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

Making this persistent and with memory #4

Open
abdcef opened this issue Feb 25, 2023 · 2 comments
Open

Making this persistent and with memory #4

abdcef opened this issue Feb 25, 2023 · 2 comments

Comments

@abdcef
Copy link

abdcef commented Feb 25, 2023

Is it possible to make this persistent so that I do not have to repeat the embeddings?
Also to have longer conversations by the bot retaining the knowledge of previous queries

@davila7
Copy link
Owner

davila7 commented Feb 25, 2023

Yes, it's possible, you should save the embedding to a vector database like Pinecone.

For the chat to have long-term memory you can use this Langchain function
https://langchain.readthedocs.io/en/latest/modules/memory.html

If you can make progress on this you can do a PR and I'll add it to the repo.

@abdcef
Copy link
Author

abdcef commented Feb 28, 2023

Thanks. Yes, trying to explore in that direction.

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