The community member is asking if there is a way to achieve the same functionality as run_multi_with_intermediates in QueryPipeline with workflows. This feature allows inspecting the results of each node after the entire query has run.
Another community member suggests two possible approaches: using the streaming functionality in the LlamaIndex documentation, or accumulating all the intermediates in the context and returning them in the StopEvent. The second community member confirms that the second approach works.
