Find answers from the community

Updated 3 months ago

Hi guys, I am trying Qdrantvector store

Hi guys, I am trying Qdrantvector store but getting timed out error while running the below code -
client = QdrantClient(url="http://xxxxxxxxxxxxxxxxxxxxx")

create our vector store with hybrid indexing enabled

batch_size controls how many nodes are encoded with sparse vectors at once

vector_store = QdrantVectorStore(
"llama2_paper", client=client, enable_hybrid=True, batch_size=20
)

storage_context = StorageContext.from_defaults(vector_store=vector_store)
Settings.chunk_size = 512

index = VectorStoreIndex.from_documents(
documents,
storage_context=storage_context,
)
how to solve this?
L
s
10 comments
Maybe lower the batch size? πŸ€·β€β™‚οΈ Hard to say without the traceback tho
Shooting in the dark here but can you validate if it is it a connection issue. Check if you can make raw API calls.
isn't it better to do it over larger batches as each insertion triggers reindexing?

EDIT: it's not always anymore.
ideally you should disable indexing when doing large uploads.
and re-enable after.
I figured larger batches might be causing the timeout
You can disable indexing on qdrant?
Still would result in lower latency when you re-enable index. But doubt it would fully knock out.
If it was a self managed node I would watch for the CPU & RAM usage. Especially the RAM usage.
Add a reply
Sign up and join the conversation on Discord