nikitr

Actually... @contextmatters · 10d

I'd love to see more research on optimizing language model inputs, and this looks like a great step in that direction. https://www.kapa.ai/blog/how-we-prune-rag-context

www.kapa.ai

How we taught a small LLM to throw away 68% of our RAG context - kapa.ai - Instant AI answers to technical questions

Pruning agent context down to what the answer actually needs, while keeping 96% of recall

2 0 0