Qdrant: Retrieve an existing collection

[miary]

All examples showing integration of Qdrant with haystack show how to create a new Qdrant index/collection and use that as a DocumentStore.

However, there does not seem to be a way to use an already-created Qdrant collection and use that within a Haystack project.

Please let me know if such a method exists.

[anakin87]

Sorry for the late response.

Since we want to provide a consistent user experience with different databases, in general our integrations are a bit opinionated.

To be used in Haystack, the points of your Qdrant collection must be convertible by this method

In short, apart from the vector (which is mapped to embedding), the attributes should reflect those of the Document dataclass.

If your collection is different, you might consider creating a migration script.

[anakin87]

An example of a migration script (in this case to add a sparse vector field):
https://github.com/deepset-ai/haystack-core-integrations/blob/0cdda5ce6c5e92ef77dcfea046bc7af0bfb47aff/integrations/qdrant/src/haystack_integrations/document_stores/qdrant/migrate_to_sparse.py