search

langchain-ai / langchain-aws

Build LangChain Applications on AWS
MIT License
97 stars 71 forks source link

langchain_aws:documentdb_vectorstore with async capabilities #30

Open Alonoparag opened 5 months ago

Alonoparag commented 5 months ago

Description

Adding documentdb_vectorestore from langchain_community, and adding async capabilities to it.

Dependencies

Alonoparag commented 5 months ago

@3coins Would you kindly review?

3coins commented 5 months ago

@Alonoparag Thanks for submitting this change. This is a very thorough PR, great job on adding tests. I will do a more detailed review later this week, can you fix the CI errors.

3coins commented 5 months ago

@efriis Would the integration tests here need any env setup to run successfully in the CI and during release?

efriis commented 5 months ago

@efriis Would the integration tests here need any env setup to run successfully in the CI and during release?

They definitely would! You can add any secrets to the Actions secrets in this repo, and you have to make sure they get passed through during the integration testing step in _release.yml

Happy to help if you need!

Alonoparag commented 5 months ago

@3coins Seems like the integration tests runner did not install motor. How would you usually instruct it to install? rerun poetry lock?

Alonoparag commented 4 months ago

@3coins the missing packages (motor, pymongo) are marked as extra. Can we change the CI file to install extras when the test is compiled?

3coins commented 4 months ago

@Alonoparag Trying to find the right POC in the DocumentDB team to review this, also evaluating what's the best way to handle the infrastructure creation for the integration tests. Thanks for your patience.

mohittalele commented 3 months ago

any update on this pr ?

Alonoparag commented 3 months ago

@mohittalele Still waiting for approval

Alonoparag commented 2 months ago

@3coins Any updates? The CI currently fails due to unrelated code (Bedrock). I've been using the added vectorstore myself in production since April, and I see no reason why it shouldn't be added to langchain-aws