Module 3 · Knowledge bases

An LLM only knows what's in its training data and what you fit in the prompt. By the end of this module you will understand why retrieval exists, how a document becomes chunks + embeddings, how the ingestion pipeline assembles them into a searchable index, and you'll build a knowledge base of your own for your agent so it can ground answers in your documents.

1Why agents need a knowledge baseA raw LLM has two hard limits: it only knows its training data (knowledge cutoff), and everything it sees has to fit — and be paid for — in the context… 6 min

2Chunking: splitting documents into bitesThe unit of retrieval isn't the document — it's the chunk. You split documents into small pieces, embed each one, and retrieve only the pieces that match… 7 min

3Embeddings and similarityAn embedding turns a piece of text into a vector — a list of numbers — such that similar meanings produce similar vectors. Cosine similarity measures how… 7 min

4Building the index: the ingestion pipelineIngestion is the one-time pipeline that turns a document into a searchable knowledge base: extract text → chunk → embed each chunk → store the vectors in… 6 min

Build this module in AI Fluens Studio