mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-14 23:01:09 +02:00
45063b88be
Add Google Gemini as a fallback provider that activates automatically when Ollama is overloaded or unavailable, ensuring LLM requests always succeed even under load. New provider (src/providers/google.py): - Full LLMProvider implementation using google-genai SDK - Chat completions (streaming + non-streaming) - Vision/multimodal support (base64 images) - Embeddings via text-embedding-004 - Model mapping: Ollama models → Gemini equivalents (gemma3:4b → gemini-2.0-flash, llava:7b → gemini-2.0-flash, etc.) Auto-fallback routing (src/providers/router.py): - Concurrent request tracking for Ollama (OLLAMA_MAX_CONCURRENT=3) - When Ollama concurrent > max: route to Google automatically - When Ollama fails: retry on Google with model mapping - Health check caching (5s TTL) to avoid hammering Ollama - Non-Ollama providers (openrouter, groq, together) are never fallback-routed - Fallback info included in /health endpoint response New config (src/config.py): - GOOGLE_API_KEY: enables Google provider - GOOGLE_DEFAULT_MODEL: default gemini-2.0-flash - AUTO_FALLBACK_ENABLED: toggle fallback (default: true) - OLLAMA_MAX_CONCURRENT: concurrent request threshold (default: 3) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| src | ||
| tests | ||
| .env.example | ||
| .gitignore | ||
| CLAUDE.md | ||
| docker-compose.dev.yml | ||
| docker-compose.yml | ||
| Dockerfile | ||
| pyproject.toml | ||
| requirements.txt | ||
| start.sh | ||