Find answers from the community

Updated 2 months ago

Hi, is it possible to use `insert_nodes`

Hi, is it possible to use insert_nodes in VectorStoreIndex async it seems async is only possible using build_index_from_nodes is that correct?
L
j
4 comments
yea good call out, not possible right now

If you are using a 3rd party vector db, you can use an ingestion pipeline to do this async
yeah, I'm using Pinecone, any tip?
I want to keep the nice text nodes abstraction
you can do something like this. If you haven't already chunked your nodes, you can also add a splitter before the embedding model in the pipeline

Plain Text
from llama_index.pipeline import IngestionPipeline

pipeline = IngestionPipeline(transformations=[OpenAIEmbedding()], vector_store=vector_store)

await pipeline.arun(nodes=nodes)
Add a reply
Sign up and join the conversation on Discord