tests/ebook_search ./tests/ebook_search
|
||||
|
||||
CMD ["pytest"]
|
||||
|
||||
|
||||
FROM base AS runtime
|
||||
|
||||
ENV EBOOK_SEARCH_HOST=0.0.0.0 \
|
||||
EBOOK_SEARCH_PORT=8070 \
|
||||
EBOOK_SEARCH_BM25_INDEX_DIR=/data/bm25
|
||||
|
||||
COPY python ./python
|
||||
|
||||
RUN useradd --create-home --uid 10001 app \
|
||||
&& mkdir -p /data \
|
||||
&& chown -R app:app /home/richie /data
|
||||
|
||||
USER app
|
||||
|
||||
EXPOSE 8070
|
||||
|
||||
CMD ["sh", "-c", "exec python -m python.ebook_search.api.main --host \"${EBOOK_SEARCH_HOST}\" --port \"${EBOOK_SEARCH_PORT}\" --log-level \"${EBOOK_SEARCH_LOG_LEVEL:-INFO}\""]
|
||||
@@ -1,77 +0,0 @@
|
||||
# Ebook Search Docker
|
||||
|
||||
Run the EPUB search app against the existing Postgres database on `jeeves`:
|
||||
|
||||
```sh
|
||||
python -m python.ebook_search.docker.containers start --library-path /path/to/epubs --build
|
||||
```
|
||||
|
||||
All ebook-search Docker files live in this directory:
|
||||
|
||||
- `Dockerfile` — multi-stage: `test` (runs pytest) and `runtime` (default target, the app image)
|
||||
- `docker-compose.yml`
|
||||
- `containers.py` — Typer lifecycle CLI
|
||||
- `pyproject.toml` / `uv.lock` — the container's uv-locked dependencies
|
||||
|
||||
The app listens on `http://localhost:8070`.
|
||||
|
||||
Useful lifecycle commands:
|
||||
|
||||
```sh
|
||||
python -m python.ebook_search.docker.containers build
|
||||
python -m python.ebook_search.docker.containers start --library-path /path/to/epubs
|
||||
python -m python.ebook_search.docker.containers test
|
||||
python -m python.ebook_search.docker.containers logs
|
||||
python -m python.ebook_search.docker.containers ps
|
||||
python -m python.ebook_search.docker.containers stop
|
||||
```
|
||||
|
||||
Direct compose usage from the repo root:
|
||||
|
||||
```sh
|
||||
docker compose -f python/ebook_search/docker/docker-compose.yml ps
|
||||
```
|
||||
|
||||
## Dependencies
|
||||
|
||||
The image builds its environment with uv from `pyproject.toml` + `uv.lock` in this
|
||||
directory — this is the source of truth for the container's dependencies. To add or
|
||||
update a dependency, edit `pyproject.toml` here and regenerate the lock (uv is
|
||||
available in the `ebook-search` dev shell):
|
||||
|
||||
```sh
|
||||
nix develop .#ebook-search -c uv lock --project python/ebook_search/docker
|
||||
```
|
||||
|
||||
## Tests
|
||||
|
||||
The main pytest suite excludes `tests/ebook_search` (its dependencies are no longer
|
||||
in the nix dev shell). The `test ebook search` CI workflow runs them in a uv env
|
||||
built from the lockfile in this directory — same commands work locally from the
|
||||
repo root (the `--override-ini` drops the main suite's ignore):
|
||||
|
||||
```sh
|
||||
uv sync --locked --project python/ebook_search/docker
|
||||
uv run --project python/ebook_search/docker --no-sync pytest tests/ebook_search --override-ini addopts="-n auto -ra"
|
||||
```
|
||||
|
||||
They can also run inside the Docker `test` image, which validates the image itself:
|
||||
|
||||
```sh
|
||||
python -m python.ebook_search.docker.containers test
|
||||
```
|
||||
|
||||
or the raw docker equivalent:
|
||||
|
||||
```sh
|
||||
docker build --file python/ebook_search/docker/Dockerfile --target test --tag ebook-search:test .
|
||||
docker run --rm ebook-search:test
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
The compose service loads the repo root `.env` into the container via `env_file`.
|
||||
|
||||
Mount your EPUB directory by setting `EBOOK_LIBRARY_HOST_PATH` in an env file or on the command line. The container sees it as `/library`, and `EBOOK_SEARCH_LIBRARY_PATHS` is set to `/library` inside the container.
|
||||
|
||||
Database connection settings are controlled by `RICHIE_DB`, `RICHIE_HOST`, `RICHIE_PORT`, `RICHIE_USER`, and `RICHIE_PASSWORD`. The default host is `jeeves`.
|
||||
@@ -1 +0,0 @@
|
||||
"""Docker packaging and lifecycle tooling for ebook search."""
|
||||
@@ -1,259 +0,0 @@
|
||||
"""Docker container lifecycle management for ebook search."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
from typing import Annotated
|
||||
|
||||
import typer
|
||||
|
||||
from python.common import configure_logger, get_repo_dir
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def get_compose_file() -> Path:
|
||||
"""Return the path to the docker-compose.yml file."""
|
||||
return Path(__file__).resolve().with_name("docker-compose.yml")
|
||||
|
||||
|
||||
def compose_base_args() -> list[str]:
|
||||
"""Return the common docker compose arguments for the ebook search stack."""
|
||||
return ["compose", "-f", str(get_compose_file())]
|
||||
|
||||
|
||||
def docker_run(
|
||||
arguments: list[str],
|
||||
*,
|
||||
env: dict[str, str] | None = None,
|
||||
capture_output: bool = False,
|
||||
) -> subprocess.CompletedProcess[str]:
|
||||
"""Run docker with repo-root cwd and consistent error handling."""
|
||||
logger.info(f"docker {' '.join(arguments)}")
|
||||
return subprocess.run(
|
||||
["docker", *arguments],
|
||||
cwd=get_repo_dir(),
|
||||
env=env,
|
||||
text=True,
|
||||
check=False,
|
||||
capture_output=capture_output,
|
||||
)
|
||||
|
||||
|
||||
def compose_env(*, library_path: Path | None = None, port: int | None = None) -> dict[str, str]:
|
||||
"""Return environment variables passed to docker compose."""
|
||||
env = os.environ.copy()
|
||||
if library_path is not None:
|
||||
resolved_library = library_path.expanduser().resolve()
|
||||
if not resolved_library.exists():
|
||||
msg = f"EPUB library path does not exist: {resolved_library}"
|
||||
raise FileNotFoundError(msg)
|
||||
env["EBOOK_LIBRARY_HOST_PATH"] = str(resolved_library)
|
||||
if port is not None:
|
||||
env["EBOOK_SEARCH_PORT"] = str(port)
|
||||
return env
|
||||
|
||||
|
||||
def ensure_compose_file() -> None:
|
||||
"""Raise if the ebook search compose file is missing."""
|
||||
if not get_compose_file().is_file():
|
||||
msg = f"Compose file not found: {get_compose_file()}"
|
||||
raise FileNotFoundError(msg)
|
||||
|
||||
|
||||
def build_image() -> None:
|
||||
"""Build the ebook search app image."""
|
||||
ensure_compose_file()
|
||||
result = docker_run([*compose_base_args(), "build"])
|
||||
if result.returncode != 0:
|
||||
msg = "Failed to build ebook search image"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
|
||||
def build_test_image() -> None:
|
||||
"""Build the ebook search test Docker image."""
|
||||
dockerfile = Path(__file__).resolve().with_name("Dockerfile")
|
||||
result = docker_run(["build", "--file", str(dockerfile), "--target", "test", "--tag", "ebook-search:test", "."])
|
||||
if result.returncode != 0:
|
||||
msg = "Failed to build ebook search test image"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
|
||||
def run_test_image() -> None:
|
||||
"""Run the ebook search test suite inside Docker."""
|
||||
result = docker_run(["run", "--rm", "ebook-search:test"])
|
||||
if result.returncode != 0:
|
||||
msg = f"Ebook search tests failed with code {result.returncode}"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
|
||||
def start_stack(
|
||||
*,
|
||||
library_path: Path | None = None,
|
||||
port: int | None = None,
|
||||
build: bool = False,
|
||||
) -> None:
|
||||
"""Start the ebook search Docker compose stack."""
|
||||
ensure_compose_file()
|
||||
env = compose_env(library_path=library_path, port=port)
|
||||
if build:
|
||||
build_image()
|
||||
result = docker_run(
|
||||
[*compose_base_args(), "up", "-d"],
|
||||
env=env,
|
||||
)
|
||||
if result.returncode != 0:
|
||||
msg = f"Ebook search stack failed to start with code {result.returncode}"
|
||||
raise RuntimeError(msg)
|
||||
logger.info("Ebook search started.")
|
||||
|
||||
|
||||
def stop_stack(
|
||||
*,
|
||||
volumes: bool = False,
|
||||
) -> None:
|
||||
"""Stop and remove ebook search containers."""
|
||||
ensure_compose_file()
|
||||
command = [*compose_base_args(), "down"]
|
||||
if volumes:
|
||||
command.append("-v")
|
||||
result = docker_run(command)
|
||||
if result.returncode != 0:
|
||||
msg = f"Ebook search stack failed to stop with code {result.returncode}"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
|
||||
def logs_stack(
|
||||
*,
|
||||
service: str | None = None,
|
||||
tail: int = 100,
|
||||
follow: bool = False,
|
||||
) -> str | None:
|
||||
"""Return recent logs from the ebook search stack."""
|
||||
ensure_compose_file()
|
||||
command = [*compose_base_args(), "logs", "--tail", str(tail)]
|
||||
if follow:
|
||||
command.append("--follow")
|
||||
if service:
|
||||
command.append(service)
|
||||
result = docker_run(command, capture_output=not follow)
|
||||
if result.returncode != 0:
|
||||
return None
|
||||
if follow:
|
||||
return ""
|
||||
return result.stdout + result.stderr
|
||||
|
||||
|
||||
def ps_stack() -> str | None:
|
||||
"""Return docker compose ps output for the ebook search stack."""
|
||||
ensure_compose_file()
|
||||
result = docker_run([*compose_base_args(), "ps"], capture_output=True)
|
||||
if result.returncode != 0:
|
||||
return None
|
||||
return result.stdout + result.stderr
|
||||
|
||||
|
||||
app = typer.Typer(help="Ebook search Docker container management.", no_args_is_help=True)
|
||||
|
||||
|
||||
@app.command()
|
||||
def build() -> None:
|
||||
"""Build the ebook search Docker image."""
|
||||
build_image()
|
||||
|
||||
|
||||
@app.command()
|
||||
def start(
|
||||
library_path: Annotated[Path | None, typer.Option(help="Override host path containing EPUB files.")] = None,
|
||||
port: Annotated[int | None, typer.Option(help="Override host port for the web UI.")] = None,
|
||||
*,
|
||||
build: Annotated[bool, typer.Option("--build", help="Build the image before starting.")] = False,
|
||||
log_level: Annotated[str, typer.Option(help="Log level.")] = "INFO",
|
||||
) -> None:
|
||||
"""Start the ebook search container."""
|
||||
configure_logger(log_level)
|
||||
start_stack(
|
||||
library_path=library_path,
|
||||
port=port,
|
||||
build=build,
|
||||
)
|
||||
|
||||
|
||||
@app.command()
|
||||
def stop(
|
||||
*,
|
||||
volumes: Annotated[bool, typer.Option("--volumes", help="Also remove ebook search data volumes.")] = False,
|
||||
log_level: Annotated[str, typer.Option(help="Log level.")] = "INFO",
|
||||
) -> None:
|
||||
"""Stop and remove ebook search containers."""
|
||||
configure_logger(log_level)
|
||||
stop_stack(volumes=volumes)
|
||||
|
||||
|
||||
@app.command()
|
||||
def restart(
|
||||
library_path: Annotated[Path | None, typer.Option(help="Override host path containing EPUB files.")] = None,
|
||||
port: Annotated[int | None, typer.Option(help="Override host port for the web UI.")] = None,
|
||||
*,
|
||||
build: Annotated[bool, typer.Option("--build", help="Build the image before starting.")] = False,
|
||||
log_level: Annotated[str, typer.Option(help="Log level.")] = "INFO",
|
||||
) -> None:
|
||||
"""Restart the ebook search stack."""
|
||||
configure_logger(log_level)
|
||||
stop_stack()
|
||||
start_stack(
|
||||
library_path=library_path,
|
||||
port=port,
|
||||
build=build,
|
||||
)
|
||||
|
||||
|
||||
@app.command()
|
||||
def logs(
|
||||
service: Annotated[str | None, typer.Option(help="Service name, or omit for all services.")] = None,
|
||||
tail: Annotated[int, typer.Option(help="Number of recent log lines.")] = 100,
|
||||
*,
|
||||
follow: Annotated[bool, typer.Option("--follow", "-f", help="Follow logs.")] = False,
|
||||
) -> None:
|
||||
"""Show recent ebook search container logs."""
|
||||
output = logs_stack(service=service, tail=tail, follow=follow)
|
||||
if output is None:
|
||||
typer.echo("No ebook search containers found.")
|
||||
raise typer.Exit(code=1)
|
||||
if output:
|
||||
typer.echo(output)
|
||||
|
||||
|
||||
@app.command("test")
|
||||
def run_tests(
|
||||
*,
|
||||
build: Annotated[bool, typer.Option("--build/--no-build", help="Build the test image before running.")] = True,
|
||||
log_level: Annotated[str, typer.Option(help="Log level.")] = "INFO",
|
||||
) -> None:
|
||||
"""Run ebook search tests inside the Docker test image."""
|
||||
configure_logger(log_level)
|
||||
if build:
|
||||
build_test_image()
|
||||
run_test_image()
|
||||
|
||||
|
||||
@app.command("ps")
|
||||
def ps() -> None:
|
||||
"""Show ebook search container status."""
|
||||
output = ps_stack()
|
||||
if output is None:
|
||||
typer.echo("No ebook search containers found.")
|
||||
raise typer.Exit(code=1)
|
||||
typer.echo(output)
|
||||
|
||||
|
||||
def cli() -> None:
|
||||
"""Typer entry point."""
|
||||
app()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
cli()
|
||||
@@ -1,36 +0,0 @@
|
||||
name: ebook-search
|
||||
|
||||
services:
|
||||
ebook-search:
|
||||
build:
|
||||
context: ../../..
|
||||
dockerfile: python/ebook_search/docker/Dockerfile
|
||||
image: ebook-search:latest
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- "${EBOOK_SEARCH_PORT:-8070}:8070"
|
||||
extra_hosts:
|
||||
- "jeeves:192.168.90.40"
|
||||
env_file:
|
||||
- ../../../.env
|
||||
environment:
|
||||
EBOOK_SEARCH_HOST: "0.0.0.0"
|
||||
EBOOK_SEARCH_PORT: "8070"
|
||||
EBOOK_SEARCH_LIBRARY_PATHS: "/library"
|
||||
EBOOK_SEARCH_BM25_INDEX_DIR: "/data/bm25"
|
||||
volumes:
|
||||
- "${EBOOK_LIBRARY_HOST_PATH:-/home/richie/ebooks}:/library:ro"
|
||||
- ebook-search-data:/data
|
||||
healthcheck:
|
||||
test:
|
||||
[
|
||||
"CMD-SHELL",
|
||||
"curl -fsS http://127.0.0.1:8070/health >/dev/null || exit 1",
|
||||
]
|
||||
interval: 30s
|
||||
timeout: 5s
|
||||
retries: 5
|
||||
start_period: 30s
|
||||
|
||||
volumes:
|
||||
ebook-search-data:
|
||||
@@ -1,41 +0,0 @@
|
||||
[project]
|
||||
name = "ebook-search"
|
||||
version = "0.1.0"
|
||||
description = "Locked runtime environment for the ebook search container."
|
||||
requires-python = "~=3.14.0"
|
||||
dependencies = [
|
||||
"alembic",
|
||||
"beautifulsoup4",
|
||||
"bm25s",
|
||||
"ebooklib",
|
||||
"fastapi",
|
||||
"httpx",
|
||||
"jinja2",
|
||||
"pgvector",
|
||||
"psycopg[binary]",
|
||||
"pydantic",
|
||||
"pydantic-settings",
|
||||
"python-multipart",
|
||||
"sqlalchemy[asyncio]",
|
||||
"tiktoken",
|
||||
"typer",
|
||||
"uvicorn[standard]",
|
||||
"yake",
|
||||
]
|
||||
|
||||
[dependency-groups]
|
||||
dev = [
|
||||
"aiosqlite",
|
||||
"pytest",
|
||||
"pytest-asyncio",
|
||||
"pytest-mock",
|
||||
"pytest-xdist",
|
||||
]
|
||||
|
||||
[tool.uv]
|
||||
package = false
|
||||
|
||||
[tool.pytest.ini_options]
|
||||
addopts = "-n auto -ra"
|
||||
asyncio_mode = "auto"
|
||||
testpaths = ["tests/ebook_search"]
|
||||
Generated
-1143
File diff suppressed because it is too large
Load Diff
@@ -1,165 +0,0 @@
|
||||
"""Embedding model helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from dataclasses import dataclass
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from sqlalchemy import func, select
|
||||
from sqlalchemy.dialects.postgresql import insert
|
||||
|
||||
from python.ebook_search.llm_interface import request_embeddings
|
||||
from python.orm.richie import (
|
||||
EbookChunk,
|
||||
EbookChunkEmbedding1024,
|
||||
EbookChunkEmbedding2560,
|
||||
EbookChunkEmbedding4096,
|
||||
EbookEmbeddingModel,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Sequence
|
||||
|
||||
import httpx
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from python.ebook_search.config import EbookSearchConfig
|
||||
|
||||
MODEL_DIMENSIONS = {
|
||||
"qwen3-embedding-0.6b": 1024,
|
||||
"qwen3-embedding-4b": 2560,
|
||||
"qwen3-embedding-8b": 4096,
|
||||
}
|
||||
|
||||
|
||||
def get_embedding_table(
|
||||
dimension: int,
|
||||
) -> type[EbookChunkEmbedding1024 | EbookChunkEmbedding2560 | EbookChunkEmbedding4096]:
|
||||
"""Return the embedding table mapped to an embedding dimension."""
|
||||
embedding_tables = {
|
||||
1024: EbookChunkEmbedding1024,
|
||||
2560: EbookChunkEmbedding2560,
|
||||
4096: EbookChunkEmbedding4096,
|
||||
}
|
||||
table = embedding_tables.get(dimension)
|
||||
if not table:
|
||||
msg = f"Embedding dimension {dimension} is not supported"
|
||||
raise ValueError(msg)
|
||||
return table
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class EmbeddingModelStats:
|
||||
"""Embedding coverage for one model."""
|
||||
|
||||
model_name: str
|
||||
dimension: int
|
||||
embedded_chunks: int
|
||||
total_chunks: int
|
||||
|
||||
@property
|
||||
def missing_chunks(self) -> int:
|
||||
"""Return chunks missing this embedding model."""
|
||||
return max(self.total_chunks - self.embedded_chunks, 0)
|
||||
|
||||
|
||||
async def embed_texts(
|
||||
client: httpx.AsyncClient,
|
||||
texts: Sequence[str],
|
||||
config: EbookSearchConfig,
|
||||
) -> list[list[float]]:
|
||||
"""Embed text with the configured vLLM embedding model."""
|
||||
logger.info(f"ebook_embed_request_start {config.embedding_base_url=} {config.embedding_model=} count={len(texts)}")
|
||||
vectors = await request_embeddings(client, texts, config)
|
||||
expected_dimension = MODEL_DIMENSIONS[config.embedding_model]
|
||||
for vector in vectors:
|
||||
if len(vector) != expected_dimension:
|
||||
msg = f"Expected {expected_dimension} dimensions, got {len(vector)}"
|
||||
raise ValueError(msg)
|
||||
logger.info(f"ebook_embed_request_complete {config.embedding_model=} count={len(vectors)} {expected_dimension=}")
|
||||
return vectors
|
||||
|
||||
|
||||
async def embed_query(client: httpx.AsyncClient, query: str, config: EbookSearchConfig) -> list[float]:
|
||||
"""Embed a search query with the Qwen retrieval instruction."""
|
||||
instructed_query = f"Instruct: Retrieve relevant passages for the query.\nQuery: {query}"
|
||||
return (await embed_texts(client, [instructed_query], config))[0]
|
||||
|
||||
|
||||
async def ensure_embedding_models(session: AsyncSession) -> None:
|
||||
"""Ensure supported embedding model rows exist."""
|
||||
for name, dimension in MODEL_DIMENSIONS.items():
|
||||
existing = await session.scalar(select(EbookEmbeddingModel).where(EbookEmbeddingModel.name == name))
|
||||
if existing is None:
|
||||
session.add(EbookEmbeddingModel(name=name, dimension=dimension, is_default=name == "qwen3-embedding-0.6b"))
|
||||
logger.info(f"ebook_embedding_model_created {name=} {dimension=}")
|
||||
await session.flush()
|
||||
|
||||
|
||||
async def embedding_model_stats(session: AsyncSession) -> list[EmbeddingModelStats]:
|
||||
"""Return embedding coverage counts for every supported model."""
|
||||
total_chunks = await session.scalar(select(func.count(EbookChunk.id))) or 0
|
||||
models = {
|
||||
model.name: model
|
||||
for model in await session.scalars(
|
||||
select(EbookEmbeddingModel)
|
||||
.where(EbookEmbeddingModel.name.in_(MODEL_DIMENSIONS))
|
||||
.order_by(EbookEmbeddingModel.name)
|
||||
)
|
||||
}
|
||||
|
||||
stats: list[EmbeddingModelStats] = []
|
||||
for model_name, dimension in MODEL_DIMENSIONS.items():
|
||||
model = models.get(model_name)
|
||||
embedded_chunks = 0
|
||||
if model is not None:
|
||||
table = get_embedding_table(dimension)
|
||||
embedded_chunks = await session.scalar(select(func.count(table.id)).where(table.model_id == model.id)) or 0
|
||||
stats.append(
|
||||
EmbeddingModelStats(
|
||||
model_name=model_name,
|
||||
dimension=dimension,
|
||||
embedded_chunks=embedded_chunks,
|
||||
total_chunks=total_chunks,
|
||||
)
|
||||
)
|
||||
return stats
|
||||
|
||||
|
||||
async def embed_missing_chunks(session: AsyncSession, client: httpx.AsyncClient, config: EbookSearchConfig) -> int:
|
||||
"""Embed chunks missing embeddings for the configured model."""
|
||||
await ensure_embedding_models(session)
|
||||
model = await session.scalar(select(EbookEmbeddingModel).where(EbookEmbeddingModel.name == config.embedding_model))
|
||||
if model is None:
|
||||
supported_models = ", ".join(MODEL_DIMENSIONS)
|
||||
msg = f"Unknown embedding model: {config.embedding_model}. Supported models: {supported_models}"
|
||||
raise ValueError(msg)
|
||||
|
||||
table = get_embedding_table(model.dimension)
|
||||
chunks = list(
|
||||
await session.scalars(
|
||||
select(EbookChunk)
|
||||
.outerjoin(table, (table.chunk_id == EbookChunk.id) & (table.model_id == model.id))
|
||||
.where(table.id.is_(None))
|
||||
.order_by(EbookChunk.id)
|
||||
.limit(config.embedding_batch_size)
|
||||
)
|
||||
)
|
||||
if not chunks:
|
||||
logger.info(f"ebook_embed_missing_none {config.embedding_model=}")
|
||||
return 0
|
||||
|
||||
logger.info(f"ebook_embed_missing_batch_start {config.embedding_model=} count={len(chunks)}")
|
||||
vectors = await embed_texts(client, [chunk.text for chunk in chunks], config)
|
||||
rows = [
|
||||
{"chunk_id": chunk.id, "model_id": model.id, "embedding": vector}
|
||||
for chunk, vector in zip(chunks, vectors, strict=True)
|
||||
]
|
||||
statement = insert(table).values(rows).on_conflict_do_nothing(index_elements=["chunk_id", "model_id"])
|
||||
await session.execute(statement)
|
||||
await session.flush()
|
||||
logger.info(f"ebook_embed_missing_batch_complete {config.embedding_model=} count={len(rows)}")
|
||||
return len(rows)
|
||||
@@ -1,95 +0,0 @@
|
||||
"""EPUB parsing helpers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from dataclasses import dataclass
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from bs4 import BeautifulSoup
|
||||
from ebooklib import ITEM_DOCUMENT, epub
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from pathlib import Path
|
||||
|
||||
WHITESPACE_RE = re.compile(r"\s+")
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ParsedChapter:
|
||||
"""Text extracted from one EPUB spine document."""
|
||||
|
||||
title: str | None
|
||||
href: str | None
|
||||
text: str
|
||||
page_labels: tuple[str, ...]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ParsedEpub:
|
||||
"""Parsed EPUB metadata and text."""
|
||||
|
||||
title: str
|
||||
author: str | None
|
||||
language: str | None
|
||||
publisher: str | None
|
||||
identifier: str | None
|
||||
chapters: tuple[ParsedChapter, ...]
|
||||
|
||||
|
||||
def parse_epub(path: Path) -> ParsedEpub:
|
||||
"""Parse EPUB metadata and spine text."""
|
||||
book = epub.read_epub(path)
|
||||
chapters = []
|
||||
for item in book.get_items_of_type(ITEM_DOCUMENT):
|
||||
soup = BeautifulSoup(item.get_content(), "html.parser")
|
||||
title = chapter_title(soup)
|
||||
page_labels = tuple(extract_page_labels(soup))
|
||||
text = clean_text(soup.get_text(" "))
|
||||
if text:
|
||||
chapters.append(ParsedChapter(title=title, href=item.get_name(), text=text, page_labels=page_labels))
|
||||
|
||||
return ParsedEpub(
|
||||
title=metadata_value(book, "title") or path.stem,
|
||||
author=metadata_value(book, "creator"),
|
||||
language=metadata_value(book, "language"),
|
||||
publisher=metadata_value(book, "publisher"),
|
||||
identifier=metadata_value(book, "identifier"),
|
||||
chapters=tuple(chapters),
|
||||
)
|
||||
|
||||
|
||||
def metadata_value(book: epub.EpubBook, name: str) -> str | None:
|
||||
"""Return the first non-empty Dublin Core metadata value for a name."""
|
||||
values = book.get_metadata("DC", name)
|
||||
if not values:
|
||||
return None
|
||||
value = values[0][0]
|
||||
return str(value).strip() or None
|
||||
|
||||
|
||||
def chapter_title(soup: BeautifulSoup) -> str | None:
|
||||
"""Extract the best available title from an EPUB document soup."""
|
||||
heading = soup.find(["h1", "h2", "h3"])
|
||||
if heading is None:
|
||||
title = soup.find("title")
|
||||
if title is None:
|
||||
return None
|
||||
return clean_text(title.get_text(" ")) or None
|
||||
return clean_text(heading.get_text(" ")) or None
|
||||
|
||||
|
||||
def extract_page_labels(soup: BeautifulSoup) -> list[str]:
|
||||
"""Extract EPUB page-break labels from a document soup."""
|
||||
labels: list[str] = []
|
||||
for tag in soup.find_all(attrs={"epub:type": "pagebreak"}):
|
||||
label = tag.get("title") or tag.get("aria-label") or tag.get_text(" ")
|
||||
clean = clean_text(str(label))
|
||||
if clean:
|
||||
labels.append(clean)
|
||||
return labels
|
||||
|
||||
|
||||
def clean_text(text: str) -> str:
|
||||
"""Normalize whitespace in extracted EPUB text."""
|
||||
return WHITESPACE_RE.sub(" ", text).strip()
|
||||
@@ -1 +0,0 @@
|
||||
"""Offline evaluation tooling for the ebook search pipeline."""
|
||||
@@ -1,71 +0,0 @@
|
||||
{"query": "Who is Damien Montgomery and how does he become a Jump Mage?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "What is a Rune Wright and why is Damien so rare?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "How does jump magic let starships travel faster than light?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "What is the role of the Mage-King of Mars in the Protectorate?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "What happened aboard the Blue Jay in the first Starship's Mage book?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "Who is Captain David Rice?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "How are amplifiers and simulacrums used to power a ship's jump?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "What duties does a Hand of the Mage-King carry out?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "Explain the structure of the Royal Martian Navy.", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "How do mages carve runes to enchant a starship?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "What threat do the Legatan rebels pose to the Protectorate?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "How does Damien handle his first command?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "What is the significance of the simulacrum on a jump ship?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "Describe a mage duel in the Starship's Mage series.", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "What moral conflicts does Damien face as a Hand of the Mage-King?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "How does the Protectorate keep peace among its member worlds?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "Who is the Keeper of Oaths and how does Damien work with them?", "answer": null, "answerable": true, "relevant_sources": ["Starship's Mage"]}
|
||||
{"query": "What event is known as the Onset and how does it change the world?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "Who is the main character at the start of the Onset?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "How do survivors adapt after the Onset begins?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "What new abilities emerge during the Onset?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "Describe the primary antagonist in the Onset series.", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "How does society collapse and reorganize after the Onset?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "What factions form in the aftermath of the Onset?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "How does the protagonist gain power throughout the Onset?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "What is the cause or origin of the Onset?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "Describe an early survival challenge faced after the Onset.", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "How do the characters defend their stronghold during the Onset?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "What relationships drive the protagonist's choices in the Onset?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "How does the Onset escalate by the end of the first book?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "What mysteries about the Onset remain unresolved?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "How do the rules of the world change once the Onset takes hold?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "What weapons or tactics work best against the threats of the Onset?", "answer": null, "answerable": true, "relevant_sources": ["The Onset"]}
|
||||
{"query": "How does Bob Johansson become a von Neumann probe?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "What is a replicant and why do Bob's copies have different personalities?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "Who are Riker, Homer, and Bill among the Bob clones?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "What is GUPPI and how does Bob use it?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "Describe the threat posed by the Others.", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "How does Bob protect and uplift the Deltans?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "Why do the replicants drift apart in personality over time?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "What is the role of FAITH and the Brazilian Empire on Earth?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "How does subspace communication work for the Bobs?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "What happens to Bender after he goes missing?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "How do the Bobs build self-replicating probes across the galaxy?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "How does Bob evacuate humanity after Earth becomes uninhabitable?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "Describe the conflict between different factions of Bobs.", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "What ethical dilemmas does Bob face when interfering with primitive species?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "How does the original Bob differ from later generations of clones?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "How do the Bobs defeat the Others' system-harvesting fleets?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
{"query": "What role does Howard play in the human colonies?", "answer": null, "answerable": true, "relevant_sources": ["We Are Legion (We Are Bob)"]}
|
||||
// querys not it the dataset
|
||||
{"query": "How does Frodo destroy the One Ring in The Lord of the Rings?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "Who killed Dumbledore in Harry Potter and the Half-Blood Prince?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "What house does Tyrion Lannister belong to in A Game of Thrones?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "How does Paul Atreides control the spice on Arrakis in Dune?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "What does the green light at the end of the dock mean in The Great Gatsby?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "Why does Hester Prynne wear a scarlet letter?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "What does the white whale represent in Moby-Dick?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "How does Elizabeth Bennet's view of Mr. Darcy change in Pride and Prejudice?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "What crime does Raskolnikov commit in Crime and Punishment?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "How does Katniss volunteer for the Hunger Games?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "What is Winston Smith's job in Nineteen Eighty-Four?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "Who is Atticus Finch defending in To Kill a Mockingbird?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "What is the capital of Australia?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "How do I bake a sourdough loaf from scratch?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "Explain how photosynthesis converts sunlight into energy.", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "What were the main causes of World War I?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "How does compound interest work?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "How do I change a flat tire on a car?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "What is the boiling point of water at sea level?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
{"query": "What is the recommended daily intake of vitamin D?", "answer": null, "answerable": false, "relevant_sources": []}
|
||||
@@ -1,47 +0,0 @@
|
||||
"""Shared query set loading for evaluation and load testing.
|
||||
|
||||
Each JSONL record has a ``query`` and an optional reference ``answer``. ``answerable``
|
||||
marks whether the query should be answerable from the library (false for out-of-corpus
|
||||
"garbage" queries used to test the refusal path). Relevance for retrieval metrics is
|
||||
labeled at source (book) granularity in ``relevant_sources``; source titles must match
|
||||
``ebook_source.title`` values for the indexed corpus.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
DEFAULT_QUERIES_PATH = Path(__file__).parent / "data" / "queries.jsonl"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class GoldQuery:
|
||||
"""One labeled query shared by the eval and load-test tools."""
|
||||
|
||||
query: str
|
||||
answer: str | None
|
||||
answerable: bool
|
||||
relevant_sources: tuple[str, ...]
|
||||
relevant_substrings: tuple[str, ...]
|
||||
|
||||
|
||||
def load_gold_queries(path: Path = DEFAULT_QUERIES_PATH) -> list[GoldQuery]:
|
||||
"""Load labeled queries from a JSONL file. Blank lines and ``//`` comment lines are skipped."""
|
||||
queries: list[GoldQuery] = []
|
||||
for line in path.read_text(encoding="utf-8").splitlines():
|
||||
stripped = line.strip()
|
||||
if not stripped or stripped.startswith("//"):
|
||||
continue
|
||||
record = json.loads(stripped)
|
||||
queries.append(
|
||||
GoldQuery(
|
||||
query=str(record["query"]),
|
||||
answer=record.get("answer"),
|
||||
answerable=bool(record.get("answerable", True)),
|
||||
relevant_sources=tuple(record.get("relevant_sources", ())),
|
||||
relevant_substrings=tuple(record.get("relevant_substrings", ())),
|
||||
)
|
||||
)
|
||||
return queries
|
||||
@@ -1,57 +0,0 @@
|
||||
"""Serve-time output guardrails for retrieval confidence and answer citations."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from dataclasses import dataclass
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from python.ebook_search.config import EbookSearchConfig
|
||||
from python.ebook_search.search import SearchResult
|
||||
|
||||
CITATION_RE = re.compile(r"\[(\d+)\]")
|
||||
|
||||
|
||||
def retrieval_confidence(results: list[SearchResult]) -> float:
|
||||
"""Return the strongest interpretable relevance signal of the top result.
|
||||
|
||||
Reciprocal-rank-fusion scores are rank-based and not comparable across queries,
|
||||
so the rerank relevance score is preferred, then vector cosine similarity, then
|
||||
the final score.
|
||||
"""
|
||||
if not results:
|
||||
return 0.0
|
||||
top = results[0]
|
||||
if top.rerank_score is not None:
|
||||
return top.rerank_score
|
||||
if top.vector_score is not None:
|
||||
return top.vector_score
|
||||
return top.score
|
||||
|
||||
|
||||
def is_confident(results: list[SearchResult], config: EbookSearchConfig) -> bool:
|
||||
"""Return whether top-result confidence meets the configured threshold."""
|
||||
return retrieval_confidence(results) >= config.min_retrieval_confidence
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class CitationReport:
|
||||
"""Validation summary for bracketed citation markers in a generated answer."""
|
||||
|
||||
cited: tuple[int, ...]
|
||||
invalid: tuple[int, ...]
|
||||
grounded: bool
|
||||
|
||||
|
||||
def validate_citations(answer: str, result_count: int) -> CitationReport:
|
||||
"""Validate bracketed citation markers against the number of shown sources.
|
||||
|
||||
A marker is valid when it points to a returned source (``1..result_count``).
|
||||
``grounded`` is true when the answer cites at least one valid source.
|
||||
"""
|
||||
markers = sorted({int(match.group(1)) for match in CITATION_RE.finditer(answer)})
|
||||
valid = range(1, result_count + 1)
|
||||
cited = tuple(marker for marker in markers if marker in valid)
|
||||
invalid = tuple(marker for marker in markers if marker not in valid)
|
||||
return CitationReport(cited=cited, invalid=invalid, grounded=bool(cited))
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user