Skip to content
Aurabase Logo
aurabase

RAG & Vector Search Guide

Build semantic search and a Retrieval-Augmented Generation (RAG) pipeline with pgvector and the Aurabase AI Gateway.

Tutorial12 min readLevel advancedRevised on Aug 19, 2026

RAG on Aurabase in 3 steps#

RAG allows your AI models to respond accurately on your own private data without retraining:

  • Vectorization: Your textual documents are transformed into digital vectors using aura.ai.embed().
  • Storage & Indexing: Vectors are stored in PostgreSQL with the native extension pgvector.
  • Augmentation & Answer: The question is compared to the stored vectors, and the relevant snippets are provided to the LLM via aura.ai.chat().

Full RAG pipeline code#

src/lib/index-doc.tstypescript
import { aura } from '@/lib/aurabase'

export async function indexDocument(content: string, metadata: Record<string, any>) {
  // Calculation of vector embedding via the AI Gateway Aurabase
  const { vectors } = await aura.ai.embed({
    provider: 'openai',
    model: 'text-embedding-3-small',
    input: [content],
  })

  // Saving in PostgreSQL table
  const { data, error } = await aura.from('documents').insert({
    content,
    metadata,
    embedding: vectors[0],
  })
  return { data, error }
}

HNSW indexing for sub-10ms queries#

For databases containing hundreds of thousands of vectors, HNSW (Hierarchical Navigable Small World) indexing provides significantly better search performance than ivfflat:

HNSW Index (Recommended)

Zero pre-training time, recall > 99% and constant latency even with continuous insertions of new documents.

Cosine Distance (<=>)

Use the <=> operator to calculate the normalized cosine distance between the embedding vectors.

Semantic cache and token savings#

Aurabase's AI Gateway integrates an automatic semantic cache: if two users ask a similar question (cosine similarity greater than 0.95), the answer is served from the in-memory cache in less than 2 ms, saving 100% of the LLM call cost.

To go further#