[Question]: Clarification on Behavior of VectorStoreIndex.from_vector_store with Multiple Indices

[Leonschmitt]

Question Validation

• I have searched both the documentation and discord for an answer.

Question

Hi,

I am currently working with the Qdrant Vector Store and have encountered a question regarding the behavior of the VectorStoreIndex.from_vector_store method when multiple vector store indices have been created.

In my current project, I have created several indices in the Vector Store. Now, I am in a situation where I am calling the VectorStoreIndex.from_vector_store method as follows:

VectorStoreIndex.from_vector_store(
    vector_store_component.vector_store,
    storage_context=self.storage_context,
    service_context=self.service_context,
    show_progress=True,
)

My question is: Which of the existing indices does this method access? Or does it create a new index encompassing all the existing indices? I am uncertain about the specific behavior in this scenario and could not find clear documentation on it.

Thank you in advance for your support t!

[dosubot]

🤖

Hey there @Leonschmitt! Great to see you diving deep into the intricacies of LlamaIndex again. 🕵️‍♂️

The VectorStoreIndex.from_vector_store method of the VectorStoreIndex class does not access any specific existing index or create a new index encompassing all the existing indices. Instead, it creates a new instance of VectorStoreIndex using the provided vector_store and service_context.

Here is the relevant code:

@classmethod
def from_vector_store(
    cls,
    vector_store: VectorStore,
    service_context: Optional[ServiceContext] = None,
    **kwargs: Any,
) -> "VectorStoreIndex":
    if not vector_store.stores_text:
        raise ValueError(
            "Cannot initialize from a vector store that does not store text."
        )

    storage_context = StorageContext.from_defaults(vector_store=vector_store)
    return cls(
        nodes=[], service_context=service_context, storage_context=storage_context
    )

This method first checks if the provided vector_store stores text. If it does not, it raises a ValueError. Then, it creates a StorageContext from the defaults of the vector_store. Finally, it returns a new instance of VectorStoreIndex with an empty list of nodes, the provided service_context, and the created storage_context.

You can find this code in the llama_index/indices/vector_store/base.py file in the LlamaIndex repository.

I hope this clarifies your question. If you have any further questions, feel free to ask.

Best regards,
Dosu

Sources

• llama_index/indices/vector_store/base.py
• llama_index/vector_stores/simple.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.