Unbundling the Graph in GraphRAG
O'Reilly Media - Ideas
NOVEMBER 19, 2024
When a question gets asked, run its text through this same embedding model, determine which chunks are nearest neighbors , then present these chunks as a ranked list to the LLM to generate a response. The various flavors of RAG borrow from recommender systems practices, such as the use of vector databases and embeddings.
Let's personalize your content