Find answers from the community

Updated 9 months ago

Hello, when creating an VectorStoreIndex

Hello, when creating an VectorStoreIndex should use as arguments a VectorStore for the embeddings and an IndexStore to save the index?

2 comments

ffabian

This is how i persist my vector store:

Plain Text

llm = Ollama(model="mixtral",request_timeout=60.0)

service_context = ServiceContext.from_defaults(llm=llm)

PERSIST_DIR = "./Data/storage/node_storage"
if not os.path.exists(PERSIST_DIR):
    # load the documents and create the index
    documents = docs
    index = VectorStoreIndex.from_documents(documents)

    index = VectorStoreIndex(
    service_context=service_context,
)

    # store it for later
    index.storage_context.persist(persist_dir=PERSIST_DIR)

LLORKA

I don't think this approach solves my problem. I'm currently trying to use a Redis DocStore, IndexStore and VectorStore

Add a reply