Vector Search & Pinecone Setup

## Introduction to Vector Search

Vector search finds similar items by comparing high-dimensional embeddings rather than matching keywords. It powers semantic search, recommendations, and RAG systems.

### How Vector Search Works

1. Embed — Convert text/images into numerical vectors using an embedding model
2. Index — Store vectors in a specialized database optimized for similarity search
3. Query — Convert the search query into a vector and find nearest neighbors
4. Return — Retrieve the most similar items with similarity scores

### Pinecone Setup

```typescript import { Pinecone } from "@pinecone-database/pinecone";

const pc = new Pinecone({ apiKey: process.env.PINECONE_API_KEY });

// Create an index await pc.createIndex({ name: "my-index", dimension: 1536, // Must match embedding model dimension metric: "cosine", spec: { serverless: { cloud: "aws", region: "us-east-1" } }, });

const index = pc.index("my-index"); ```

### Choosing Dimensions & Metrics

| Embedding Model | Dimensions | Best Metric | |----------------|-----------|------------| | OpenAI text-embedding-3-small | 1536 | cosine | | OpenAI text-embedding-3-large | 3072 | cosine | | Cohere embed-v3 | 1024 | cosine | | Sentence Transformers | 384-768 | cosine |

### Index Types

• Serverless: Auto-scales, pay per usage — best for most use cases
• Pod-based: Dedicated resources, predictable performance — for high-throughput