Unpinned docling-core resolved to 2.84.0 on image rebuild and removed
legacy_doc.base.BoundingBox, breaking extraction at import time
(EXTRACTION_FAILED for every document). 2.19.x verified live: import OK,
satisfies docling<2.15 and docling-ibm-models>=2.19.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Docling's DocumentConverter shape (text_items, prov[0].page_no,
export_to_markdown signature) still moves between 2.x minor releases.
Cap docling to >=2.0.0,<2.15 so a wheel bump cannot silently break
the defensive walkers in app/ingestion/docling_extractor.py until a
staging smoke test has run against the new minor.
Every other runtime dep gets the same major/minor upper bound:
- web/api: fastapi <0.117, uvicorn <0.33, pydantic <3
- db: sqlalchemy <2.1, psycopg <3.3, alembic <1.14
- search: opensearch-py <3, qdrant-client <1.13
- ingest: ocrmypdf <17, pikepdf <10, pypdf <6
- ml: FlagEmbedding <2, sentence-transformers <4, transformers <5,
torch <3, numpy <3
- ops/utils: structlog <26, orjson <4, httpx <0.29, click <9
Lift any specific upper bound only after the corresponding regression
test passes on a staging upgrade.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
