Hi...I am looking to orchestrate a number of chat messages before extracting some structued output at the end of a chain of queries. I see the QueryPipeline is now deprecated in favor of workflows but I don't see a similar convenient way of passing chat history between workflow steps like in QueryPipeline.
Is there anything in workflow that makes passing chat history between steps easy?
By increasing the num_workers on the pipeline, and putting the pipeline into async mode per the instructions, the acall method is invoked.
This makes it possible to put all the await asyncio.gather() and create tasks into acall(). TaskGroups however do not seem to work due to some fault llamaIndex throws so gather is the only option.
Hi everyone. I have a "problem" with TextNode.ref_doc_id. I am not sure if this is a bug or I just don't understand how this is supposed to work?
I have situations right now where after submitting a Document to my data ingest pipeline of transformers (no storage) of let's say doc_id=123 I get TextNodes from that doc which do not all have ref_doc_id=123. I get some nodes returned with ref_doc_ids of previously ingested documents or IDs I don't recognize at all. What is the expected behavior?
I have checked I am not writing to this field anywhere in my pipeline. So, am I misunderstanding the behavior around TextNode.ref_doc_id?
