Learn
Plain-language guides to AI document search.
What RAG is, how a pipeline works, how to keep it secure, how to protect personal data and how to measure quality, written for people who have to choose, build or approve these systems.
Basics
Start here.
What is retrieval-augmented generation (RAG)?
Retrieval-augmented generation (RAG) is a way of making an AI model answer from your own documents. Before the model writes a reply, a search step finds the most…
Read the guide →What is a RAG pipeline?
A RAG pipeline is the full chain of steps that turns raw documents into grounded answers: ingest, parse, chunk, embed, index, retrieve, re-rank and generate. Each…
Read the guide →What is chunking, and which strategy should you use?
Chunking is splitting a document into passages before they are indexed for search. The goal is passages small enough to match a question precisely but complete enough…
Read the guide →What is a vector database, and what are embeddings?
An embedding is a list of numbers that represents the meaning of a piece of content, and a vector database is a store built to find the embeddings closest to a query…
Read the guide →RAG vs fine-tuning: which should you use?
Use RAG when the model lacks knowledge, such as your documents or recent facts, and fine-tuning when it lacks a behaviour, such as a style or a fixed output format.…
Read the guide →Search quality
Search quality.
What is hybrid search, and why add reranking?
Hybrid search runs keyword search and meaning-based vector search side by side and merges the results, because each finds what the other misses. A reranker then…
Read the guide →How do you reduce hallucinations in RAG?
Reduce hallucinations by making sure the right evidence is retrieved, instructing the model to answer only from it, requiring citations, verifying that each claim is…
Read the guide →How do you evaluate a RAG system?
Evaluate a RAG system by building a set of real questions with known good sources and answers, then measuring retrieval (did the right passage come back, and how…
Read the guide →What is GraphRAG?
GraphRAG adds a knowledge graph, a map of the people, organisations, products and other entities in your documents and how they connect, to retrieval. It helps with…
Read the guide →How does multilingual RAG work?
Multilingual RAG maps text from many languages into one shared meaning space, so a question in English can retrieve a passage written in Hindi, Arabic or Russian. It…
Read the guide →Security and privacy
Security and privacy.
What is PII, and how do you protect it in AI systems?
PII, or personally identifiable information, is any data that can identify a person, such as a name, phone number, account number or medical record number. In an AI…
Read the guide →How do you secure a RAG system?
Secure a RAG system by treating retrieval as an authorisation decision: enforce permissions inside the search, protect sensitive data before indexing, screen…
Read the guide →What is permission-aware retrieval?
Permission-aware retrieval means the search itself enforces who may see what, so a question can only retrieve passages the asker is entitled to. It is applied before…
Read the guide →What is private or air-gapped RAG?
Private RAG keeps your documents, vectors and models inside infrastructure you control, and air-gapped RAG goes further by running with no connection to the outside…
Read the guide →Documents and data
Documents and data.
How do you parse scanned PDFs and tables for RAG?
Parsing turns files into clean, structured text before they are indexed. Scanned pages need OCR, which reads the pixels, and tables need layout analysis so that rows…
Read the guide →How does web crawling work for RAG?
Web crawling for RAG means visiting a website, collecting the useful pages and the documents linked from them, cleaning the text and indexing it with its source. The…
Read the guide →Industries
In your industry.
How is RAG used in finance?
In finance, RAG lets teams ask questions of statements, filings, policies and contracts and get answers with sources. The key requirements are exact numbers,…
Read the guide →How is RAG used in healthcare?
In healthcare, RAG helps clinicians and staff search discharge summaries, guidelines, protocols and drug information, with answers that cite their sources. Privacy,…
Read the guide →How is RAG used in legal work?
In legal work, RAG helps lawyers and legal operations search contracts, judgments, statutes and policies and get answers that point to the exact clause or passage.…
Read the guide →How is RAG used in hospitality?
In hospitality, RAG lets guests and staff get accurate answers about rooms, rates, menus, policies and procedures from the property's own documents, consistently and…
Read the guide →How is RAG used in government and the public sector?
In government and the public sector, RAG helps staff and citizens find circulars, notifications, schemes, tenders and rules, with answers that cite the document, its…
Read the guide →See it on your own documents.
The free tier is a one-time budget of 500 pages, enough to judge the quality properly. No card required.