Is there a way to use gpt-4o with OpenAIMultiModal - I've updated llama-index-llms-openai to the latest version but that doesn't seem to help

Is there a way to add new metadata keys to existing vectors in pinecone via llama-index?

When combining the retrieval results of the bm25 retriever and a dense retriever is there a way to scale the scores from the bm25 within 0-1 so that they can be compared with cosine similarity scores from the dense retriever?

For pinecone vector db is there another way to persist the docstore other than using .persist() without having to store it the local?
from llama_index.storage.docstore import SimpleDocumentStore docstore = SimpleDocumentStore() docstore.add_documents(documents) docstore.persist(persist_path="./docstore.json") new_docstore = SimpleDocumentStore.from_persist_path("./docstore.json")

has anyone experienced longer running times with .acomplete compared to the synchronous .complete?