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

Support AWS OpenSearch Serverless #2302

Closed
annassommer opened this issue Aug 16, 2023 · 2 comments
Closed

Support AWS OpenSearch Serverless #2302

annassommer opened this issue Aug 16, 2023 · 2 comments
Labels
auto:improvement Medium size change to existing code to handle new use-cases

Comments

@annassommer
Copy link

Hi, I have been trying to use the OpenSearch Vector Store together with AWS OpenSearch Serverless, however I have run into a couple of issues there. The refresh call when creating the Vector Store and adding vectors is not supported by AWS OpenSearch Serverless.
Screenshot 2023-08-16 at 10 51 01
It therefore throws a 404 Error when called. I spoke with someone from AWS OpenSearch Serverless, and they told me that for AOSS the refresh call was not supported, but also not needed and could simply be removed.
Querying for Data did also not work, since the body of the request is different in AOSS:
Screenshot 2023-08-16 at 10 54 44

And AOSI (AWS OpenSearch Ingestion):
Screenshot 2023-08-16 at 10 55 34

I saw that AOSS is already supported in langchain python: langchain-ai/langchain#8256
It would be a great help if you could also add AOSS support for langchain js.
Thank you in advance for any help here.

@dosubot dosubot bot added the auto:improvement Medium size change to existing code to handle new use-cases label Aug 16, 2023
@dosubot
Copy link

dosubot bot commented Aug 16, 2023

🤖

Hello,

Thank you for bringing this to our attention. It seems like you're encountering issues with AWS OpenSearch Serverless (AOSS) when using the LangChain JS framework.

As you've mentioned, the refresh call when creating the Vector Store and adding vectors is not supported by AOSS. This is due to the fact that the addDocuments and addVectors methods in the PrismaVectorStore class are currently designed to update the vector column in the database for each document, which includes a refresh call.

Regarding the issue with querying for data, it seems like the body of the request is different in AOSS and AWS OpenSearch Ingestion (AOSI). This could be due to differences in the way these services handle requests.

We appreciate your suggestion to add AOSS support for LangChain JS, especially since AOSS is already supported in LangChain Python. We understand the importance of this feature and will consider it for future updates.

In the meantime, you might want to consider modifying the addDocuments and addVectors methods in the PrismaVectorStore class to remove the refresh call and adjust the body of the request to match the AOSS requirements. Please note that this is just a workaround and might not work in all cases.

We will keep you updated on any progress regarding this issue. Thank you for your patience and understanding.

Best,
Dosu

Sources


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.

Copy link

dosubot bot commented Dec 19, 2023

Hi, @annassommer,

I'm helping the langchainjs team manage their backlog and am marking this issue as stale. From what I understand, the issue involves the lack of support for the refresh call in AWS OpenSearch Serverless, resulting in a 404 error when called, and the need for adjustments to the request body when querying for data. Dosubot from the maintainers' team has acknowledged the issue and provided some guidance on potential workarounds while indicating that the suggestion will be considered for future updates.

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 the issue will be automatically closed in 7 days.

Thank you for your understanding and contribution to langchainjs!

@dosubot dosubot bot added the stale Issue has not had recent activity or appears to be solved. Stale issues will be automatically closed label Dec 19, 2023
@dosubot dosubot bot closed this as not planned Won't fix, can't repro, duplicate, stale Dec 26, 2023
@dosubot dosubot bot removed the stale Issue has not had recent activity or appears to be solved. Stale issues will be automatically closed label Dec 26, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
auto:improvement Medium size change to existing code to handle new use-cases
Projects
None yet
Development

No branches or pull requests

1 participant