Open Ph0rk0z opened 3 months ago
couldnt you use litellm to act as a passthrough?
It was easier editing the code but I got stuck on the search. Now someone has made it happen so we can finally use this: https://github.com/stitionai/devika/pull/70
Not sure I understand. Why not using litellm? It's easier to handle models with litellm than having to deal with changing the URL. Mistral large and its function calling seems promising.
because I'm not using an API. i'm using my own model through textgen
You can use litellm to point towards OpenAI API and change the URL to point to the textgen local URL apparently.
It's 10x easier to just add the endpoint parameter to the openAI initialization than to run another proxy server.
A lot of local servers use openAPI spec. tabbyAPI, textgen, llama.cpp server, etc. Is it possible to add support for that? ollama is very limiting and I want to use this with 70b+. I'm of course going to kludge the code to try but you may be able to support many projects all at once by generalizing one API.