Unexpected behaviour when no match is found using the llamacloudindex

Question

I'm using the LlamaCloudIndex with similarity_top_k=3, I noticed that when no match is found the source_nodes contain one chunk only and that chunk is the whole document. Is that expected behaviour? I'm surprised as I thought there would always be source nodes as we're looking at top similarities, i.e. it would return the most similar nodes even though they might not be similar at all.

WhiteFang_Jr · Answer

Have you added any postprocessing step like Similiarity Postprocessing?

kristian · Answer

no

kristian · Answer

I only have:index = LlamaCloudIndex(...)query_engine = index.as_query_engine(...)query_engine.aquery(...)

WhiteFang_Jr · Answer

Hey @Logan M , could you please take a look into this🙏

Logan M · Answer

I'm pretty sure by defult, the llama cloud retriever uses "auto" mode, where it automatically decides to do either top-k based chunk retrieval, or retrieving entire files based on metadata

Find answers from the community

Unexpected behaviour when no match is found using the llamacloudindex