With arrival of the new workflows architecture it opens the possibility of making the powerful COA chain of abstraction approach even better by making it execute in steps rather than one shot, it can then revise the execution plan as data comes in and even progressively refine an answer until a validator triggers a stop event. @Logan M have you thought about making a notebook on how to implement a COA rag pipeline with the new workflows?
Yea definitely i think we can do some cool stuff with agents and workflows. Haven't looked into COA myself just yet (if you happen to give it a try, it would make a great demo/example!)
I have folder data including a file llama2.pdf, i have try to degrade from 0.11.1 to 0.10.68 and it work fine. Perhaps there are something bug in the latest version?
If you are moving to 0.11 I would suggest upgrading all the libraries that you have. There was a pydantic v2 upgrade which requires all the libraries to be updated
Same code work fine in llama-index and llama-index-core with version "0.10.68" but occor error in "0.11.1", there must something wrong in latest version. Maybe i can wait several days to check if anyone else have the same issue.🥹