RAG

How it is used

Pronounced like the word 'rag'. Teams build RAG pipelines over company documents so that answers stay up to date and can cite sources without retraining the model. Quality depends heavily on retrieval: chunking, embeddings and ranking.

Example sentences

1. With RAG, the chatbot can answer questions about policies we changed last week.

2. Most wrong answers came from the retrieval step, not the LLM, so we fixed that part of the RAG pipeline first.

Common collocations

• RAG pipeline
• RAG system
• build a RAG app
• RAG evaluation

Related terms

• embeddingA list of numbers (a vector) that represents a word, sentence, image or other item in such a way that items with similar meanings end up close to each other.
• vector databaseA database designed to store embeddings and quickly find the ones most similar to a query, which makes it a common part of semantic search and RAG systems.
• LLMShort for large language model: a very large neural network trained on huge amounts of text to predict the next token, which lets it answer questions, write, summarize and code.
• hallucinationA confident but false or made-up output from a generative model, such as an invented fact, quote, source or piece of code.
• fine-tuningExtra training of an already pretrained model on a smaller, task-specific dataset, so that it does better on that task or follows a particular style.

This word in other fields

The same English word can have a different meaning in another field:

• RAG · Software Engineering

More terms: Prompts and Retrieval

• prompt
• system prompt
• prompt engineering
• few-shot prompting
• chain of thought