Initial Services

Code/TODO.md

@@ -19,18 +19,42 @@
 - [x] Both sync directions tested and working
 - [x] Old JingTian-Rclone repo archived on Gitea
 
-## Phase 1: Foundation
+## Phase 1: Services (Services-First Approach)
 
-- [ ] Init Go module
-- [ ] SQLite schema + migrations (documents, extractions, processing_log)
+Rationale: De-risk unknowns (Docling OCR quality, Ollama CPU inference speed) before building orchestrator.
+
+### 1a. Docker Compose + Docling
+
+- [ ] Docker Compose base (Docling service)
+- [ ] Test Docling API with sample PDFs (curl)
+- [ ] Validate OCR quality on real PDFs + generated samples
+
+### 1b. Ollama
+
+- [ ] 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.)
+
+### 1c. Python Tools Service
+
+- [ ] FastAPI + openpyxl service
+- [ ] Endpoints: read tracker, write/update rows, get column schema
+- [ ] Test with sample Tracker.xlsx
+
+### 1d. Manual Integration Test
+
+- [ ] Chain test: PDF → Docling → Ollama → Tools → Excel updated
+- [ ] Document any issues / adjustments needed
+
+## Phase 2: Go Orchestrator
+
+- [ ] Init Go module in Tracker/
 - [ ] Config loading (YAML)
-- [ ] Docker Compose (Docling, Ollama, Python Tools, Go server)
-
-## Phase 2: Pipeline Core
-
+- [ ] SQLite schema + migrations (documents, extractions, processing_log)
 - [ ] Docling HTTP client
-- [ ] Ollama HTTP client + structured extraction prompt
-- [ ] Tools service (FastAPI + openpyxl Excel endpoints)
+- [ ] Ollama HTTP client
+- [ ] Tools service HTTP client
 - [ ] File watcher (inotify on Ubuntu, 2-min stability check via SHA256 hash)
 - [ ] State tracker integration (new/changed/skip logic)
 - [ ] Pipeline orchestrator (read latest Tracker before writing, merge not overwrite)