Often, when building digital assistants and generative AI copilots, you need to implement a conversational flow that gathers information from the user in a prescribed manner and then take some culminating action when all the info has been gathered. When the amount of information that needs to be gathered is more than just a few things, you need to create a guided conversation where the G-AI solution implements sort of a “call script” that expertly guides the user by prompting them for the information that is required. This prescribed back and forth becomes a multi-turn conversational dialog between the user and G-AI assistant.

I am following Krish NAik’s tutorial on Langchain and agents. I’m trying to build an agent executer using open_ai_tools_agent. My tools include a Wikipedia tool and an Arxiv tool. However, whenever I query, I get an error:

I have a master_agent which is returning an agentexecutor, and using two tools, eda (llamaindex_query_engine) and another one, I want to pass the dataframe the user is uploading to the streamlit app using fileuploader, pass to the eda agent. Can anyone help?