Add a conversation memory that combines a (optionally persistent) vectorstore history with a token buffer #22155
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Ignored Deployment
|
dosubot
bot
added
size:L
isahers1
reviewed
Jun 13, 2024
libs/langchain/langchain/memory/token_buffer_vectorstore_memory.py
Outdated
Show resolved
Hide resolved
|
BTW, I'm using this routinely with persistence in my personal chatbots and am constantly amazed at how frequently the chatbot recalls something relevant from a previous conversation. For small (7b) local models, this really works much better than the conversation summary chain. I think a maintainer needs to approve the required workflows? |
lstein
force-pushed
the
conversation_memory_vectorstore
branch
from
f1e65aa
to
ba23101
Compare
|
Deployment failed with the following error: |
|
The |
|
@isahers1 All tests are passing, documentation looks good. At what point does this get merged with the main branch — or is more needed to be done? |
|
Just merged, sorry for the delay! |
hinthornw
pushed a commit
that referenced
this pull request
Jul 3, 2024
…torstore history with a token buffer (#22155) **langchain: ConversationVectorStoreTokenBufferMemory** -**Description:** This PR adds ConversationVectorStoreTokenBufferMemory. It is similar in concept to ConversationSummaryBufferMemory. It maintains an in-memory buffer of messages up to a preset token limit. After the limit is hit timestamped messages are written into a vectorstore retriever rather than into a summary. The user's prompt is then used to retrieve relevant fragments of the previous conversation. By persisting the vectorstore, one can maintain memory from session to session. -**Issue:** n/a -**Dependencies:** none -**Twitter handle:** Please no!!! - [X] **Add tests and docs**: I looked to see how the unit tests were written for the other ConversationMemory modules, but couldn't find anything other than a test for successful import. I need to know whether you are using pytest.mock or another fixture to simulate the LLM and vectorstore. In addition, I would like guidance on where to place the documentation. Should it be a notebook file in docs/docs? - [X] **Lint and test**: I am seeing some linting errors from a couple of modules unrelated to this PR. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Lincoln Stein <lstein@gmail.com> Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
langchain: ConversationVectorStoreTokenBufferMemory
-Description: This PR adds ConversationVectorStoreTokenBufferMemory. It is similar in concept to ConversationSummaryBufferMemory. It maintains an in-memory buffer of messages up to a preset token limit. After the limit is hit timestamped messages are written into a vectorstore retriever rather than into a summary. The user's prompt is then used to retrieve relevant fragments of the previous conversation. By persisting the vectorstore, one can maintain memory from session to session.
-Issue: n/a
-Dependencies: none
-Twitter handle: Please no!!!
Add tests and docs: I looked to see how the unit tests were written for the other ConversationMemory modules, but couldn't find anything other than a test for successful import. I need to know whether you are using pytest.mock or another fixture to simulate the LLM and vectorstore. In addition, I would like guidance on where to place the documentation. Should it be a notebook file in docs/docs?
Lint and test: I am seeing some linting errors from a couple of modules unrelated to this PR.
If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.