Find answers from the community

Updated 3 months ago

llama_index/docs/examples/query_engine/m...

Hi, I am trying to run this notebook:

https://github.com/run-llama/llama_index/blob/main/docs/examples/query_engine/multi_doc_auto_retrieval/multi_doc_auto_retrieval.ipynb

It gives me a TypeError: unsupported operand type(s) for *: 'NoneType' and 'float' when I tried to replace the Weaviate Vector Store with the local Vector Store.

What I did is replacing:
Plain Text
vector_store = WeaviateVectorStore(
    weaviate_client=client, index_name=class_name
)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

vector_store = WeaviateVectorStore(
    weaviate_client=client, index_name=doc_class_name
)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

doc_index = VectorStoreIndex.from_documents(
    docs, storage_context=storage_context
)


With the following:

Plain Text
index = VectorStoreIndex.from_documents(new_docs)

doc_index = VectorStoreIndex.from_documents(docs)
n
L
4 comments
It gives me a TypeError: unsupported operand type(s) for *: 'NoneType' and 'float'.

The cell that produces the error is:
Plain Text
nodes = retriever.retrieve("Tell me about some issues on 12/11")
Only weaviate supports querying with an empty query_str actually
The default vector db probably needs to be updated to support that type of query, somehow
I see. thanks Logan
Add a reply
Sign up and join the conversation on Discord