Refreshing the Index Results in a Python

SSayan

Refreshing the Index Results in a Python Error

I am adhering to the instructions provided here: https://docs.llamaindex.ai/en/latest/module_guides/indexing/document_management.html#refresh

Plain Text

index = VectorStoreIndex.from_vector_store(vector_store=vector_store, service_context=service_context)
refreshed_docs = index.refresh_ref_docs(
    documents,
    update_kwargs={"delete_kwargs": {
        "delete_from_docstore": True
    }}
)

Error:

ERROR - Unexpected err=TypeError("delete_ref_doc() got multiple values for keyword argument 'delete_from_docstore'"), type(err)=<class 'TypeError'>

I am using the latest version of LlamaIndex. Can anyone please help?

7 comments

mmaybe goats dont exist

can i see where you are defining your documents and index

SSayan

sure

Plain Text

loader = JsonDataReader()
        documents = loader.load_data(source_data)

That's documents.

Plain Text

index = VectorStoreIndex.from_vector_store(vector_store=vector_store, service_context=service_context)

I am using Qdrant as the vector store

LLogan M

No need to pass the update kwargs it seems 🤔

LLogan M

Attachment

SSayan

@Logan M got it, thanks! So looks like it'll do a delete_from_docstore even without the kwargs, right?

LLogan M

Seems like it!

LLogan M

That would be the only way to do a proper upsert

Add a reply

Find answers from the community

Refreshing the Index Results in a Python