This is basically HyDE (Hypothetical Document Embeddings), no? I had tried this approach in the past, worked with limited success.
This is basically HyDE (Hypothetical Document Embeddings), no? I had tried this approach in the past, worked with limited success.
https://arxiv.org/abs/2212.10496 for others like me hearing about HyDE for the first time
We have this running in production. Can get pretty expensive and slow. We are trying to replace this with cheaper and faster methods that don’t hammer our LLM and elastic search endpoints as much.