Update REST rag_chat endpoint to include the stuff summarisation already in streaming endpoint

[andy-symonds]

Context

We want both the streaming endpoint point and REST endpoint to have the same functionality.

stuff_summarisation has recently been added to main using Langchain Expression Language (LCEL) runnables. This work adds the same stuff_summarisation functionality, using the same LCEL runnables to the REST rag_chat endpoint.

Changes proposed in this pull request

Updated REST rag_chat endpoint and added basic test to check the type of response when sent down the stuff_summarisation route.

Guidance to review

Relevant links

Things to check

• I have added any new ENV vars in all deployed environments
• I have tested any code added or changed
• I have run integration tests

[wpfl-dbt]

It shouldn’t be that complicated but that’s not on you, it’s that we need to refactor the in-between bit so it return a more consistent object to turn into a response.

For the scope of the PR, I think this does the job nicely.