Logan M i am looking at

@Logan M i am looking at:
https://gpt-index.readthedocs.io/en/stable/examples/node_postprocessor/MetadataReplacementDemo.html#metadata-replacement-node-sentence-window

I see that you are passing the node_parser into the ServiceContext:

Plain Text

ctx = ServiceContext.from_defaults(
    llm=llm,
    embed_model=HuggingFaceEmbeddings(
        model_name="sentence-transformers/all-mpnet-base-v2"
    ),
    node_parser=node_parser,
)

Is this node_parser what's taking the documents and then "breaking them up" as opposed to calculating the embeddings for the entire thing and shoving the whole document into the index?

Find answers from the community

Logan M i am looking at