7ef3ffa00e
Move services out of the monolithic openai/docker-compose.yml: - ollama/ — ollama GPU + CPU inference servers - openwebui/ — open-webui chat UI (uses env var for ANTHROPIC_API_KEY) - searxng/ — SearXNG container + searxng-mcp MCP server (port 3102) openai/ now contains only: litellm, langfuse, qdrant, faster-whisper, silero-tts, pipecat. searxng-mcp exposes a single searxng_search tool via MCP HTTP on :3102. Registered in ~/.claude.json as the "searxng" MCP server. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
34 lines
1.1 KiB
YAML
34 lines
1.1 KiB
YAML
services:
|
|
open-webui:
|
|
image: ghcr.io/open-webui/open-webui:main
|
|
container_name: open-webui
|
|
ports:
|
|
- "3125:8080"
|
|
volumes:
|
|
- /mnt/ssd/ai/open-webui:/app/backend/data
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
restart: always
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
environment:
|
|
- ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
|
|
- OPENAI_API_BASE_URL=http://host.docker.internal:4000/v1
|
|
- OPENAI_API_KEY=dummy
|
|
# STT — Faster-Whisper large-v3-turbo
|
|
- AUDIO_STT_ENGINE=openai
|
|
- AUDIO_STT_OPENAI_API_BASE_URL=http://host.docker.internal:8880/v1
|
|
- AUDIO_STT_OPENAI_API_KEY=dummy
|
|
- AUDIO_STT_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
|
|
# TTS — Silero v4
|
|
- AUDIO_TTS_ENGINE=openai
|
|
- AUDIO_TTS_OPENAI_API_BASE_URL=http://host.docker.internal:8881/v1
|
|
- AUDIO_TTS_OPENAI_API_KEY=dummy
|
|
- AUDIO_TTS_MODEL=silero
|
|
- AUDIO_TTS_VOICE=onyx
|