Spaces:
Sleeping
Sleeping
Commit History
-
fix: use microsoft/Phi-3-mini-4k-instruct - officially supported free model
viktor-hirenkoea6f355 -
fix: use google/flan-t5-base - small, fast, 100% free model
viktor-hirenko26520e9 -
fix: switch to Mistral-7B model for better HF Inference API compatibility
viktor-hirenko5bb2eac -
fix: use google/flan-t5-large model for HF Inference API
viktor-hirenko4ce414b -
feat: migrate from Ollama to Hugging Face Inference API
viktor-hirenko- Replace Ollama with HF Inference API in llm_handler.py - Update config.py with HF model settings - Remove ollama dependencies, add huggingface_hub - Create app.py as HF Spaces entry point - Add HF token validation in main.py - Create README_HF.md with HF Spaces YAML frontmatter - Add comprehensive documentation: - DEPLOYMENT_GUIDE.md: Step-by-step deployment instructions - ENV_SETUP.md: Environment variables documentation - MIGRATION_SUMMARY.md: Complete migration overview - test_hf_integration.py: Integration test suite Ready for deployment to Hugging Face Spaces with free, permanent hosting.5fd4bb2 -
Initial commit: RAG system with local LLM
viktor-hirenko- Implement complete RAG pipeline with Ollama + ChromaDB - Add document processing (PDF, DOCX, TXT) - Integrate sentence-transformers for embeddings - Add Gradio web interface for Q&A - Include comprehensive documentation (EN/UK) - Add deployment guide and architecture docs - Configure environment variables and dependencies Tech stack: Python 3.9+, Ollama (llama3.2), ChromaDB, LangChain, Gradio40e5eae