New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Building blocks: LLM utils #557

Open

sachinr opened this issue Oct 27, 2023 · 1 comment

Assignees

Labels

feature

Milestone

Nov 30 hitlist - ...

Member

sachinr commented Oct 27, 2023

SR: I need someone with more experience to flesh this out

sachinr added the feature label

sachinr added this to the Nov 30 hitlist - devxp/example apps milestone

miguel-nascimento self-assigned this

sachinr mentioned this issue

Nov 13 sprint #603

Open

21 tasks

Contributor

miguel-nascimento commented Dec 13, 2023 •

edited

Loading

llm-utils applet

Question: Do you guys like the approach that I made? Are you guys happy with the usage?
Is there any missing feature/util/config?

I saw some comments in the applet and I want to raise them here:

What if we export a default AI object using ChatOpenAI LLM? So we could support something like

import { chat } from 'ai/chat'
import { ai } from 'ai/general'

Unify invoke with run and allow undefined args
Currently, chat is different from the ai, (the latter is a more direct Q&A). The Chat API uses .invoke to send the request to the LLM service, and the AI API uses .run to do the same

What do you guys think about unifying both? Is it needed?

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