fix: use microsoft/Phi-3-mini-4k-instruct - officially supported free model

fix: use google/flan-t5-base - small, fast, 100% free model

fix: switch to Mistral-7B model for better HF Inference API compatibility

fix: handle StopIteration in HF Inference API streaming

fix: update huggingface_hub version to resolve dependency conflicts

fix: add HF Space YAML metadata to README

Merge HF Space initial files

initial commit

fix: use google/flan-t5-large model for HF Inference API

docs: add quick start guide for 5-minute deployment

feat: migrate from Ollama to Hugging Face Inference API

Initial commit: RAG system with local LLM