I am untilizing Langchain with LLamaIndex, I am having issues with the agent. Firstly, when I create a chat_agent, I am getting a output-parse error. I know exactly why it is throwing the error but I have no idea why the output from the llm is in that format. Creating just the agent fixes this but when It comes to querying multiple document it is not returning the other documents. Does anyone have an idea as what is wrong?
Alright, so I have tried to get my program to answer queries regarding legal documentation but the result is not what I want. I have used fine-tuning, coupled with ToolRetrieverRouterQueryEngine and SubQueryEngine to try and answer queries about my documents. The response is seldom correct or just absolutely incorrect. Does anyone else have an idea on how to improve retrieval?
Hi guys, I ma having issues with my code. So the response from the LLM gets the correct answer (in the log) but it does understand the context and it fails to return the correct answer. PS: This setup is just for testing.
