Yogin

http://emqtt.io

Feature Request: Add support for custom chunking strategy for all types of document readers

1

Inspiration: 5-levels of chunking [https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb) Reader should support multiple levels of chunking strategy, including a custom chunker

pprint_run_response doesn't print if it is ResponseModel in case of stream

4

pprint_run_response print blank response if it is Iterable and from structured response. Possibility in case of a Workflow. /[phi](https://github.com/phidatahq/phidata/tree/main/phi)/[utils](https://github.com/phidatahq/phidata/tree/main/phi/utils)/pprint.py ```python else: streaming_response_content: str = "" with Live() as live_log: status...