2 comments

[ 0.19 ms ] story [ 5.5 ms ] thread
Nice use of Qdrant for the retrieval layer.Curious how you're handling the question generation, are you chunking the study material and generating per chunk, or doing something more document-level?
Yes, I do semantic chunk to better split the text into coherent chunks. I even use Llamaparse api (by Llamaindex) to parsing any type of documents, images or imported study material, with a very high quality results. Llamaparse is great!