Spaces:
Running
Running
Bhaskar Ram
fix: sentence-aware chunking, score threshold, DOCX tables, streaming error handling, LLM_MODEL env var
2623b17 | # Environment variable template — copy to .env and fill in your values | |
| # Required: Your Hugging Face API token (get one at https://huggingface.co/settings/tokens) | |
| HF_TOKEN=hf_... | |
| # Optional: Override the default LLM model (defaults to Llama 3.1 8B if not set) | |
| # LLM_MODEL=meta-llama/Llama-3.1-8B-Instruct | |
| # LLM_MODEL=mistralai/Mistral-7B-Instruct-v0.3 | |
| # LLM_MODEL=mistralai/Mixtral-8x7B-Instruct-v0.1 | |
| # Optional: Gradio server settings | |
| # GRADIO_SERVER_PORT=7860 | |
| # GRADIO_SERVER_NAME=0.0.0.0 | |