Hi guys i have a quick question

At a glance

Hi guys, i have a quick question:

I created an script to get data from qdrant:

Plain Text

  service_context = ServiceContext.from_defaults()
    vector_store = QdrantVectorStore(client=client, collection_name="pdfs")
    storage_context = StorageContext.from_defaults(vector_store=vector_store)
    index = VectorStoreIndex.from_documents(
        documents=[], storage_context=storage_context, service_context=service_context
    )

And then i query:

Plain Text

query_engine = index.as_query_engine(
        similarity_top_k=similarity_top_k, 
        response_mode=response_mode
    )
    response = query_engine.query(q)

But i would like some times make general question about all the context.. but looks like in the background just some similar data is fetched from qdrant... are there any way about use everything?

7 comments

LLogan M

Hmmm.... with a vector index, the only way to fetch everything is to just set the top-k extremely high

LLogan M

then, it will fetch all the nodes 😅

RRedhmam

Hmmm, do you recommend some another way?

LLogan M

mmm maybe?

The (ideal) alternative is throwing all the nodes into a list index, but this assumes you have the original documents still

RRedhmam

I have those files, do you have any article talking about?

LLogan M

Plain Text

from llama_index import ListIndex

index = ListIndex.from_documents(documents)

query_engine = index.as_query_engine(response_mode="tree_summarize")

response = query_engine.query("What are the general themes discussed in the text?")

LLogan M

ez pz

Add a reply

Find answers from the community

Hi guys i have a quick question