feat: initialize Hypothesis Machine Pi extension

2026-07-31 22:36:16 +03:00
commit 528983ee50
57 changed files with 7790 additions and 0 deletions
@@ -0,0 +1,101 @@
+name: hypothesis-machine
+
+x-firecrawl-env: &firecrawl-env
+  REDIS_URL: redis://redis:6379
+  REDIS_RATE_LIMIT_URL: redis://redis:6379
+  PLAYWRIGHT_MICROSERVICE_URL: http://playwright-service:3000/scrape
+  POSTGRES_USER: postgres
+  POSTGRES_PASSWORD: postgres
+  POSTGRES_DB: postgres
+  POSTGRES_HOST: nuq-postgres
+  POSTGRES_PORT: "5432"
+  USE_DB_AUTHENTICATION: "false"
+  NUQ_RABBITMQ_URL: amqp://rabbitmq:5672
+  ENV: local
+  HOST: 0.0.0.0
+  PORT: "3002"
+  SEARXNG_ENDPOINT: http://searxng:8080
+  NUM_WORKERS_PER_QUEUE: "2"
+  CRAWL_CONCURRENT_REQUESTS: "4"
+  MAX_CONCURRENT_JOBS: "3"
+
+services:
+  searxng:
+    image: searxng/searxng:latest
+    restart: unless-stopped
+    ports: ["127.0.0.1:${SEARXNG_PORT:-8888}:8080"]
+    volumes: ["./searxng/settings.yml:/etc/searxng/settings.yml:ro"]
+    environment:
+      SEARXNG_BASE_URL: http://localhost:8080/
+    security_opt: ["no-new-privileges:true"]
+    cap_drop: ["ALL"]
+    cap_add: ["CHOWN", "SETGID", "SETUID"]
+    networks: [research]
+
+  firecrawl:
+    image: ghcr.io/firecrawl/firecrawl:latest
+    restart: unless-stopped
+    ports: ["127.0.0.1:3002:3002"]
+    environment: *firecrawl-env
+    command: node dist/src/harness.js --start-docker
+    depends_on:
+      redis: { condition: service_started }
+      rabbitmq: { condition: service_healthy }
+      nuq-postgres: { condition: service_started }
+      playwright-service: { condition: service_started }
+    security_opt: ["no-new-privileges:true"]
+    cap_drop: ["ALL"]
+    networks: [research, firecrawl-backend]
+
+  playwright-service:
+    image: ghcr.io/firecrawl/playwright-service:latest
+    restart: unless-stopped
+    environment:
+      PORT: "3000"
+      ALLOW_LOCAL_WEBHOOKS: "false"
+      BLOCK_MEDIA: "true"
+      MAX_CONCURRENT_PAGES: "4"
+    shm_size: 1gb
+    security_opt: ["no-new-privileges:true"]
+    cap_drop: ["ALL"]
+    tmpfs: ["/tmp/.cache:noexec,nosuid,size=1g"]
+    networks: [firecrawl-backend, research]
+
+  redis:
+    image: redis:7-alpine
+    restart: unless-stopped
+    command: redis-server --bind 0.0.0.0 --save "" --appendonly no
+    security_opt: ["no-new-privileges:true"]
+    cap_drop: ["ALL"]
+    cap_add: ["SETGID", "SETUID"]
+    networks: [firecrawl-backend]
+
+  rabbitmq:
+    image: rabbitmq:3-alpine
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "rabbitmq-diagnostics", "-q", "check_running"]
+      interval: 5s
+      timeout: 5s
+      retries: 8
+    security_opt: ["no-new-privileges:true"]
+    networks: [firecrawl-backend]
+
+  nuq-postgres:
+    image: ghcr.io/firecrawl/nuq-postgres:latest
+    restart: unless-stopped
+    environment:
+      POSTGRES_USER: postgres
+      POSTGRES_PASSWORD: postgres
+      POSTGRES_DB: postgres
+    volumes: ["nuq-data:/var/lib/postgresql/data"]
+    security_opt: ["no-new-privileges:true"]
+    networks: [firecrawl-backend]
+
+networks:
+  research: {}
+  firecrawl-backend:
+    internal: true
+
+volumes:
+  nuq-data: {}