feat: initialize bangwen recruitment aggregation and search engine

- Rust core engine with HTTP ingestion gateway, hybrid search, and white-box resume matching - Python edge collectors supporting declarative TOML and specialized adapters - PostgreSQL schema migrations with pgvector embedding support - Hardened security controls: strict CSP, terminal sanitization, and input boundary validation - Multi-service container orchestration with dedicated non-root execution
2026-10-23 23:44:10 +08:00
commit 1059be1b62
61 changed files with 10489 additions and 0 deletions
@@ -0,0 +1,57 @@
+services:
+  postgres:
+    image: pgvector/pgvector:pg16
+    container_name: bangwen-postgres
+    restart: unless-stopped
+    environment:
+      POSTGRES_USER: bangwen
+      POSTGRES_PASSWORD: bangwen_dev
+      POSTGRES_DB: bangwen
+    ports:
+      - "127.0.0.1:5432:5432"
+    volumes:
+      - pgdata:/var/lib/postgresql/data
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U bangwen -d bangwen"]
+      interval: 5s
+      timeout: 5s
+      retries: 5
+
+  core:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: bangwen-core
+    restart: unless-stopped
+    depends_on:
+      postgres:
+        condition: service_healthy
+    environment:
+      DATABASE_URL: postgres://bangwen:bangwen_dev@postgres:5432/bangwen
+      SERVER_HOST: "0.0.0.0"
+      SERVER_PORT: "8080"
+      LOG_LEVEL: info
+      INGEST_TOKEN: ${INGEST_TOKEN:?INGEST_TOKEN must be set in .env or environment}
+      OLLAMA_BASE_URL: ${OLLAMA_BASE_URL:-http://host.docker.internal:11434}
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    ports:
+      - "127.0.0.1:8080:8080"
+
+  collector:
+    build:
+      context: ./collectors
+      dockerfile: Dockerfile
+    container_name: bangwen-collector
+    restart: unless-stopped
+    depends_on:
+      - core
+    environment:
+      CORE_INGEST_URL: http://core:8080/api/v1/ingest
+      INGEST_TOKEN: ${INGEST_TOKEN:?INGEST_TOKEN must be set in .env or environment}
+      SCHEDULE_INTERVAL_HOURS: 6
+    volumes:
+      - ./collectors/config.toml:/app/config.toml:ro
+
+volumes:
+  pgdata: