Your AI SaaS business, ready by this week!
Try demoRAG (retrieval-augmented generation) is a technique where relevant passages are first retrieved from a knowledge base and then given to an AI model with the question, so the answer is grounded in that content.
Documents are split into chunks and turned into embeddings, numeric vectors that capture meaning. They are stored in a vector database.
When a user asks a question, the question is embedded too, the closest chunks are found, and those chunks are added to the prompt. The model answers from them rather than only from its training data.
RAG is how most "chat with your documents" and customer-support chatbots work, because it keeps answers current without retraining a model.
Custom assistants and website chatbots in Aikeedo use RAG. Users add files and links as a knowledge base, and embeddings are stored in the built-in vector store or in Qdrant through a plugin.
Discover more terms connected to this one
Embeddings are lists of numbers that represent the meaning of a piece of text, so that texts with similar meaning end up close together and can be found by similarity search.
A vector database stores embeddings and finds the ones closest to a query vector quickly, which makes it the search engine behind RAG and semantic search.
Chunking is splitting documents into smaller passages before embedding them, so retrieval can return just the relevant part rather than a whole file.