Pass HF_TOKEN to embedding model to avoid 429 rate limits

Stream LLM tokens in real-time, trim history, and reduce retriever k

Restore full URL list in configs/config.py

Raise HF max_new_tokens and load .env from any cwd

Switch HF default to openai/gpt-oss-120b with auto provider routing

Unpin gradio to match HF Spaces base image

Fix HuggingFace provider crash and harden chain init

change embeddings

Update configs/config.py

update requirements

update requirements

update requirements

update requirements

update requirements.txt

make mistral default model

refactor UI and embedding of URL's

pull latest changes

Add CLAUDE.md for Claude Code guidance

Update requirements.txt

Update README.md

Update requirements.txt

Update README.md

Update README.md

Update configs/config.py

Update configs/config.py

Update app.py

Update configs/config.py

Update llm_setup/llm_setup.py

Update configs/config.py

Update configs/config.py

Update configs/config.py

Update configs/config.py

Update configs/config.py

Update configs/config.py

Update configs/config.py

Create .env

Update README.md

Update README.md

Update configs/config.py

Update configs/config.py

Create .env

make it a framework

implement streaming

Update configs/config.py

Update configs/config.py

Update configs/config.py

Add prompt to ask followup questions

Update README.md

Update configs/config.py

Merge branch 'main' of hf.co:spaces/vaishnaveswar/AIVIZ-BOT