-
Notifications
You must be signed in to change notification settings - Fork 14
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
Use orchestration lib #22
Conversation
92a4c52
to
dedc31b
Compare
b83b811
to
e41dca1
Compare
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.
Pretty sure the retrieval strategy change is a breaking change. If there's a way to do it in a nonbreaking way, that would be best!
63c7756
to
a7beb68
Compare
a7beb68
to
46e1c12
Compare
libs/elasticsearch/tests/integration_tests/test_vectorstores.py
Outdated
Show resolved
Hide resolved
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 great! Im excited for this change :)
1a14907
to
142bfe9
Compare
Update documentation with the [new names for retrieval strategies](langchain-ai/langchain-elastic#22) --------- Co-authored-by: Erick Friis <[email protected]>
Update documentation with the [new names for retrieval strategies](langchain-ai/langchain-elastic#22) --------- Co-authored-by: Erick Friis <[email protected]>
We moved much of the VectorStore logic to the Elasticsearch client library (elastic/elasticsearch-py#2528, see module) in order to centralize the development, ensure all GenAI library integrations work the same and offer users direct access to this abstraction in the future.
This PR integrates the new module into LangChain and converts most tests to unit tests that just check if the backend vector store is called correctly (the integration tests now live in elasticsearch-py).
The LangChain classes keep their existing interfaces.