Chinese OCR

Code/TODO.md

@@ -23,18 +23,46 @@
 
 Rationale: De-risk unknowns (Docling OCR quality, Ollama CPU inference speed) before building orchestrator.
 
-### 1a. Docker Compose + Docling
+### 1a. Docker Compose + Docling (DONE)
 
-- [ ] Docker Compose base (Docling service)
-- [ ] Test Docling API with sample PDFs (curl)
-- [ ] Validate OCR quality on real PDFs + generated samples
+- [x] Docker Compose base (Docling service)
+- [x] Test Docling API with sample PDFs (curl)
+- [x] Validate OCR quality on real PDFs + generated samples
+- [x] Test OCR on images (PNG) — works with `force_ocr=true`
 
-### 1b. Ollama
+**Docling API Spec:**
+- Image: `ds4sd/docling-serve:latest`
+- Port: `5001`
+- Endpoint: `POST /v1/convert/file`
+- Form params: `files=@<path>;type=application/pdf`, `to_formats=md`, `do_ocr=true`
+- Response: `{ "document": { "md_content": "..." }, "status": "success" }`
+- OCR engine: `easyocr` (default), supports CJK
 
-- [ ] Add Ollama to Docker Compose (Qwen3-1.7B, CPU mode)
-- [ ] Test structured extraction prompt (curl)
-- [ ] Measure inference time per document
-- [ ] Validate extraction accuracy (deadline, doc type, etc.)
+**OCR Options:**
+- `do_ocr=true` — enabled by default, processes bitmap content
+- `force_ocr=true` — use for images/scanned PDFs (replaces existing text with OCR)
+- `ocr_engine` — `easyocr` (default), `tesseract`, `rapidocr`, `tesserocr`, `ocrmac`
+- `ocr_lang` — language codes (engine-specific), e.g. `ch_sim` for Simplified Chinese
+
+**Tested Formats:**
+- PDF (Filing Receipt) — extracted text, tables, CJK content ✅
+- PNG (Email screenshot) — extracted subject, dates, recipient ✅ (CJK trademark garbled, may need `ocr_lang`)
+
+### 1b. Ollama (DONE)
+
+- [x] Add Ollama to Docker Compose (Qwen3-1.7B, CPU mode)
+- [x] Test structured extraction prompt (curl)
+- [x] Measure inference time per document (~15-30s on 4 vCPU)
+- [x] Validate extraction accuracy (deadline, doc type, etc.)
+
+**Ollama API Spec:**
+- Image: `ollama/ollama:0.9.3`
+- Port: `11434`
+- Model: `qwen3:1.7b` (~1.4 GB, auto-pulled on startup)
+- Endpoint: `POST /api/generate`
+- Body: `{"model":"qwen3:1.7b","prompt":"...","stream":false,"options":{"temperature":0}}`
+- Response: `{ "response": "<json>" }` (strip `<think>...</think>` tags in post-processing)
+- Note: Qwen3 includes reasoning by default; `/no_think` leaves empty tags, so strip instead
 
 ### 1c. Python Tools Service