Retrieval-Augmented Generation (RAG)
An AI architecture that combines information retrieval with text generation to produce answers grounded in source documents.
RAG works by first searching a knowledge base for passages relevant to a user query, then feeding those passages into a large language model so the generated answer is grounded in real data. This dramatically reduces hallucinations compared to pure generative approaches.
In document intelligence platforms, RAG enables citation-backed answers where every claim can be traced to a specific page and paragraph. The technique is particularly valuable in compliance and legal contexts where verifiability is non-negotiable.
More ai/ml Terms
Vector Embedding
A numerical representation of text as a high-dimensional vector, enabling semantic similarity comparisons between passages.
BM25
A probabilistic keyword-ranking algorithm that scores documents by term frequency and inverse document frequency.
Chunking
The process of splitting large documents into smaller, overlapping segments optimized for retrieval and embedding.
Hallucination
When an AI model generates plausible-sounding but factually incorrect or fabricated information.
Large Language Model (LLM)
A neural network trained on massive text corpora that can understand and generate human language.
Fine-Tuning
The process of further training a pre-trained model on domain-specific data to improve its performance on targeted tasks.
Analyze Documents Related to Retrieval-Augmented Generation (RAG)
Upload any document and get AI-powered analysis with verifiable citations.
Start Free