-
Notifications
You must be signed in to change notification settings - Fork 175
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
Add support for Qdrant VectorDB #812
Add support for Qdrant VectorDB #812
Conversation
Thanks for the PR! Some of the team is traveling right now but we'll try to take a look next week once tests are passing. |
Codecov ReportAttention: Patch coverage is
📢 Thoughts on this report? Let us know! |
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.
Thank you @hkhajgiwale.
LGTM with the CI green.
@collindutter @vasinov Can you please approve this MR? |
Thanks @Anush008 for investing time and providing the valuable feedback |
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.
overall looks great, there's some changes needed for the example in the docs. all code snippets in the docs run as integration tests on a remote runner. the test needs to be updated to support that.
@vachillo @vasinov @collindutter Incorporated all the said changes. Kindly review |
Fixed |
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! one last request: please add
- `QdrantVectorStoreDriver` to integrate with Qdrant vector databases.
under Added
in the CHANGELOG
Added in the changelog. |
Description
This pull request introduces a new feature that integrates Griptape with Qdrant VectorDB, enhancing the capabilities of Griptape for handling large-scale vector data.
Problem Statement
Managing and querying large-scale vector data efficiently has been a challenge. The current solutions lack seamless integration for ingesting, processing, and indexing vector embeddings, leading to inefficiencies in AI and machine learning workflows.
Solution
The integration between Griptape and Qdrant VectorDB provides a scalable and efficient solution for ingesting, processing, and indexing vector embeddings. Leveraging Griptape's powerful data pipeline capabilities and Qdrant's advanced vector search technology, this integration supports a wide range of AI and machine learning applications.
Key Features
Alternatives Considered
Additional Context
This integration has been well tested with the following code, ensuring reliable performance and accuracy:
Output
Please refer to attached screenshot regarding the data insertion into Qdrant
Special Note
Utilization of batches is still in progress, (the code is already present in the MR) and we are actively working on it to further enhance the efficiency of the integration.
📚 Documentation preview 📚: https://griptape--812.org.readthedocs.build//812/