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

feat: Qdrant support #1228

Merged
merged 2 commits into from
Nov 13, 2023
Merged

feat: Qdrant support #1228

merged 2 commits into from
Nov 13, 2023

Conversation

Anush008
Copy link
Contributor

This PR intends to add Qdrant as a supported vector database.

The database to be used can be configured using the new vectorstore.database property. The default values are set, ensuring no breaking change in the current behaviour.

imartinez
imartinez previously approved these changes Nov 13, 2023
Copy link
Collaborator

@imartinez imartinez left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Amazing PR. Thanks for the clarity, the configurability and the detail to documentation.

I tried it as QdrantLocal and works perfect (faster than Chromadb at around x2 in my first tests).

As a piece of unrelated feedback (definitely not to be fixed in the scope of this PR, but it will affect people adoption of qdrant), the configuration of QdrantClient is a little misleading as can be seen in the actual implementation of it:

 if location == ":memory:":
            self._client = QdrantLocal(location=location)
        else:
            if path is not None:
                self._client = QdrantLocal(location=path)
            else:
                if location is not None and url is None:
                    url = location
                self._client = QdrantRemote(

It is hard to understand how to configure it for local usage vs remote vs on memory.

Again, thanks a lot for the integration!

Co-authored-by: Iván Martínez <ivanmartit@gmail.com>
@imartinez imartinez merged commit 03d1ae6 into zylon-ai:main Nov 13, 2023
6 checks passed
@Anush008 Anush008 deleted the qdrant-support branch November 13, 2023 20:25
simonbermudez pushed a commit to simonbermudez/saimon that referenced this pull request Feb 24, 2024
* feat: Qdrant support

* Update private_gpt/components/vector_store/vector_store_component.py
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants