Richie b995e9b6cb feat(ebook): add phrase metadata tables for protected phrase matching
Introduce four ORM models and their Alembic migration to support
phrase-based query matching in the ebook RAG engine:

- EbookCandidatePhrase: high-recall phrase candidates extracted per book,
  with source flags (ngram/yake/spacy/capitalized/metadata), scoring, and
  LLM judge results.
- EbookProtectedPhrase: phrases accepted by the LLM judge, with canonical
  id, importance, and nesting controls.
- EbookPhraseAlias: normalized aliases mapping to protected phrases.
- EbookChunkPhraseMention: precomputed phrase occurrences within chunks.

Export the new models from python.orm.richie and add a JSON_DOCUMENT
helper (JSON with JSONB postgres variant) for storing sample contexts.
2026-06-29 00:56:58 -04:00
2026-06-18 12:55:46 -04:00
2026-05-14 15:12:53 -04:00
2026-05-14 15:12:53 -04:00
2025-12-06 12:33:10 -05:00
2026-06-14 21:29:45 -04:00
2026-06-27 23:01:03 -04:00
2026-06-18 12:55:46 -04:00
2026-06-14 15:40:31 -04:00
2025-09-27 11:56:20 -04:00
2026-06-22 11:31:47 -04:00
2025-11-10 23:21:54 -05:00
2024-08-24 17:53:37 -04:00
2026-06-14 21:29:45 -04:00
2024-09-08 08:38:29 -04:00
2025-11-08 08:21:27 -05:00
2025-10-31 22:37:54 -04:00
S
Description
No description provided
Readme MIT
13 MiB
Languages
Python 81.7%
Nix 11.6%
HTML 3.8%
Rust 1.6%
CSS 0.7%
Other 0.5%