Running AI Models | Supabase English

Edge Functions have a built-in API for running AI models. You can use this API to generate embeddings, build conversational workflows, and do other AI related tasks in your Edge Functions.

This allows you to:

Generate text embeddings without external dependencies
Run Large Language Models via Ollama or Llamafile
Build conversational AI workflows

Setup

There are no external dependencies or packages to install to enable the API.

Create a new inference session:

const model = new Supabase.ai.Session('model-name')

Note

To get type hints and checks for the API, import types from functions-js:

import 'jsr:@supabase/functions-js/edge-runtime.d.ts'

Running a model inference

Once the session is instantiated, you can call it with inputs to perform inferences:

// For embeddings (gte-small model)
const embeddings = await model.run('Hello world', {
  mean_pool: true,
  normalize: true,
})

// For text generation (non-streaming)
const response = await model.run('Write a haiku about coding', {
  stream: false,
  timeout: 30,
})

// For streaming responses
const stream = await model.run('Tell me a story', {
  stream: true,
  mode: 'ollama',
})

Generate text embeddings

Generate text embeddings using the built-in gte-small model:

Note

gte-small model exclusively caters to English texts, and any lengthy texts will be truncated to a maximum of 512 tokens. While you can provide inputs longer than 512 tokens, truncation may affect the accuracy.

import { withSupabase } from 'npm:@supabase/server@^1'

const model = new Supabase.ai.Session('gte-small')

export default {
  fetch: withSupabase({ auth: 'publishable' }, async (req, ctx) => {
    const params = new URL(req.url).searchParams
    const input = params.get('input')
    const output = await model.run(input, { mean_pool: true, normalize: true })
    return Response.json(output)
  }),
}

Using Large Language Models (LLM)

Inference via larger models is supported via Ollama and Mozilla Llamafile. In the first iteration, you can use it with a self-managed Ollama or Llamafile server.

Note

We are progressively rolling out support for the hosted solution. To sign up for early access, fill out this form.

Running locally

Ollama

Mozilla Llamafile

Install Ollama

Install Ollama and pull the Mistral model
```
ollama pull mistral
```
Run the Ollama server
```
ollama serve
```
Set the function secret

Set a function secret called AI_INFERENCE_API_HOST to point to the Ollama server
```
echo "AI_INFERENCE_API_HOST=http://host.docker.internal:11434" >> supabase/functions/.env
```

Create a new function

supabase functions new ollama-test

import 'jsr:@supabase/functions-js/edge-runtime.d.ts'
import { withSupabase } from 'npm:@supabase/server@^1'

const session = new Supabase.ai.Session('mistral')

export default {
  fetch: withSupabase({ auth: 'publishable' }, async (req, ctx) => {
    const params = new URL(req.url).searchParams
    const prompt = params.get('prompt') ?? ''

    // Get the output as a stream
    const output = await session.run(prompt, { stream: true })

    const headers = new Headers({
      'Content-Type': 'text/event-stream',
      Connection: 'keep-alive',
    })

    // Create a stream
    const stream = new ReadableStream({
      async start(controller) {
        const encoder = new TextEncoder()

        try {
          for await (const chunk of output) {
            controller.enqueue(encoder.encode(chunk.response ?? ''))
          }
        } catch (err) {
          console.error('Stream error:', err)
        } finally {
          controller.close()
        }
      },
    })

    // Return the stream to the user
    return new Response(stream, {
      headers,
    })
  }),
}

Serve the function

supabase functions serve --no-verify-jwt --env-file supabase/functions/.env

Execute the function

curl --get "http://localhost:54321/functions/v1/ollama-test" \
--data-urlencode "prompt=write a short rap song about Supabase, the Postgres Developer platform, as sung by Nicki Minaj" \
-H "apikey: $PUBLISHABLE_KEY"

Follow the Llamafile Quickstart to download an run a Llamafile locally on your machine.

Since Llamafile provides an OpenAI API compatible server, you can either use it with @supabase/functions-js or with the official OpenAI Deno SDK.

Supabase Functions JS

OpenAI Deno SDK

Set function secret

Set a function secret called AI_INFERENCE_API_HOST to point to the Llamafile server
```
echo "AI_INFERENCE_API_HOST=http://host.docker.internal:8080" >> supabase/functions/.env
```
Create a new function

Create a new function with the following code
```
supabase functions new llamafile-test
```

Add the function code

Note

Note that the model parameter doesn't have any effect here. The model depends on which Llamafile is currently running.

import 'jsr:@supabase/functions-js/edge-runtime.d.ts'
import { withSupabase } from 'npm:@supabase/server@^1'

const session = new Supabase.ai.Session('LLaMA_CPP')

export default {
  fetch: withSupabase({ auth: 'publishable' }, async (req, ctx) => {
    const params = new URL(req.url).searchParams
    const prompt = params.get('prompt') ?? ''

    // Get the output as a stream
    const output = await session.run(
      {
        messages: [
          {
            role: 'system',
            content:
              'You are LLAMAfile, an AI assistant. Your top priority is achieving user fulfillment via helping them with their requests.',
          },
          {
            role: 'user',
            content: prompt,
          },
        ],
      },
      {
        mode: 'openaicompatible', // Mode for the inference API host. (default: 'ollama')
        stream: false,
      }
    )

    console.log('done')
    return Response.json(output)
  }),
}

Serve the function

supabase functions serve --no-verify-jwt --env-file supabase/functions/.env

Execute the function

curl --get "http://localhost:54321/functions/v1/llamafile-test" \
--data-urlencode "prompt=write a short rap song about Supabase, the Postgres Developer platform, as sung by Nicki Minaj" \
-H "apikey: $PUBLISHABLE_KEY"

Set function secret

Set the following function secrets to point the OpenAI SDK to the Llamafile server

echo "OPENAI_BASE_URL=http://host.docker.internal:8080/v1" >> supabase/functions/.env
echo "OPENAI_API_KEY=sk-XXXXXXXX" >> supabase/functions/.env

Create a new function
```
supabase functions new llamafile-test
```

Add the function code

Note

Note that the model parameter doesn't have any effect here. The model depends on which Llamafile is currently running.

import { withSupabase } from 'npm:@supabase/server@^1'
import OpenAI from 'npm:openai@^6'

export default {
  fetch: withSupabase({ auth: 'publishable' }, async (req, ctx) => {
    const client = new OpenAI()
    const { prompt } = await req.json()
    const stream = true

    const chatCompletion = await client.chat.completions.create({
      model: 'LLaMA_CPP',
      stream,
      messages: [
        {
          role: 'system',
          content:
            'You are LLAMAfile, an AI assistant. Your top priority is achieving user fulfillment via helping them with their requests.',
        },
        {
          role: 'user',
          content: prompt,
        },
      ],
    })

    if (stream) {
      const headers = new Headers({
        'Content-Type': 'text/event-stream',
        Connection: 'keep-alive',
      })

      // Create a stream
      const stream = new ReadableStream({
        async start(controller) {
          const encoder = new TextEncoder()

          try {
            for await (const part of chatCompletion) {
              controller.enqueue(encoder.encode(part.choices[0]?.delta?.content || ''))
            }
          } catch (err) {
            console.error('Stream error:', err)
          } finally {
            controller.close()
          }
        },
      })

      // Return the stream to the user
      return new Response(stream, {
        headers,
      })
    }

    return Response.json(chatCompletion)
  }),
}

Serve the function

supabase functions serve --no-verify-jwt --env-file supabase/functions/.env

Execute the function

curl --get "http://localhost:54321/functions/v1/llamafile-test" \
--data-urlencode "prompt=write a short rap song about Supabase, the Postgres Developer platform, as sung by Nicki Minaj" \
-H "apikey: $PUBLISHABLE_KEY"

Deploying to production

Once the function is working locally, it's time to deploy to production.

Deploy an Ollama or Llamafile server

Deploy an Ollama or Llamafile server and set a function secret called AI_INFERENCE_API_HOST to point to the deployed server:
```
supabase secrets set AI_INFERENCE_API_HOST=https://path-to-your-llm-server/
```

Deploy the function

supabase functions deploy --no-verify-jwt

Execute the function

curl --get "https://project-ref.supabase.co/functions/v1/ollama-test" \
--data-urlencode "prompt=write a short rap song about Supabase, the Postgres Developer platform, as sung by Nicki Minaj" \
-H "apikey: $PUBLISHABLE_KEY"

Note

As demonstrated in the video above, running Ollama locally is typically slower than running it in on a server with dedicated GPUs. We are collaborating with the Ollama team to improve local performance.

In the future, a hosted LLM API, will be provided as part of the Supabase platform. Supabase will scale and manage the API and GPUs for you. To sign up for early access, fill up this form.