Open jjmachan opened 1 month ago
We lack chunk quality metrics as of today. It will be good to see some chunk quality evaluation metrics.
hey @rajib76, thanks for chipping in 🙂
could you explain a bit more about how you're measuring quality here? maybe an example too if possible?
One of the hard problem today in RAG is to determine the right size of the chunk. If a chunk talks about multiple concept, it is very difficult to find the most relevant chunk for the question. I was looking for a metrics that will tell that a chunk is atomic and it talks about only one concept. The semantic chunking approach did not work as the embedding model itself has a semantic dissonance.
From SyncLinear.com | R-263