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

Feat: add ConversationTokenBufferMemory #2753

Closed
danny-avila opened this issue Sep 29, 2023 · 5 comments
Closed

Feat: add ConversationTokenBufferMemory #2753

danny-avila opened this issue Sep 29, 2023 · 5 comments
Labels
auto:enhancement A large net-new component, integration, or chain. Use sparingly. The largest features

Comments

@danny-avila
Copy link

Been running into needing this, from Python counterpart: https://python.langchain.com/docs/modules/memory/types/token_buffer

Maybe I can put in a PR for this as it's simple enough looking at the other memory classes.

@dosubot dosubot bot added the auto:enhancement A large net-new component, integration, or chain. Use sparingly. The largest features label Sep 29, 2023
@dosubot
Copy link

dosubot bot commented Sep 29, 2023

🤖

That's great to hear! Adding a ConversationTokenBufferMemory to langchainjs sounds like a valuable addition. It's wonderful that you're considering contributing by creating a pull request. If you're confident in your understanding of the existing memory classes and feel comfortable implementing this feature, I encourage you to go ahead and submit a PR. The maintainers will review it and provide feedback if needed. Thank you for your contribution!


This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

@ychen5601
Copy link
Contributor

Hi! I would like to work on this issue. I will take this on later this week. Thanks in advance!

@danny-avila
Copy link
Author

Hi! I would like to work on this issue. I will take this on later this week. Thanks in advance!

Great! If I had more time, I would've started already but this remains to be seen for the week. Will be on the lookout for your PR.

@ychen5601
Copy link
Contributor

ychen5601 commented Oct 10, 2023

@danny-avila after taking a look into the ticket, I noticed that method llm.get_num_tokens_from_messages from Python is not implemented in the JavaScript repo. I'm looking into a workaround for this but please expect a modest delay to the pull request.

This is my first PR in an open-source repository so thank you in advance for your patience, and any advice is greatly appreciated!

Copy link

dosubot bot commented Jan 30, 2024

Hi, @danny-avila,

I'm helping the langchainjs team manage their backlog and am marking this issue as stale. From what I understand, you proposed adding ConversationTokenBufferMemory to the repository, inspired by a similar feature in the Python counterpart. You and @ychen5601 have been discussing the potential pull request, and it seems there was a modest delay due to an unimplemented method from the Python repo in the JavaScript repo.

Could you please confirm if this issue is still relevant to the latest version of the langchainjs repository? If it is, please let the langchainjs team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days. Thank you!

@dosubot dosubot bot added the stale Issue has not had recent activity or appears to be solved. Stale issues will be automatically closed label Jan 30, 2024
@dosubot dosubot bot removed the stale Issue has not had recent activity or appears to be solved. Stale issues will be automatically closed label Jan 30, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
auto:enhancement A large net-new component, integration, or chain. Use sparingly. The largest features
Projects
None yet
Development

No branches or pull requests

2 participants