Find answers from the community

Updated 3 months ago

Heyo, I have a question, it is possible

Heyo, I have a question, it is possible to create a chromadb vectorstore when using llama parse ?
I'm using llama parse to read pdfs, from I've seen from the notebooks in documentation, they usually create "nodes" from the parsed documents by llama parse.
what i used before is using the simple directory reader and and i use VectorStoreIndex from documents having created the vectorstore with a chroma collection, just basic stuff

6 comments

WWhiteFang_Jr

Yes, llamaparse is to extract content from your documents

WWhiteFang_Jr

You can use any vector store to save the embeddings

gghxsted.

so there's no need to creates the nodes ?

WWhiteFang_Jr

It depends on your case, If you want to use any node parser of your choice like MArkdownNodeParser then you can else simply pass the documents to your index creation step.

Plain Text

# Llamaparse purpose is to generate documents only.
documents = get from LlamaParse 

nodes = If you want to use any node parser.

index = VectorStoreIndex.from_documents(documents) # Incase you dont want to use any node parser. 

index = VectorStoreIndex(nodes) # if you generate ndoes.

gghxsted.

i'm sorry but nodes are a new concept for me, do you have any resources I can use, just to understand their usage etc

WWhiteFang_Jr

Sure, here you go: https://docs.llamaindex.ai/en/stable/module_guides/loading/documents_and_nodes/root.html#documents-nodes

Add a reply