book search engine #18

Merged

Richie merged 43 commits from feature/book-search-engine into main 2026-06-21 22:31:45 -04:00

Conversation 0 Commits 43 Files Changed 66

+4968 -24

Richie commented 2026-06-12 03:13:14 -04:00

Owner

Copy Link

Copy Source

No description provided.

Richie force-pushed feature/book-search-engine from 09d847e66a to 8d43fcbc09 2026-06-12 13:16:01 -04:00 Compare

Richie force-pushed feature/book-search-engine from 06ff6ae32b to 7740ebb594 2026-06-13 22:17:55 -04:00 Compare

Richie changed title from Feature/book search engine to book search engine 2026-06-13 22:18:31 -04:00

Richie force-pushed feature/book-search-engine from 7740ebb594 to 2c366e581d 2026-06-13 22:41:16 -04:00 Compare

Richie added 28 commits 2026-06-14 15:41:20 -04:00

adding embedding Models to jeeves e1ef4de6a3

removed hedgedoc d022251a58

added ebook embedding to orm cdded5da12

built BM25 search foundation db98bd3559

set up embedding system 0a2d4c08cb

built rag search setup aed1e14d95

built ingest ad1834c537

added rerank 82a367a2b6

made llm_interface.py e01c687625

added __init__ 666ea97754

added answer.py and config 26ff1f0fd3

build api and frountend 6715bbf0a5

setup tests 07eb170b34

updated python 911df63513

add .ebook_search_bm25 to gitignore 5544dfa61c

improved queary for vector search 11cbe31152

fixed duplicat enrichment 6e3635ca01

improved reranking weights dd67de3993

updated tests 45a9e90524

added proper cache invalidation to load_bm25_corpus 8301db39e5

made fastapi tools c53afb3c70

reworked ebook_search routers eb76edb740

added vector_engine to fix name postgres name space issue e9a80a0308

added ZstdMiddleware to ebook_search 50795ab7fc

improved BM25 write c88315e9b6

added a index for the VEctor DB 121eb979a4

opning ports for testing dce1838163

fixed test 2995a75748

Richie force-pushed feature/book-search-engine from 6d2c001735 to 2995a75748 2026-06-14 15:41:20 -04:00 Compare

Richie added 1 commit 2026-06-14 15:42:11 -04:00

fixed fomat issue a5d7c3be4f

Richie added 7 commits 2026-06-16 17:33:27 -04:00

converting to pydantic-settings 68b3a38b81

added AppConfig and AppEngine b126987b63

added health endpoints 2e68c83021

added guardrails.py to constrain responses and added validation to config.py f71ae7d2c6

moved config = load_config() to lifespan 0c9583c1cc

converted addmin.py and page.py to DbSession and AppConfig 4640ebf8ce

updated front end 241a42b20d

Richie added 5 commits 2026-06-20 23:22:54 -04:00

moved TC001 expetop out of pyproject.toml a9daa60c17

test(ebook-search): organize tests under dedicated package ... dbc6b5b53b

Move ebook search tests into tests/ebook_search and standardize mocking on pytest-mock.

feat(ebook-search): add load-test CLI for the search service ... 6ae1ff1f5c

Add a Typer CLI script that drives POST /search on a running server at a
configurable concurrency and reports latency percentiles (p50/p90/p95/p99),
throughput, and HTTP status distribution. Queries are drawn from the shared
eval JSONL set so load testing and evaluation exercise the same questions.

fix(ebook-search): code clean up to impove reliablty and readabilty 6bc30115d9

adding words to spell check fcb69cc68b

Richie added 1 commit 2026-06-21 14:45:47 -04:00

fix(ebook-search): skip comment lines in gold query loader and realign tests ... 09d963ba34

load_gold_queries now skips blank and `//` comment lines so the committed
section separator in queries.jsonl no longer breaks dataset/load-test loading.

Update tests left stale by the search refactor (6bc3011):
- pass the now-required rank_constant to reciprocal_rank_fusion
- expect bm25_candidates to receive the full query and drop the removed
  "BM25 query preparation" timing step
- assert reranking is enabled by default

Richie added 1 commit 2026-06-21 15:04:46 -04:00

Merge branch 'main' into feature/book-search-engine fc01fb9d0b

Richie merged commit fc01fb9d0b into main 2026-06-21 22:31:45 -04:00

Richie deleted branch feature/book-search-engine 2026-06-21 22:31:46 -04:00

Sign in to join this conversation.

Reviewers

No Reviewers

Labels

Clear labels

automated

bug

Something is not working

dependencies

duplicate

This issue or pull request already exists

enhancement

New feature

flake_lock_update

help wanted

Need some help

invalid

Something is wrong

question

More information is needed

wontfix

This won't be fixed

No labels

Milestone

No items

No Milestone

Projects

Clear projects

No projects

Assignees

Clear assignees

Richie

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: Richie/dotfiles#18