justin/morpheus-docs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(scrape): make vision OCR a per-bundle allowlist, not a corpus sweep (#6)

Browse Source 
Co-authored-by: claude <[email protected]>
This commit was merged in pull request #6.
This commit is contained in:
claude
2026-08-06 11:39:47 -04:00
committed by claude
parent 43d891968e
commit 08c4b4b71d
66 changed files with 223 additions and 447 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitea/workflows/refresh.yml
+7 -7
View File
@@ -39,13 +39,13 @@ env:
OLLAMA_URLS: http://192.168.0.2:11435,http://192.168.0.2:11436,http://192.168.0.125:11434,http://192.168.0.126:11434
EMBED_MODEL: nomic-embed-text
# Vision OCR of image-only pages (support/lifecycle matrices etc. — see
# scrape/vision.py). Uses the host's primary Ollama on :11434, the only one
# with a vision model; the embed pool above is nomic-only. qwen2.5vl:7b
# scored best on the release-schedule matrix (55-56/56, ~18s, GPU-resident,
# prompt-robust). Content-hash cached in corpus/.vision-cache/; VISION_MAX_NEW
# bounds NEW OCRs per run so the cache fills incrementally instead of a
# multi-hour first pass. Any failure degrades to the pre-vision behavior.
# Vision OCR of image-only data pages (the release-schedule matrix — see
# scrape/vision.py). OCR is a per-bundle opt-in (BundleSpec.ocr), so this
# only runs on allowlisted docs, NOT every screenshot in the corpus. Uses
# the host's primary Ollama on :11434, the only one with a vision model
# (the embed pool above is nomic-only). qwen2.5vl:7b scored best on the
# matrix (55-56/56, ~18s, GPU-resident). Any failure degrades to the
# pre-vision behavior.
VISION_OCR: "1"
VISION_URL: http://192.168.0.2:11434
VISION_MODEL: qwen2.5vl:7b