Files
dotfiles/python/ebook_search/api/routes/admin.py
T
Richie dab18c1385 Add models and database persistence for protected phrase extraction
- Introduced dataclasses for phrase candidates, judgments, and matches in `models.py`.
- Implemented database operations for candidate and protected phrases in `store.py`, including loading, saving, and deleting phrases.
- Enhanced text normalization functions in `text_normalization.py` with detailed docstrings.
- Refactored search functionality to utilize new models and methods for detecting protected phrases.
2026-07-09 11:04:59 -04:00

170 lines
6.5 KiB
Python

"""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 (
AppConfig, # noqa: TC001 FastAPI resolves this annotated dependency at runtime
)
from python.ebook_search.api.web import 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.fastapi_tools import DbSession # noqa: TC001 FastAPI resolves this annotated dependency at runtime
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/admin")
@router.get("", response_class=HTMLResponse)
def admin(request: Request, config: AppConfig, session: DbSession) -> HTMLResponse:
"""Render the admin page."""
stats = embedding_model_stats(session)
logger.info("ebook_admin_page_loaded models=%s", len(stats))
return templates.TemplateResponse(request, "admin.html", {"config": config, "stats": stats})
@router.post("/scan", response_class=HTMLResponse)
def scan_library(request: Request, config: AppConfig, session: DbSession) -> HTMLResponse:
"""Scan configured library paths for EPUB changes."""
try:
count = ingest_configured_paths(session, config)
session.commit()
except Exception as error:
logger.exception("ebook_admin_scan_failed")
return templates.TemplateResponse(request, "partials/error.html", {"message": str(error)}, status_code=500)
logger.info("ebook_admin_scan_complete changed_files=%s", count)
if count > 0:
schedule_bm25_refresh(request.app)
return templates.TemplateResponse(request, "partials/admin_status.html", {"message": f"Indexed {count} EPUBs"})
@router.post("/generate-ngrams", response_class=HTMLResponse)
def generate_ngrams(request: Request, config: AppConfig, session: DbSession) -> HTMLResponse:
"""Generate candidate n-grams for indexed books without LLM judging."""
try:
result = generate_candidate_phrases_for_books(session, config)
session.commit()
except Exception as error:
session.rollback()
logger.exception("ebook_admin_generate_ngrams_failed")
return templates.TemplateResponse(request, "partials/error.html", {"message": str(error)}, status_code=500)
logger.info(
"ebook_admin_generate_ngrams_complete books_seen=%s books_built=%s candidates=%s",
result.books_seen,
result.books_built,
result.candidate_phrases,
)
return templates.TemplateResponse(
request,
"partials/admin_status.html",
{
"message": (
f"Generated n-grams for {result.books_built} of {result.books_seen} books; "
f"{result.candidate_phrases} candidates stored"
)
},
)
@router.post("/judge-ngrams", response_class=HTMLResponse)
def judge_ngrams(request: Request, config: AppConfig, session: DbSession) -> HTMLResponse:
"""Judge stored candidate n-grams and promote accepted protected phrases."""
try:
result = judge_candidate_phrases_for_books(session, config)
session.commit()
except Exception as error:
session.rollback()
logger.exception("ebook_admin_judge_ngrams_failed")
return templates.TemplateResponse(request, "partials/error.html", {"message": str(error)}, status_code=500)
logger.info(
"ebook_admin_judge_ngrams_complete books_seen=%s books_judged=%s books_failed=%s candidates_judged=%s "
"protected=%s mentions=%s",
result.books_seen,
result.books_judged,
result.books_failed,
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)
def embed_missing(request: Request, config: AppConfig, session: DbSession) -> HTMLResponse:
"""Embed chunks missing vectors for the configured model."""
try:
count = embed_missing_chunks(session, config)
session.commit()
except Exception as error:
logger.exception("ebook_admin_embed_missing_failed")
return templates.TemplateResponse(request, "partials/error.html", {"message": str(error)}, status_code=500)
logger.info("ebook_admin_embed_missing_complete chunks=%s", count)
return templates.TemplateResponse(
request,
"partials/admin_status.html",
{"message": f"Embedded {count} chunks"},
)
@router.post("/embed-all", response_class=HTMLResponse)
def embed_all(request: Request, config: AppConfig, session: DbSession) -> HTMLResponse:
"""Embed all chunks missing vectors in fixed-size batches."""
total = 0
batches = 0
try:
while True:
count = embed_missing_chunks(session, config)
if count == 0:
break
session.commit()
total += count
batches += 1
logger.info(
"ebook_admin_embed_all_batch_complete batch=%s chunks=%s total_chunks=%s",
batches,
count,
total,
)
except Exception as error:
logger.exception(
"ebook_admin_embed_all_failed batches=%s chunks=%s",
batches,
total,
)
return templates.TemplateResponse(
request,
"partials/error.html",
{"message": f"Embed all failed after {total} chunks in {batches} batches: {error}"},
status_code=500,
)
logger.info("ebook_admin_embed_all_complete batches=%s chunks=%s", batches, total)
return templates.TemplateResponse(
request,
"partials/admin_status.html",
{"message": f"Embedded {total} chunks in {batches} batches of {config.embedding_batch_size}"},
)