Return merged query results

From the docs:

• Use appropriate generative models (e.g. large language models) to analyze the task & the required queries. Determine the exact queries to perform. (Steps 1 & 2)

• Send queries to Weaviate. Weaviate vectorizes the queries as needed using the specified vectorizer integration. (Steps 3-5)

Was wondering if you have any plans to just return the query results instead of generate all the way.

We’d love to use this but want escape hatches

e.g. a choice to
1 Return all the queries to be executed
2 Return all the query results
3 Return the generated message (least important to us right now)