> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/supabase/supabase/llms.txt
> Use this file to discover all available pages before exploring further.

# AI & Vectors Overview

> Build AI-powered applications with Supabase using vector embeddings, similarity search, and pgvector

Supabase provides powerful AI capabilities through pgvector, vector storage, and integration with AI frameworks. Build semantic search, recommendation systems, and RAG applications at scale.

## Key Features

<CardGroup cols={2}>
  <Card title="Vector Embeddings" icon="brain">
    Store and query high-dimensional vectors for semantic search
  </Card>

  <Card title="Similarity Search" icon="magnifying-glass">
    Find similar items using cosine, L2, or inner product distance
  </Card>

  <Card title="pgvector Extension" icon="database">
    Native PostgreSQL extension with full SQL support
  </Card>

  <Card title="AI Integrations" icon="robot">
    Works with OpenAI, Anthropic, Hugging Face, and more
  </Card>
</CardGroup>

## What are Vector Embeddings?

Vector embeddings are numerical representations of data that capture semantic meaning. Similar items have similar vectors.

```typescript theme={null}
// Text embeddings from OpenAI
const embedding = [0.123, -0.456, 0.789, ...] // 1536 dimensions

// Similar texts have similar vectors
const query = "cat chases mouse"
const similar = "kitten hunts rodent" // High similarity
const different = "weather forecast" // Low similarity
```

## Use Cases

<Accordion title="Semantic Search">
  Search by meaning, not just keywords. Find documents that match the intent of a query even if they use different words.

  ```typescript theme={null}
  const { data } = await supabase
    .rpc('match_documents', {
      query_embedding: embedding,
      match_threshold: 0.8,
      match_count: 10
    })
  ```
</Accordion>

<Accordion title="Recommendation Systems">
  Recommend products, content, or users based on similarity to past interactions or preferences.
</Accordion>

<Accordion title="RAG (Retrieval Augmented Generation)">
  Build chatbots that answer questions using your own data by retrieving relevant context before generating responses.
</Accordion>

<Accordion title="Content Moderation">
  Detect similar or duplicate content, classify images, or identify inappropriate material.
</Accordion>

## Architecture Options

Supabase offers three ways to work with vectors:

<Tabs>
  <Tab title="pgvector Extension">
    Store vectors directly in PostgreSQL tables with full SQL support.

    ```sql theme={null}
    create extension vector;

    create table documents (
      id bigint primary key,
      content text,
      embedding vector(1536)
    );
    ```

    Best for: Transactional workloads, complex queries with SQL
  </Tab>

  <Tab title="Vector Buckets">
    Specialized storage buckets optimized for high-throughput vector operations.

    Best for: Large-scale vector storage, high-performance similarity search
  </Tab>

  <Tab title="Analytics Buckets">
    Store vectors with analytical queries using SQL through DuckDB.

    Best for: Large datasets, analytical workloads
  </Tab>
</Tabs>

## Getting Started

<Steps>
  <Step title="Enable pgvector">
    Enable the vector extension in your database:

    ```sql theme={null}
    create extension vector;
    ```
  </Step>

  <Step title="Create a table">
    Create a table to store vectors:

    ```sql theme={null}
    create table documents (
      id bigserial primary key,
      content text,
      embedding vector(1536)
    );
    ```
  </Step>

  <Step title="Generate embeddings">
    Use OpenAI or another provider to generate embeddings:

    ```typescript theme={null}
    import OpenAI from 'openai'

    const openai = new OpenAI()

    const response = await openai.embeddings.create({
      model: 'text-embedding-3-small',
      input: 'Your text here'
    })

    const embedding = response.data[0].embedding
    ```
  </Step>

  <Step title="Store and search">
    Store embeddings and perform similarity search:

    ```typescript theme={null}
    // Insert
    await supabase
      .from('documents')
      .insert({ content: 'Your text', embedding })

    // Search
    const { data } = await supabase
      .rpc('match_documents', {
        query_embedding: embedding,
        match_count: 5
      })
    ```
  </Step>
</Steps>

## Next Steps

<CardGroup cols={2}>
  <Card title="Vector Embeddings" href="/ai/vector-embeddings">
    Learn how to generate and store embeddings
  </Card>

  <Card title="Similarity Search" href="/ai/similarity-search">
    Build semantic search functionality
  </Card>

  <Card title="pgvector Guide" href="/ai/pgvector">
    Deep dive into the pgvector extension
  </Card>

  <Card title="AI Examples" href="/examples/ai">
    Explore complete AI application examples
  </Card>
</CardGroup>