Generate Embeddings

<StepHikeCompact.Details title="Set up Supabase locally">

  Make sure you have the latest version of the [Supabase CLI installed](/docs/guides/cli/getting-started).

  Initialize Supabase in the root directory of your app and start your local stack.

</StepHikeCompact.Details>

<StepHikeCompact.Code>

  ```shell
  supabase init
  supabase start
  ```

</StepHikeCompact.Code>

<StepHikeCompact.Details title="Create Edge Function">

  Create an Edge Function that we will use to generate embeddings. We'll call this `embed` (you can name this anything you like).

  This will create a new TypeScript file called `index.ts` under `./supabase/functions/embed`.

</StepHikeCompact.Details>

<StepHikeCompact.Code>

  ```shell
  supabase functions new embed
  ```

</StepHikeCompact.Code>

<StepHikeCompact.Details title="Setup Inference Session" fullWidth>

  Let's create a new inference session to be used in the lifetime of this function. Multiple requests can use the same inference session.

  Currently, only the `gte-small` (https://huggingface.co/Supabase/gte-small) text embedding model is supported in Supabase's Edge Runtime.

</StepHikeCompact.Details>

<StepHikeCompact.Code>
  ```ts ./supabase/functions/embed/index.ts
  const session = new Supabase.ai.Session('gte-small');
  ```
</StepHikeCompact.Code>

<StepHikeCompact.Details title="Implement request handler">

  Modify our request handler to accept an `input` string from the POST request JSON body.

  Then generate the embedding by calling `session.run(input)`.

</StepHikeCompact.Details>

<StepHikeCompact.Code>

  ```ts ./supabase/functions/embed/index.ts
  Deno.serve(async (req) => {
    // Extract input string from JSON body
    const { input } = await req.json();

    // Generate the embedding from the user input
    const embedding = await session.run(input, {
      mean_pool: true,
      normalize: true,
    });

    // Return the embedding
    return new Response(
      JSON.stringify({ embedding }),
      { headers: { 'Content-Type': 'application/json' } }
    );
  });
  ```

</StepHikeCompact.Code>

<StepHikeCompact.Details fullWidth>

  Note the two options we pass to `session.run()`:

  - `mean_pool`: The first option sets `pooling` to `mean`. Pooling refers to how token-level embedding representations are compressed into a single sentence embedding that reflects the meaning of the entire sentence. Average pooling is the most common type of pooling for sentence embeddings.
  - `normalize`: The second option normalizes the embedding vector so that it can be used with distance measures like dot product. A normalized vector means its length (magnitude) is 1 - also referred to as a unit vector. A vector is normalized by dividing each element by the vector's length (magnitude), which maintains its direction but changes its length to 1.

</StepHikeCompact.Details>

<StepHikeCompact.Details title="Test it!">

  To test the Edge Function, first start a local functions server.

</StepHikeCompact.Details>

<StepHikeCompact.Code>

  ```shell
  supabase functions serve
  ```

</StepHikeCompact.Code>

<StepHikeCompact.Details fullWidth>

  Then in a new shell, create an HTTP request using cURL and pass in your input in the JSON body.

  ```shell
  curl --request POST 'http://localhost:54321/functions/v1/embed' \
    --header 'Authorization: Bearer ANON_KEY' \
    --header 'Content-Type: application/json' \
    --data '{ "input": "hello world" }'
  ```

  Be sure to replace `ANON_KEY` with your project's anonymous key. You can get this key by running `supabase status`.

</StepHikeCompact.Details>