Find answers from the community

Updated 9 months ago

Hi guys, I am using the simple fusion

Hi guys, I am using the simple fusion retriever with Qdrant as vectorDB. While trying to run - nodes_with_scores = retriever.retrieve("How do I setup a chroma vector store?"), getting this error -

Attachment

Screenshot_2024-03-22_at_12.30.53_PM.png

17 comments

WWhiteFang_Jr

would you mind sharing the code?

PPujari12

https://colab.research.google.com/drive/13NJEyhKWT7xdJFAJ6nB8mq-fk22UVDKa?usp=sharing

PPujari12

its working fine when using the normal vectorstoreindex

PPujari12

but not working while using qdrant vector store

PPujari12

its even working with weaviate index

PPujari12

🥲

WWhiteFang_Jr

The error is being generated at line 690 in your code while the same code is present on line 704: https://github.com/run-llama/llama_index/blob/f5263896121721de1051ce58338a1e0ea6950ca7/llama-index-integrations/vector_stores/llama-index-vector-stores-qdrant/llama_index/vector_stores/qdrant/base.py#L704

I think maybe you dont have the latest qdrant installed

WWhiteFang_Jr

Also, you have added openAI key

PPujari12

Im following this doc - https://docs.llamaindex.ai/en/stable/examples/vector_stores/QdrantIndexDemo/

PPujari12

still getting the same error

PPujari12

can you tried running it on your side?

PPujari12

@WhiteFang_Jr @dev_advocate any update on this?

PPujari12

@Logan M any comments on this issue?

LLogan M

qdrant is pretty janky with async

Set use_async=False, in the retriever

LLogan M

qdrant requires both a sync and async client

QdrantVectorStore(client=QdrantClient(..), aclient=AsyncQdrantClient(...))

But if using :memory: , those clients do not share data

PPujari12

will it be the same case if I am using my own qdrant instance?

LLogan M

at least then you can provide both a client and aclient, and they will access the same data

Add a reply