feat(scrape): vision OCR of image-only doc pages (support matrices) (#5)

Co-authored-by: claude <[email protected]>

.gitea/workflows/refresh.yml

@@ -37,6 +37,18 @@ 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: "1"
+  VISION_URL: http://192.168.0.2:11434
+  VISION_MODEL: qwen2.5vl:7b
+  VISION_MAX_NEW: "60"
+
   PRODUCT_NAME: morpheus
 
 jobs:
@@ -64,6 +76,9 @@ jobs:
         run: |
           python -m pip install -q --upgrade pip
           python -m pip install -q -r requirements.txt
+          # Vision OCR deps (Pillow) — only the scrape step needs these; kept
+          # out of requirements.txt so they never bloat the server image.
+          python -m pip install -q -r requirements-vision.txt
 
       # ---- Phase 1: scrape ---------------------------------------
       - name: Refresh bundle catalog