-
Notifications
You must be signed in to change notification settings - Fork 5.3k
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
Integrate Mem0 for providing long-term memory for AI Agents #3389
Conversation
@microsoft-github-policy-service agree company="Mem0" |
@Dev-Khant thanks for the PR. we would love to have this implementation in a notebook. can you please put the working code on the notebook. |
Hi @Hk669, Thanks for reviewing the PR. I have added the colab notebook link, please check. |
thanks for adding in the link, we would love to have the notebook in the repository. this should help you: https://github.com/microsoft/autogen/blob/main/notebook/contributing.md#how-to-get-a-notebook-displayed-on-the-website |
love mem0 and taranjeet tools :-) |
Hey @Hk669 I added the notebook. |
|
Sorry, I forgot about it. It's done now. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
looks good to me. thanks @Dev-Khant
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you @Dev-Khant for the PR. I've two quick questions.
- Why there are changes to
autobuild_agent_library.ipynb
andlats_search.ipynb
? - Can we add memory to
Mem0
inside a chat conversations? In the examples, it looks like we can only retrieve memory. Would you like to add support to adding memory automatically? I believe that would bring more value to the users.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please see the comments.
@Dev-Khant -- can you also please improve the description of this PR to explain what this PR is doing. Useful to do that in general to speed up the review process. |
Hi @thinkall Thanks for reviewing the PR. Answers for your questions:
Please share any feedbacks or suggestions on how can we use |
Sorry my bad, should have written proper description. Will take care of this from now on! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you @Dev-Khant for the updates.
You may want to start with extending ConversableAgent instead of updating it directly. There are some examples under folder agentchat/contrib
. But this can be done in a separate PR.
@thinkall We were already planning to extend the ConversibleAgent class itself, but still, we wanted to explore the best way to integrate |
@gagb Please let me know if anything is pending from my side for the PR. Thanks! |
Added documentation and a notebook example demonstrating how to use memory with AI agents. Here Mem0 is used for managing the memory related operations.
Why are these changes needed?
It helps users to have a memory component attached to their agents. So AI agents can remember what user is talking about.
Related issue number
Checks