Files
adolf/docker-compose.yml
Alvis 32089ed596 Add routecheck service and CommuteTool fast tool
routecheck/ — FastAPI service (port 8090):
  - Image captcha (PIL: arithmetic problem, noise, wave distortion)
  - POST /api/captcha/new + /api/captcha/solve → short-lived token
  - GET /api/route?from=lat,lon&to=lat,lon&token=... → Yandex Routing API
  - Internal bypass via INTERNAL_TOKEN env var (for CommuteTool)
  - HTTPS proxy forwarded to reach Yandex API from container

CommuteTool (fast_tools.py):
  - Matches commute/traffic/arrival time queries
  - Calls routecheck /api/route with ROUTECHECK_TOKEN
  - Hardcoded route: Balashikha home → Moscow center
  - Returns traffic-adjusted travel time + delay annotation

Needs: YANDEX_ROUTING_KEY + ROUTECHECK_TOKEN in .env

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-13 07:08:48 +00:00

107 lines
2.8 KiB
YAML

services:
bifrost:
image: maximhq/bifrost
container_name: bifrost
ports:
- "8080:8080"
volumes:
- ./bifrost-config.json:/app/data/config.json:ro
environment:
- APP_DIR=/app/data
- APP_PORT=8080
- LOG_LEVEL=info
extra_hosts:
- "host.docker.internal:host-gateway"
restart: unless-stopped
deepagents:
build: .
container_name: deepagents
ports:
- "8000:8000"
environment:
- PYTHONUNBUFFERED=1
# Bifrost gateway — all LLM inference goes through here
- BIFROST_URL=http://bifrost:8080/v1
# Direct Ollama GPU URL — used only by VRAMManager for flush/prewarm
- OLLAMA_BASE_URL=http://host.docker.internal:11436
- DEEPAGENTS_MODEL=qwen3:4b
- DEEPAGENTS_COMPLEX_MODEL=qwen3:8b
- DEEPAGENTS_ROUTER_MODEL=qwen2.5:1.5b
- SEARXNG_URL=http://host.docker.internal:11437
- GRAMMY_URL=http://grammy:3001
- CRAWL4AI_URL=http://crawl4ai:11235
- ROUTECHECK_URL=http://routecheck:8090
- ROUTECHECK_TOKEN=${ROUTECHECK_TOKEN}
extra_hosts:
- "host.docker.internal:host-gateway"
depends_on:
- openmemory
- grammy
- crawl4ai
- bifrost
- routecheck
restart: unless-stopped
openmemory:
build: ./openmemory
container_name: openmemory
ports:
- "8765:8765"
environment:
# Extraction LLM runs on GPU — qwen2.5:1.5b for speed (~3s)
- OLLAMA_GPU_URL=http://host.docker.internal:11436
- OLLAMA_EXTRACTION_MODEL=qwen2.5:1.5b
# Embedding (nomic-embed-text) runs on CPU — fast enough for search (50-150ms)
- OLLAMA_CPU_URL=http://host.docker.internal:11435
extra_hosts:
- "host.docker.internal:host-gateway"
restart: unless-stopped
grammy:
build: ./grammy
container_name: grammy
ports:
- "3001:3001"
environment:
- TELEGRAM_BOT_TOKEN=${TELEGRAM_BOT_TOKEN}
- DEEPAGENTS_URL=http://deepagents:8000
restart: unless-stopped
cli:
build:
context: .
dockerfile: Dockerfile.cli
container_name: cli
environment:
- DEEPAGENTS_URL=http://deepagents:8000
depends_on:
- deepagents
stdin_open: true
tty: true
profiles:
- tools
routecheck:
build: ./routecheck
container_name: routecheck
ports:
- "8090:8090"
environment:
- YANDEX_ROUTING_KEY=${YANDEX_ROUTING_KEY}
- INTERNAL_TOKEN=${ROUTECHECK_TOKEN}
- HTTPS_PROXY=http://host.docker.internal:56928
extra_hosts:
- "host.docker.internal:host-gateway"
restart: unless-stopped
crawl4ai:
image: unclecode/crawl4ai:latest
container_name: crawl4ai
ports:
- "11235:11235"
environment:
- CRAWL4AI_LOG_LEVEL=WARNING
shm_size: "1g"
restart: unless-stopped