fa1bddf537
Open WebUI's OpenAI connection to LiteLLM was silently 401ing on every request (OPENAI_API_KEY=dummy vs LiteLLM's real master key), so none of the litellm-routed models (judge, tip-generator, kimi-agent, OpenRouter free tier) ever appeared in the model picker -- only the direct Ollama connection's models did. Key is now sourced from openwebui/.env (gitignored), matching the langfuse key pattern already used elsewhere.
36 lines
1.2 KiB
YAML
36 lines
1.2 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=${ANTHROPIC_API_KEY}
|
|
- OLLAMA_BASE_URL=http://host.docker.internal:11436
|
|
- OPENAI_API_BASE_URL=http://host.docker.internal:4000/v1
|
|
- OPENAI_API_KEY=${LITELLM_MASTER_KEY}
|
|
# 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
|
|
- ENABLE_API_KEYS=True
|