claudeandClaude Opus 4.8
1d3e52a5ed
Some HPE pages carry information only inside an image. The Morpheus release schedule / support-lifecycle matrix (sf000111242en_us) is the case that surfaced this: the entire "which version ships when, when a stream hits Maintenance/EOL" table is a JPEG, so html_to_md dropped every value and retrieval could never answer "when does 8.x.x reach end of life". New scrape/vision.py (opt-in via VISION_OCR) transcribes qualifying images with a local Ollama vision model and appends a labeled markdown block to the page so the text is chunked, embedded and retrieved. Model/prompt chosen against ground truth on the matrix (14x4 cells): - qwen2.5vl:7b + a bare "transcribe the table" prompt: 55-56/56, ~18s, GPU-resident, and prompt-ROBUST (accurate without hand-tuning). - gemma3:12b needs an exact "read row by row, keep cells aligned" prompt or it shifts a column by one row; qwen2.5vl:32b is no more accurate and 5x slower (CPU spill). Both documented in the code. - Note: self-consistency (2 samples must agree) only catches RANDOM flakiness — a wrong read is stable across seeds — so every block also ships a "verify against the source image" caveat. Reliability/cost: - content-hash cache in corpus/.vision-cache/ (committed) — each unique image OCR'd once ever, shared across version bundles. - VISION_MAX_NEW bounds NEW OCRs per run so the first pass can't balloon into hours; the cache fills incrementally. Deferred count is logged. - every failure path degrades to the pre-vision behavior; never blocks the scrape. Also: - add the morpheus_release_schedule bundle (sf single-doc) + 2 eval golden queries for it. - fetch_single_doc: title falls back to the bundle title (not docId) when a page has no <h1> (sf solution articles). - Pillow in requirements-vision.txt (scrape-only; kept out of the server image), installed + VISION_* wired into refresh.yml. Verified locally: matrix transcribes to the exact 14-row table; second run is a cache hit (ocr=0). Co-Authored-By: Claude Opus 4.8 <[email protected]> Claude-Session: https://claude.ai/code/session_01LFowQzJu7k97QLCRDSAeh1
7 lines
379 B
Plaintext
7 lines
379 B
Plaintext
# Optional: local vision OCR of image-only doc pages (scrape/vision.py).
|
|
# Installed only in the refresh workflow, NOT baked into the server image —
|
|
# the MCP server never runs OCR, so keeping Pillow out of the base image
|
|
# keeps it lean (same reasoning as requirements-rerank.txt keeping out torch).
|
|
# requests (the Ollama client) is already in requirements.txt.
|
|
Pillow>=10.0
|