Yassine Mhirsi
feat: Add topic similarity service using Google Generative AI embeddings, enabling improved topic matching and similarity analysis. Update topic extraction logic to utilize this service and enhance overall functionality.
a453c29
| fastapi>=0.115.0 | |
| uvicorn[standard]>=0.29.0 | |
| python-multipart>=0.0.6 | |
| python-dotenv>=1.0.0 | |
| pydantic>=2.5.0 | |
| # API Clients | |
| requests>=2.31.0 | |
| groq>=0.9.0 | |
| supabase>=2.0.0 | |
| google-genai>=0.2.0 | |
| # LangChain | |
| langchain>=0.1.0 | |
| langchain-core>=0.1.0 | |
| langchain-groq>=0.1.0 | |
| langsmith>=0.1.0 | |
| # Audio processing (optionnel si vous avez besoin de traitement local) | |
| soundfile>=0.12.1 | |
| # Hugging Face | |
| transformers>=4.35.0 | |
| torch>=2.0.1 | |
| # Autres dépendances | |
| numpy>=1.26.4 | |
| scikit-learn>=1.3.0 | |
| mcp>=1.0.0 | |
| # Note: fastapi-mcp peut ne pas exister officiellement, | |
| # vous devrez probablement créer votre propre intégration | |
| # generation-model | |
| protobuf>=3.20.1,<4.0.0 | |
| transformers[sentencepiece] | |
| sentencepiece | |
| accelerate | |
| datasets | |
| evaluate | |
| rouge-score | |
| bert-score |