AI SDK + RAG chat

AI SDK + RAG chat (Postgres / pgvector) What is RAG?

RAG stands for retrieval-augmented generation. Instead of hoping the model already "knows" your facts, you retrieve snippets that match the user's question and augment the prompt with that text so generation is grounded in your data.

Why is RAG important?

Large language models only see what they were trained on (plus whatever you put in the context window). That breaks down for private or fresh information: internal docs, product details, notes you typed yesterday, or anything after a model's knowledge cutoff. RAG fixes that by fetching relevant passages at query time and passing them in as context, so answers can stay accurate and attributable to your sources.

A minimal intuition: without extra context, "What's my favorite food?" gets a generic refusal. With retrieved context ("user loves pepperoni + pineapple pizza), the model can answer correctly—because you gave it the fact, not because it remembered you.

Note: Retrieval can be web search, a file store, or anything else. Here I use semantic search over embeddings stored in Postgres. That's one solid pattern, not the only one.