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

Recipes for balancing agent response time and completeness/accuracy #87

Open

hinthornw opened this issue Sep 17, 2023 · 0 comments

Assignees

Contributor

hinthornw commented Sep 17, 2023

Collection of recipes.

Probably a few tactics people would want to employ:

Streaming to optimize time to first token
Callbacks for tools to respond with progress
Callbacks in runnable chains (or whatever other cognitive arch we propose)

May be a couple common "runtimes" too:

Chat apps where you can indeed stream/control the UX
Whatsapp/Discord/SMS/Twilio etc. bots that are beholden to webhook timeouts and can only send in batch

Use cases:

Retrieval Q&A -
- Perplexity clone
- Perplexity + more lookup to finalize answer
- More + various sources
Code tutor/copilots
- Like the "help me build this app" type of thing

hinthornw self-assigned this

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