flâneur — a map of the web's best reading

Introducing Contextual Retrieval \ Anthropic

anthropic.com · 2,310 words · saved by 1 readers

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

For an AI model to be useful in specific contexts, it often needs access to background knowledge. For example, customer support chatbots need knowledge about the specific business they're being used for, and legal analyst bots need to know about a vast array of past cases. Developers typically enhance an AI model's knowledge using Retrieval-Augmented Generation (RAG). RAG is a method that retrieves relevant information from a knowledge base and appends it to the user's prompt, significantly enhancing the model's response. The problem is that traditional RAG solutions remove context when encodi

Explore this link on the map →

related reading