Stream LLM tokens in real-time, trim history, and reduce retriever k 7abe457
vaishnav Claude Opus 4.6 (1M context) commited on
Spaces:
Runtime error
Runtime error
Commit History
Raise HF max_new_tokens and load .env from any cwd 51f4eed
vaishnav Claude Opus 4.6 (1M context) commited on
Switch HF default to openai/gpt-oss-120b with auto provider routing 1c2dc4f
vaishnav Claude Opus 4.6 (1M context) commited on
Fix HuggingFace provider crash and harden chain init 332bfab
vaishnav Claude Opus 4.6 (1M context) commited on
make mistral default model a856301
vaishnav commited on
Update llm_setup/llm_setup.py 7dbb9b2 verified
make it a framework 429af6c
vaishnav commited on
update gradio sdk and add lfu caching e19d910
vaishnav commited on
use gemini-2.0-flash-thinking-exp-01-21 9206b9a verified
Use 1.5 flash 4cb7289 verified
add chat history ac53d3d
vaishnav commited on
add chat history 23d9a47
vaishnav commited on
Update Gemini model 8a2c920 verified
chatbot history added eb93a33
pdoshi commited on