**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>
This PR fixes two mistakes in the import paths from community for the
json data aiding the cli migration to 0.2.
It is intended as a quick follow-up to
https://github.com/langchain-ai/langchain/pull/21913 .
@nicoloboschi FYI
0.2 is not a breaking release for core (but it is for langchain and
community)
To keep the core+langchain+community packages in sync at 0.2, we will
relax deps throughout the ecosystem to tolerate `langchain-core` 0.2
This auto generates partner migrations.
At the moment the migration is from community -> partner.
So one would need to run the migration script twice to go from langchain to partner.
Add script to help generate migrations.
This works well for partner packages. Migrations are generated based on run time rather than static analysis (much simpler to get the correct migrations implemented).
The script for generating migrations from langchain to community still needs work.
