Hi guys, do you know if it'd be possible to use the option response_format from the openai client(https://github.com/openai/openai-python/blob/main/src/openai/resources/chat/completions.py#L69) in llama_index?

For what i understood in the code there's no kwargs being sent to the client but i'm not sure if there's some other way around

Hi everyone, just wondering, is it possible to pipeline query execution on different indices?

The use case would be to first send a query and then use the results to send it as input to query another index, like a pipelining of queries and indices.