juioudgdgeue894

FR: Utilise vision models via image attachments

5

Currently, Sidekick only allows document file uploads but does not support actual image analysis. Adding vision model capabilities would allow users to upload images for processing, enabling object recognition, scene...

BUG: App crashes during code generation

1

Example prompt that continuously crashes Sidekick (infinite beachball spinning wheel): Generate HTML for a website homepage, it should include a header, hero section, about section, CTA and footer. Regardless of...

FR: A model selector within the chat window

1

Would be very handy to be able to quickly select and switch models from within the chat window instead of going to settings. Would also be good to be able...

Feature Request: The ability to attach documents and use RAG to chat with them

2

Would be great to be able to attach a document (.txt, .pdf, .csv) and use the LLM to "chat" with the document and learn more about it.

Feature Request: Ability to perform web search via Tavily or similar

1

Hollama is _nearly_ the perfect LLM application! Being able to perform web searches via Tavily would take it up a further notch.

Would be great to be able to change the default / system prompt and also a separate prompt for each individual chat