We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Fix importmap
Fixed chat parsing issue when using Mistral template with system message
Refactoring to reduce code duplication
Fix text decoding in OpenAI non-streaming responses
Add support for non-standard OpenAI responses sent by llama.cpp
Fix for new llama.cpp API response body
Fix potential race condition when saving sessions
Don't try saving inactive sessions
Fixes to prediction preview
Disable prediction preview for AI Horde backend