What's Changed
-
Open router implementation + UI optimizations. by @Hairetsucodes in #16
-
Fedora fix2 by @Hairetsucodes in #17
-
Gpu/mac m series by @Hairetsucodes in #20
-
Fedora cuda fix by @Hairetsucodes in #21
-
Azure openai endpoint by @Hairetsucodes in #22
-
Update version to 1.0.4 and refactor LLM components for improved clar… by @Hairetsucodes in #23
-
Added Llama.cpp support
-
Added Transformers support
-
Added Cuda Support for Windows and Linux
-
Ollama no longer required, Select your ollama folder and launch with llamacpp or use ollama.
-
UX Improvements
-
Improved the UI Styling to be more consistent.
-
Fixed error in too large of chunks being embedded by local model with web crawl/documentation
-
Added Azure Open AI support
Full Changelog: v1.0.3...v1.0.4