Glossary
What is retrieval-augmented generation?
Fetching relevant documents and adding them to the prompt before the model answers.
RAG systems index a corpus, retrieve the passages most similar to the question, and place them in the context window alongside the question.
The retrieval step is where most RAG quality lives. Good answers over bad retrieval are not possible.
Sending your open tabs is manual retrieval: you already decided which documents matter, so the selection step is as accurate as it gets.
In practice
A support bot that searches its docs before answering is doing automatically what you do when you paste the docs page yourself.
Common questions
- What does retrieval-augmented generation mean in one sentence?
- Fetching relevant documents and adding them to the prompt before the model answers.
- Why does retrieval-augmented generation matter when you use Claude or ChatGPT?
- Sending your open tabs is manual retrieval: you already decided which documents matter, so the selection step is as accurate as it gets.
- Can you give an example of retrieval-augmented generation?
- A support bot that searches its docs before answering is doing automatically what you do when you paste the docs page yourself.
Related terms
- GroundingTying an AI answer to specific source material you supplied.
- Context windowThe amount of text an AI assistant can hold in mind during a single conversation.
- Readable content extractionPulling the main article text out of a page and discarding the furniture.
- Glossary indexEvery AI context term, defined in plain language.
Get LocalBridge
One click sends your open tabs into Claude or ChatGPT. One-time licence, no subscription.
See how it works