danny-avila / LibreChat

Enhanced ChatGPT Clone: Features Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. Actively in public development.
https://librechat.ai/
MIT License
19.4k stars 3.24k forks source link

[Bug]: Gemini's response cut off in half way #4754

Closed TheValkyrja closed 1 week ago

TheValkyrja commented 1 week ago

What happened?

When using Gemini endpoint and setting the model as gemini-exp-1114, AI's response cut off halfway, showing "The response is incomplete; it's either still processing, was cancelled, or censored. Refresh or try a different prompt." after refresh, the response shown as "network error". This only happens while using gemini-exp-1114 the specific model but not happening while using other geminis.

i found similar problem in #4440 , however didn't experienced the problem in gemini-1.5-pro-002 but in gemini-exp-1114.

Steps to Reproduce

1.set the model to gemini-exp-1114 2.give a relatively long promt 3.the response cut in half way.

What browsers are you seeing the problem on?

No response

Relevant log output

No response

Screenshots

image image

Code of Conduct