Getting Started with Vector Search (Part 2)

In Part 1, we set up PostgreSQL with pgvector. Now, let's see how vector search actually works.

Contents

• What are Embeddings?
• Loading Sample Data
• Exploring Vector Search
• Understanding PostgreSQL Operators
• Next Steps

What are Embeddings?

An embedding is like a smart summary of content in numbers. The distance between two embeddings indicates their level of similarity. A small distance suggests that the vectors are quite similar, and a large distance indicates that they are less related.

? Book A: Web Development  (Distance: 0.2) ⬅️ Very Similar!
? Book B: JavaScript 101   (Distance: 0.3) ⬅️ Similar!
? Book C: Cooking Recipes  (Distance: 0.9) ❌ Not Similar

Loading Sample Data

Now, let's populate our database with some data. We'll use:

• Open Library API for book data
• OpenAI API to create embeddings
• pgvector to store and search them

Project Structure

pgvector-setup/             # From Part 1
  ├── compose.yml
  ├── postgres/
  │   └── schema.sql
  ├── .env                  # New: for API keys
  └── scripts/              # New: for data loading
      ├── requirements.txt
      ├── Dockerfile
      └── load_data.py

Create a Script

Let's start with a script to load data from external APIs. The full script is Here.

Setting Up Data Loading

1. Create .env:

OPENAI_API_KEY=your_openai_api_key

1. Update compose.yml to add the data loader:

services:
  # ... existing db service from Part 1

  data_loader:
    build:
      context: ./scripts
    environment:
      - DATABASE_URL=postgresql://postgres:password@db:5432/example_db
      - OPENAI_API_KEY=${OPENAI_API_KEY}
    depends_on:
      - db

1. Load the data:

docker compose up data_loader

You should see 10 programming books with their metadata.

Exploring Vector Search

Connect to your database:

docker exec -it pgvector-db psql -U postgres -d example_db

Understanding Vector Data

Let's peek at what embeddings actually look like:

-- View first 5 dimensions of an embedding
SELECT
    name,
    (embedding::text::float[])[1:5] as first_5_dimensions
FROM items
LIMIT 1;

• Each embedding has 1536 dimensions (using OpenAI's model)
• Values typically range from -1 to 1
• These numbers represent semantic meaning

Finding Similar Books

Try a simple similarity search:

-- Find 3 books similar to any book about Web
SELECT name, metadata
FROM items
ORDER BY embedding <-> (
    SELECT embedding
    FROM items
    WHERE metadata->>'title' LIKE '%Web%'
    LIMIT 1
)
LIMIT 3;

1. Find a book with "Web" in its title
2. Get that book's embedding (its mathematical representation)
3. Compare this embedding with all other books' embeddings
4. Get the 3 most similar books (smallest distances)

Understanding PostgreSQL Operators

Let's break down the operators used in vector search queries:

JSON Text Operator: ->>

Extracts text value from a JSON field.

Example:

-- If metadata = {"title": "ABC"}, it returns "ABC"
SELECT metadata->>'title' FROM items;

Vector Distance Operator: <->

Measures similarity between two vectors.

• Smaller distance = More similar
• Larger distance = Less similar

Example:

-- Find similar books
SELECT name, embedding <-> query_embedding as distance
FROM items
ORDER BY distance
LIMIT 3;

Next Steps

Up next, we'll:

• Build a FastAPI application
• Create search endpoints
• Make our vector search accessible via API

Stay tuned for Part 3: "Building a Vector Search API"! ?

Feel free to drop a comment below! ?

The above is the detailed content of Getting Started with Vector Search (Part 2). For more information, please follow other related articles on the PHP Chinese website!