Skip to content
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.

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

Another approach could be to run history through an embeddings API, save the embeddings to a Vector DB, then do a lookup for relevant _memories_ on each step. #89

Closed
KadirErturk4r opened this issue Apr 3, 2023 · 3 comments

Comments

@KadirErturk4r
Copy link

          Another approach could be to run history through an embeddings API, save the embeddings to a Vector DB, then do a lookup for relevant _memories_ on each step.

Originally posted by @tedspare in #5 (comment)

That reminds me cross attention but in different context.

@KadirErturk4r KadirErturk4r closed this as not planned Won't fix, can't repro, duplicate, stale Apr 3, 2023
@jantic
Copy link

jantic commented Apr 3, 2023

Any reason why this was closed? This is a great idea as far as I can tell....

@KadirErturk4r
Copy link
Author

sorry it is my bad. I tried to add as a comment, but created a new issue.

@KadirErturk4r
Copy link
Author

and also I wish you attach public models like GPT4All, so that we dont need GPT4

tgonzales pushed a commit to tgonzales/Auto-GPT that referenced this issue Apr 19, 2023
…de_version_requirement

chore: specify node version in readme and package.json
Say383 pushed a commit to Say383/Auto-GPT that referenced this issue Sep 8, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants