Skip to content

Conversation

mkrueger12
Copy link
Contributor

No description provided.


#### User Request Schema for Embedding Route

TBU
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looking forward to see proposed unified requests/responses 👀 The remaining workflow should be fairly close to the chat API.

@roma-glushko roma-glushko self-requested a review February 11, 2024 10:21
@roma-glushko roma-glushko added the enhancement New feature or request label Feb 11, 2024
....
-0.0028842222,
],
"token_count": {
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I have recently changed token_count to token_usage. I feel like this is a bit more explicit.


## Future Work

- Could we abstract away the entire RAG architecture? A single endpoint that takes a chat message -> embeds -> text semantic search -> LLM -> response
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This actually sounds like an idea for another service that would use Glide to talk to LLMs while providing RAG related addition to Glide's workflows. @mkrueger12 what do you think? What would be MVP for such a service?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants