Csv

Question

Hi all , iam used pagedcsvreader along with chromadb and when iam querying with similarity_top_k as 10 but none of the documents are relevant to query. Although iam directly specifying important keywords in query. What can I do to improve rag with CSV data

Logan M · Answer

You probably don't want to be doing top k with most csv data

Logan M · Answer

Probably better to be doing text2sql or something like that

Logan M · Answer

Unless your csv is something textual, like QA pairs

Tech explorer · Answer

Tried doing text2sql by loading data into sqlite, but it's not able to answer based on previous question/ previous output . Also even for a hello it's trying to execute SQL query . Is there any tutorial to create chatbot with CSV , SQL data where history is also taken care or we have memory buffer

Logan M · Answer

probably you want an agent with text2sql as a tool

Tech explorer · Answer

Tried to build agent as per documentation many times it keeps executing never ending loop without response.

Logan M · Answer

what llm are you using? what kind of agent?

Logan M · Answer

how did you setup the tool?

Tech explorer · Answer

https://docs.llamaindex.ai/en/stable/examples/agent/agent_runner/query_pipeline_agent/

Tech explorer · Answer

I followed this article and sometimes agent is running in loop

Find answers from the community

Csv