mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-15 13:21:08 +02:00
1495dbe476
Python/FastAPI service providing unified OpenAI-compatible API for Ollama and cloud LLM providers (OpenRouter, Groq, Together). Features: - Chat completions with streaming (SSE) - Vision/multimodal support - Embeddings generation - Multi-provider routing (provider/model format) - Prometheus metrics - Optional Redis caching
25 lines
474 B
Text
25 lines
474 B
Text
# Service
|
|
PORT=3025
|
|
LOG_LEVEL=info
|
|
|
|
# Ollama (Primary)
|
|
OLLAMA_URL=http://localhost:11434
|
|
OLLAMA_DEFAULT_MODEL=gemma3:4b
|
|
OLLAMA_TIMEOUT=120
|
|
|
|
# OpenRouter (Cloud Fallback)
|
|
OPENROUTER_API_KEY=sk-or-v1-xxx
|
|
OPENROUTER_DEFAULT_MODEL=meta-llama/llama-3.1-8b-instruct
|
|
|
|
# Groq (Optional)
|
|
GROQ_API_KEY=gsk_xxx
|
|
|
|
# Together (Optional)
|
|
TOGETHER_API_KEY=xxx
|
|
|
|
# Caching (Optional)
|
|
REDIS_URL=redis://localhost:6379
|
|
CACHE_TTL=3600
|
|
|
|
# CORS
|
|
CORS_ORIGINS=http://localhost:5173,https://mana.how
|