[Bug]: Qdrant named vectors are not working

[wodka]

Bug Description

When named vectors are used, it must be defined where to do the distance search. If no vector name is passed, then a error is shown:

Wrong input: Default vector params are not specified in config

Version

0.6.31

Qdrant as of version 0.10.0 has named vectors:

Available as of v0.10.0 If the collection was created with multiple vectors, each vector data can be provided using the vector’s name:

Steps to Reproduce

1. Create a collection in qdrant
2. Add an entry with a vector name
3. use https://github.com/jerryjliu/llama_index/blob/48f5460b24e43ae1fe4540ce2fefa37ea6cc1c76/docs/examples/vector_stores/QdrantIndexDemo.ipynb to try to access the vector name

Relevant Logs/Tracbacks

No response

[logan-markewich]

Our vector store integrations are really mostly intended to be used with vector dbs created by llama index (I.e llama index was the one to insert vectors)

Working on improving this in the future, but for now it makes sense that this doesn't work

We have vector db readers as well, but those are less useful

[dosubot[bot]]

Hi, @wodka! I'm Dosu, and I'm here to help the LlamaIndex team manage their backlog. I wanted to let you know that we are marking this issue as stale.

From what I understand, the bug you reported in Qdrant is related to an error that occurs when using named vectors without passing a vector name. This bug was present in version 0.6.31. Logan-markewich commented on the issue, mentioning that the vector store integrations are mostly intended to be used with vector dbs created by LlamaIndex. They are aware of this bug and are actively working on improving it in the future.

Before we close this issue, we would like to confirm if it is still relevant to the latest version of the LlamaIndex repository. If it is, please let us know by commenting on this issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days.

Thank you for your contribution to the LlamaIndex project!

[wodka]

it would still be relevant, but makes sense that it is not a priority for llamaindex

[dosubot[bot]]

@logan-markewich Could you please help @wodka with the issue they reported? They mentioned that the bug is still relevant, but understand that it may not be a priority for LlamaIndex. Thank you!

[dosubot[bot]]

Hi, @wodka,

I'm helping the LlamaIndex team manage their backlog and am marking this issue as stale. From what I understand, you reported an error related to using named vectors in Qdrant without specifying a vector name for distance search. Logan-markewich mentioned that the vector store integrations are primarily intended for use with vector dbs created by LlamaIndex and they are working on improving this in the future. You confirmed that the issue is still relevant but understand that it may not be a priority for LlamaIndex.

Could you please confirm if the issue is still relevant to the latest version of the LlamaIndex repository? If it is, please let the LlamaIndex team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days.

Thank you for your understanding and cooperation.

I (Dosu)

[wodka]

it would still be relevant, but makes sense that it is not a priority for llamaindex

[dosubot[bot]]

Hi, @wodka,

I'm helping the LlamaIndex team manage their backlog and am marking this issue as stale. From what I understand, the issue was reported by you, highlighting a bug in Qdrant version 0.6.31. Logan-markewich commented that the vector store integrations are primarily intended for use with vector dbs created by LlamaIndex and they are working on improving this in the future. You confirmed that the issue is still relevant but understand that it may not be a priority for LlamaIndex.

Could you please confirm if the issue is still relevant to the latest version of the LlamaIndex repository? If it is, please let the LlamaIndex 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 cooperation. If you have any further questions or concerns, feel free to reach out to me or the LlamaIndex team.

I

[wodka]

it would still be relevant, but makes sense that it is not a priority for llamaindex

... bots are becoming annoying - also a bit schizophrenic?