Step-by-step articles on RAG & Vector Search, part of our Generative AI collection.
Showing 10 articles
An LLM only knows what was in its training data. Retrieval-augmented generation (RAG) lets it answer questions about your data, such as docs, tickets or policies, by finding the relevant passages first and putting them in the prompt. The pipeline Ingest: split...
An embedding is a list of numbers (a vector) that represents the meaning of a piece of text. Texts with similar meanings get vectors that point in similar directions, even if they share no words. from sentence_transformers import SentenceTransformer model = Se...
Chunking decides what the retriever can find. Chunks that are too small lose context; chunks that are too large mix several topics and dilute the embedding. 1. Fixed-size chunks with overlap The simplest approach: split every N tokens or characters and repeat...
You don't always need a separate vector database. The pgvector extension adds a vector type, distance operators and approximate indexes to PostgreSQL, so embeddings live next to the rest of your data. Set up the table CREATE EXTENSION IF NOT EXISTS vector; CRE...
Vector search is great at meaning ("cancel my subscription" finds "how to end your plan") but weak at exact tokens: error codes, product SKUs, function names. Keyword search is the opposite. Hybrid search runs both and merges the results. Keyword search in Pos...
Embedding search compares a query vector with chunk vectors that were computed separately. It is fast, but it misses nuance. A reranker reads the query and each candidate chunk together and scores how well they match. It is slower, so you use it on a short lis...
Users trust an answer more when they can click through to the source. Citations also make hallucinations easy to spot: an unsupported claim has nothing to point at. Option 1: Ask for chunk IDs Answer the question using only the sources below. After each senten...
Without evaluation, every change to chunking, embeddings or prompts is a guess. A small labelled dataset turns RAG tuning into engineering. 1. Build an evaluation set Collect 50-200 real questions from logs, support tickets or users. For each, record the ID(s)...
Exact nearest-neighbour search checks every vector, which gets slow past a few hundred thousand rows. Approximate nearest neighbour (ANN) indexes trade a little recall for a huge speed-up. pgvector offers two: HNSW and IVFFlat . HNSW (Hierarchical Navigable Sm...
A chunk like "Revenue grew 3% over the previous quarter" is useless on its own: which company, which quarter? Contextual retrieval , a technique published by Anthropic, fixes this by adding a short explanation of where the chunk sits in its document before emb...
