supabase/apps/docs/content/guides/ai.mdx

---
id: 'ai'
title: 'AI & Vectors'
description: 'The best vector database is the database you already have.'
subtitle: 'The best vector database is the database you already have.'
hideToc: true
---

Supabase provides an open source toolkit for developing AI applications using Postgres and pgvector. Use the Supabase client libraries to store, index, and query your vector embeddings at scale.

The toolkit includes:

- A [vector store](/docs/guides/ai/vector-columns) and embeddings support using Postgres and pgvector.
- A [Python client](/docs/guides/ai/vecs-python-client) for managing unstructured embeddings.
- An [embedding generation](/docs/guides/ai/quickstarts/generate-text-embeddings) process using open source models directly in Edge Functions.
- [Database migrations](/docs/guides/ai/examples/headless-vector-search#prepare-your-database) for managing structured embeddings.
- Integrations with all popular AI providers, such as [OpenAI](/docs/guides/ai/examples/openai), [Hugging Face](/docs/guides/ai/hugging-face), [LangChain](/docs/guides/ai/langchain), and more.

## Search

You can use Supabase to build different types of search features for your app, including:

- [Semantic search](/docs/guides/ai/semantic-search): search by meaning rather than exact keywords
- [Keyword search](/docs/guides/ai/keyword-search): search by words or phrases
- [Hybrid search](/docs/guides/ai/hybrid-search): combine semantic search with keyword search

## Examples

Check out all of the AI [templates and examples](https://github.com/supabase/supabase/tree/master/examples/ai) in our GitHub repository.

{/* <!-- vale off --> */}

<div className="grid md:grid-cols-12 gap-4 not-prose">
  <div className="col-span-4">
    <Link href="/guides/ai/examples/headless-vector-search" passHref>
      <GlassPanel
        icon={'/docs/img/icons/github-icon'}
        hasLightIcon={true}
        title="Headless Vector Search"
      >
        A toolkit to perform vector similarity search on your knowledge base embeddings.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="/guides/ai/examples/image-search-openai-clip" passHref>
      <GlassPanel
        icon={'/docs/img/icons/github-icon'}
        hasLightIcon={true}
        title="Image Search with OpenAI CLIP"
      >
        Implement image search with the OpenAI CLIP Model and Supabase Vector.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="/guides/ai/examples/huggingface-image-captioning" passHref>
      <GlassPanel
        icon={'/docs/img/icons/github-icon'}
        hasLightIcon={true}
        title="Hugging Face inference"
      >
        Generate image captions using Hugging Face.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="/guides/ai/examples/openai" passHref>
      <GlassPanel
        icon={'/docs/img/icons/github-icon'}
        hasLightIcon={true}
        title="OpenAI completions"
      >
        Generate GPT text completions using OpenAI in Edge Functions.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="/guides/ai/examples/building-chatgpt-plugins" passHref>
      <GlassPanel
        icon={'/docs/img/icons/github-icon'}
        hasLightIcon={true}
        title="Building ChatGPT Plugins"
      >
        Use Supabase as a Retrieval Store for your ChatGPT plugin.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="/guides/ai/examples/nextjs-vector-search" passHref>
      <GlassPanel
        icon={'/docs/img/icons/github-icon'}
        hasLightIcon={true}
        title="Vector search with Next.js and OpenAI"
      >
        Learn how to build a ChatGPT-style doc search powered by Next.js, OpenAI, and Supabase.
      </GlassPanel>
    </Link>
  </div>
</div>

{/* <!-- vale on --> */}

## Integrations

{/* <!-- vale off --> */}

<div className="grid md:grid-cols-12 gap-4 not-prose">
  <div className="col-span-4">
    <Link href="/guides/ai/examples/building-chatgpt-plugins" passHref>
      <GlassPanel title="OpenAI">
        OpenAI is an AI research and deployment company. Supabase provides a way to use OpenAI in
        your applications.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="/guides/ai/integrations/amazon-bedrock" passHref>
      <GlassPanel title="Amazon Bedrock">
        A fully managed service that offers a choice of high-performing foundation models from
        leading AI companies.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="/guides/ai/hugging-face" passHref>
      <GlassPanel title="Hugging Face">
        Hugging Face is an open-source provider of NLP technologies. Supabase provides a way to use
        Hugging Face's models in your applications.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="/guides/ai/langchain" passHref>
      <GlassPanel title="LangChain">
        LangChain is a language-agnostic, open-source, and self-hosted API for text translation,
        summarization, and sentiment analysis.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="/guides/ai/integrations/llamaindex" passHref>
      <GlassPanel title="LlamaIndex">
        LlamaIndex is a data framework for your LLM applications.
      </GlassPanel>
    </Link>
  </div>
</div>

{/* <!-- vale on --> */}

## Case studies

{/* <!-- vale off --> */}

<div className="grid md:grid-cols-12 gap-4 not-prose">
  <div className="col-span-4">
    <Link href="https://supabase.com/customers/berriai" passHref>
      <GlassPanel title="Berri AI Boosts Productivity by Migrating from AWS RDS to Supabase with pgvector">
        Learn how Berri AI overcame challenges with self-hosting their vector database on AWS RDS
        and successfully migrated to Supabase.
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="https://supabase.com/customers/firecrawl" passHref>
      <GlassPanel title="Firecrawl switches from Pinecone to Supabase for Postgres vector embeddings">
        How Firecrawl boosts efficiency and accuracy of chat powered search for documentation using
        Supabase with pgvector
      </GlassPanel>
    </Link>
  </div>
  <div className="col-span-4">
    <Link href="https://supabase.com/customers/markprompt" passHref>
      <GlassPanel title="Markprompt: GDPR-Compliant AI Chatbots for Docs and Websites">
        AI-powered chatbot platform, Markprompt, empowers developers to deliver efficient and
        GDPR-compliant prompt experiences on top of their content, by leveraging Supabase's secure
        and privacy-focused database and authentication solutions
      </GlassPanel>
    </Link>
  </div>
</div>

{/* <!-- vale on --> */}