Skip to content
This repository has been archived by the owner on Oct 11, 2024. It is now read-only.

Let users choose between local/hosted inference & cloud APIs #129

Open
3 of 6 tasks
frgfm opened this issue Mar 15, 2024 · 4 comments
Open
3 of 6 tasks

Let users choose between local/hosted inference & cloud APIs #129

frgfm opened this issue Mar 15, 2024 · 4 comments
Labels
endpoint: code module: services type: feat

Comments

@frgfm
Copy link
Member

frgfm commented Mar 15, 2024 •
edited
Loading

It makes sense that some users won't have compatible hardware to run LLMs locally. In that case, they might want to use external APIs for this.

It could be interesting to provide the following options:
@bright258
Copy link

I agree.

@frgfm
Copy link
Member Author

frgfm commented May 13, 2024

I agree.

@bright258 which LLM provider would you like to use most? We now have full support of Groq & Ollama

@bright258
Copy link

OpenAI

@frgfm frgfm mentioned this issue May 15, 2024
Merged
@frgfm
Copy link
Member Author

frgfm commented May 15, 2024 •
edited
Loading

OpenAI

@bright258 Done :) Just merged #163

@sarthakkapila sarthakkapila mentioned this issue May 28, 2024
Closed
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees
No one assigned
Labels
endpoint: code module: services type: feat
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

feat(llm): add integration for Mistral, Gemini and Claude
2 participants
@frgfm @bright258