retrieval augmented generation (RAG)
A technique where a language model's answer is grounded in external documents retrieved at query time, rather than relying solely on the model's internal knowledge.
As defined in Knowledge Graph or Vector Database… Which is Better?
Other definitions
A technique where a language model takes user input, retrieves relevant documents from a knowledge base, augments the prompt with those documents, and then generates a response based on both the query and retrieved context
Perplexity CEO: Disrupting Google Search with AI
Where it comes up · 9
- The 7 Levels of Claude Code & RAG19 claims
- Knowledge Graph or Vector Database… Which is Better?15 claims
- Feed Your OWN Documents to a Local Large Language Model!15 claims
- Is Gemini File Search Actually a Game-Changer?11 claims
- Karpathy Method for Building a Second Brain3 claims
- What are AI Agents?2 claims
- Perplexity CEO: Disrupting Google Search with AI1 claim
- Your AI Stack Isn't Ready for Claude Mythos1 claim
and 1 more
Most important claims · 10 of 68Search all claims for “retrieval augmented generation (RAG)” →
- Standard retrieval-augmented generation (RAG) scans documents on demand, retrieves relevant chunks into active memory, generates an answer, and then forgets everything once the chat window closes, meaning the knowledge remains entirely fragmented in raw state and the AI's interaction is transient.Karpathy Method for Building a Second Brain
- Context management is the third harness primitive; it decides what context matters and enters the model at a given moment. Techniques include retrieval-augmented generation (RAG), reranking of retrieved chunks, summarization at intervals, compaction when context limits are reached, and context compression. The goal is to protect the model's attention by ensuring only relevant context consumes the limited context window.Harness Engineering Masterclass: Technical Deep Dive on how to build Agentic Systems
- The key strength of RAG is its ability to efficiently handle large amounts of data by pulling only what's necessary at the moment of query, making it a more scalable approach especially when dealing with complex and evolving datasets.Feed Your OWN Documents to a Local Large Language Model!
- No one-size-fits-all approach exists for RAG system design—different use cases require different retrieval strategies and techniques.Is Gemini File Search Actually a Game-Changer?
- As you scale a knowledge base by adding topics or more text on the same topic, traditional RAG gets bottlenecked at the retrieval step because retrieving just N relevant chunks based on the query misses connections between similarities across the data and broader themes the information conveys.Knowledge Graph or Vector Database… Which is Better?
- The three primary methods for adding knowledge to existing large language models are: retraining the model with new data, using retrieval augmented generation (RAG), and uploading documents directly into the context window.Feed Your OWN Documents to a Local Large Language Model!
- Global search is something traditional RAG performs very poorly at, because it can only return specificities from unstructured text chunks; GraphRAG's embedded Community Reports allow it to answer queries about broad themes and ideas across the entire knowledge base.Knowledge Graph or Vector Database… Which is Better?
- RAG (Retrieval Augmented Generation) works like a student who doesn't have all information at their fingertips but knows where to look: when asked a question, the student quickly consults relevant sources from a library and combines that information with prior knowledge to provide a comprehensive answer.Feed Your OWN Documents to a Local Large Language Model!
- There are three primary ways to add knowledge to large language models: retraining the model, using retrieval augmented generation (RAG), and uploading documents directly into the context window.Feed Your OWN Documents to a Local Large Language Model!
- Traditional RAG benefits from simpler implementation/deployment, suits straightforward retrieval tasks, handles structured text data well, and has lower computational overhead, but loses structural information when chunking, can break related content, has limited ability to capture relationships, and struggles to reason across disparate facts—risking incomplete or fragmented answers.Knowledge Graph or Vector Database… Which is Better?