The community member is interested in using the chat engine in LlamaIndex, but has only seen examples using indexes. They want to know if there is a solution to save the chat history of the results of NLSQL query engine or Pandasquery engine.
The comments suggest that the community member can wrap their query engine into a custom retriever class to use with a context chat engine. One community member mentions that they can plug any query engine into an agent, and another suggests that the community member can wrap the query engine into a custom retriever if they want to use it with a context chat engine.
i have seen there is a caht engine in LlamaIndex. however, in all the examples it is used with indexes. Is there any solution to save the chat history of the results of NLSQL query engine or Pandasquery engine?
I mean, it supports, but open-source is pretty bad at agentic behaviour lol
Optionally you can provide a retriever and use a context chat engine. But you'd have to wrap your query engine into a sort of custom retriever class for that to work
