Add PDF document service with AI extraction and per-app settings
- New `features/doc-service` FastAPI microservice: PDF upload, async text extraction (pdfplumber), AI classification via Anthropic/Ollama/ LM Studio, per-user categories, file download - Alembic migration isolated with `alembic_version_doc_service` table - Main backend: httpx proxy routers for /api/documents/* and /api/documents/categories/*, admin settings API at /api/settings/* - Runtime config in /config/doc_service_config.json (shared Docker volume); api_key masking on reads; atomic write with os.replace() - Frontend: DocumentsPage, DocumentAdminSettingsPage, updated AppsPage launcher hub, simplified Nav (removed Settings link), new routes - docker-compose: doc-service service, doc_data + app_config volumes, removed internal:true from backend-net for outbound AI API calls - Fix pre-commit hook: probe Docker socket path so git subprocess picks up Docker Desktop on macOS - Fix security_check.py: use sys.executable for bandit so venv python is used instead of system python Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
+28
-2
@@ -30,6 +30,30 @@ services:
|
||||
env_file: ./backend/.env
|
||||
environment:
|
||||
DATABASE_URL: postgresql+asyncpg://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-password}@db:5432/${POSTGRES_DB:-destroying_sap}
|
||||
DOC_SERVICE_URL: http://doc-service:8001
|
||||
volumes:
|
||||
- app_config:/config
|
||||
depends_on:
|
||||
db:
|
||||
condition: service_healthy
|
||||
networks:
|
||||
- backend-net
|
||||
|
||||
# ── Doc service (PDF extraction) ────────────────────────────────────────────
|
||||
doc-service:
|
||||
build:
|
||||
context: ./features/doc-service
|
||||
dockerfile: Dockerfile
|
||||
network: host
|
||||
user: "1001:1001"
|
||||
restart: unless-stopped
|
||||
environment:
|
||||
DATABASE_URL: postgresql+asyncpg://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-password}@db:5432/${POSTGRES_DB:-destroying_sap}
|
||||
DATA_DIR: /data/documents
|
||||
CONFIG_PATH: /config/doc_service_config.json
|
||||
volumes:
|
||||
- doc_data:/data/documents
|
||||
- app_config:/config
|
||||
depends_on:
|
||||
db:
|
||||
condition: service_healthy
|
||||
@@ -54,10 +78,12 @@ services:
|
||||
|
||||
volumes:
|
||||
postgres_data:
|
||||
doc_data: # PDF files persisted across restarts
|
||||
app_config: # Per-service runtime config JSON files
|
||||
|
||||
networks:
|
||||
# Internal-only: db ↔ backend ↔ frontend reverse proxy. No host routing.
|
||||
# backend-net: db ↔ backend ↔ doc-service. No host ports bound.
|
||||
# internal:true removed — doc-service needs outbound access for cloud AI providers.
|
||||
backend-net:
|
||||
internal: true
|
||||
# External-facing: only the frontend binds a host port through this network.
|
||||
frontend-net:
|
||||
|
||||
Reference in New Issue
Block a user