> ## Documentation Index
> Fetch the complete documentation index at: https://portkey-docs-add-third-party-integration-issues-fixes.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# AWS SageMaker

> Route to your AWS Sagemaker models through Portkey

Sagemaker allows users to host any ML model on their own AWS infrastructure.

With portkey you can manage/restrict access, log requests, and more.

<Note>
  Provider Slug. `sagemaker`
</Note>

## Portkey SDK Integration with AWS Sagemaker

### 1. Install the Portkey SDK

Add the Portkey SDK to your application to interact with Sagemaker's API through Portkey's gateway.

<Tabs>
  <Tab title="NodeJS">
    ```sh theme={null}
    npm install --save portkey-ai
    ```
  </Tab>

  <Tab title="Python">
    ```sh theme={null}
    pip install portkey-ai
    ```
  </Tab>
</Tabs>

### 2. Initialize Portkey with a Virtual Key

There are multiple ways to integrate Sagemaker with Portkey.
You can use your AWS credentials, or use an assumed role.

In this example we will create a virtual key and use it to interact with Sagemaker.
This helps you restrict access (specific models, few endpoints, etc).

<Note>
  Here's how to find your AWS credentials:

  <CardGroup cols={2}>
    <Card title="AWS Access Key" href="/integrations/llms/aws-bedrock#how-to-find-your-aws-credentials">
      <br />Use your `AWS Secret Access Key`, `AWS Access Key Id`, and `AWS Region` to create your Virtual key.<br /><br />

      [**Integration Guide**](/integrations/llms/aws-bedrock#how-to-find-your-aws-credentials)
    </Card>

    <Card title="AWS Assumed Role" href="/product/ai-gateway/virtual-keys/bedrock-amazon-assumed-role">
      <br />Take your `AWS Assumed Role ARN` and `AWS Region` to create the virtaul key.<br /><br /><br />

      [**Integration Guide**](/product/ai-gateway/virtual-keys/bedrock-amazon-assumed-role)
    </Card>
  </CardGroup>
</Note>

Create a virtual key in the Portkey dashboard in the virtual keys section.
You can select sagemaker as the provider, and fill in deployment details.

Initialize the Portkey SDK with the virtual key. (If you are using the REST API, skip to next step)

<Tabs>
  <Tab title="NodeJS SDK">
    ```js theme={null}
    import Portkey from 'portkey-ai'

    const portkey = new Portkey({
        apiKey: "PORTKEY_API_KEY", // Replace with your Portkey API key
        virtualKey: "VIRTUAL_KEY" // Replace with your Sagemaker Virtual Key
    })
    ```
  </Tab>

  <Tab title="Python SDK">
    ```python theme={null}
    from portkey_ai import Portkey

    portkey = Portkey(
        api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
        virtual_key="VIRTUAL_KEY" # Replace with your Sagemaker Virtual Key
    )
    ```
  </Tab>
</Tabs>

### 3. Invoke the Sagemaker model

<Tabs>
  <Tab title="Python SDK">
    ```python theme={null}
    response = portkey.post(
        url="endpoints/{endpoint_name}/invocations",
        # You can pass any key value pair required by the model, apart from `url`, they are passed as kwargs to the Sagemaker endpoint
        inputs="my_custom_value",
        my_custom_key="my_custom_value",
    )

    print(response)
    ```
  </Tab>

  <Tab title="NodeJS SDK">
    ```js theme={null}
    const response = await portkey.post(
        url="endpoints/{endpoint_name}/invocations",
        // You can pass any key value pair required by the model, apart from `url`, they are passed as kwargs to the Sagemaker endpoint
        inputs="my_custom_value",
        my_custom_key="my_custom_value",
    )


    console.log(response);
    ```
  </Tab>

  <Tab title="REST API">
    ```cURL theme={null}
    curl --location 'https://api.portkey.ai/v1/endpoints/{endpoint_name}/invocations' \
    --header 'x-portkey-virtual-key: {VIRTUAL_KEY}' \
    --header 'x-portkey-api-key: {PORTKEY_API_KEY}' \
    --header 'Content-Type: application/json' \
    --data '{
        # You can pass any key value pair required by the model, they are passed as kwargs to the Sagemaker endpoint
        "inputs": "my_custom_value",
        "my_custom_key": "my_custom_value"
    }'
    ```
  </Tab>
</Tabs>

## Making Requests without Virtual Keys

If you do not want to add your AWS details to Portkey vault, you can also directly pass them while instantiating the Portkey client.

These are the supported headers/parameters for Sagemaker (Not required if you're using a virtual key):

| Node SDK                         | Python SDK                             | REST Headers                                       |
| -------------------------------- | -------------------------------------- | -------------------------------------------------- |
| awsAccessKeyId                   | aws\_access\_key\_id                   | x-portkey-aws-access-key-id                        |
| awsSecretAccessKey               | aws\_secret\_access\_key               | x-portkey-aws-secret-access-key                    |
| awsRegion                        | aws\_region                            | x-portkey-aws-region                               |
| awsSessionToken                  | aws\_session\_token                    | x-portkey-aws-session-token                        |
| sagemakerCustomAttributes        | sagemaker\_custom\_attributes          | x-portkey-amzn-sagemaker-custom-attributes         |
| sagemakerTargetModel             | sagemaker\_target\_model               | x-portkey-amzn-sagemaker-target-model              |
| sagemakerTargetVariant           | sagemaker\_target\_variant             | x-portkey-amzn-sagemaker-target-variant            |
| sagemakerTargetContainerHostname | sagemaker\_target\_container\_hostname | x-portkey-amzn-sagemaker-target-container-hostname |
| sagemakerInferenceId             | sagemaker\_inference\_id               | x-portkey-amzn-sagemaker-inference-id              |
| sagemakerEnableExplanations      | sagemaker\_enable\_explanations        | x-portkey-amzn-sagemaker-enable-explanations       |
| sagemakerInferenceComponent      | sagemaker\_inference\_component        | x-portkey-amzn-sagemaker-inference-component       |
| sagemakerSessionId               | sagemaker\_session\_id                 | x-portkey-amzn-sagemaker-session-id                |
| sagemakerModelName               | sagemaker\_model\_name                 | x-portkey-amzn-sagemaker-model-name                |

### Example

<Tabs>
  <Tab title="Python">
    ```python theme={null}
    from portkey_ai import Portkey

    portkey = Portkey(
        api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
        provider="sagemaker",
        aws_region="us-east-1", # Replace with your AWS region  
        aws_access_key_id="AWS_ACCESS_KEY_ID", # Replace with your AWS access key id
        aws_secret_access_key="AWS_SECRET_ACCESS_KEY", # Replace with your AWS secret access key
        amzn_sagemaker_inference_component="SAGEMAKER_INFERENCE_COMPONENT" # Replace with your Sagemaker inference component
    )

    response = portkey.post(
        url="endpoints/{endpoint_name}/invocations",
        # You can pass any key value pair required by the model, apart from `url`, they are passed as kwargs to the Sagemaker endpoint
        inputs="my_custom_value",
        my_custom_key="my_custom_value"
    )

    print(response)
    ```
  </Tab>

  <Tab title="NodeJS">
    ```js theme={null}
    import Portkey from 'portkey-ai'

    const portkey = new Portkey({
        api_key:"PORTKEY_API_KEY",
        provider:"sagemaker",
        aws_access_key_id:"AWS_ACCESS_KEY_ID",
        aws_secret_access_key:"AWS_SECRET_ACCESS_KEY",
        aws_region:"us-east-1",
        amzn_sagemaker_inference_component:"SAGEMAKER_INFERENCE_COMPONENT"
    })

    const response = await portkey.post(
        url="endpoints/{endpoint_name}/invocations",
        // You can pass any key value pair required by the model, apart from `url`, they are passed as kwargs to the Sagemaker endpoint
        inputs="my_custom_value",
        my_custom_key="my_custom_value"
    )

    console.log(response)
    ```
  </Tab>

  <Tab title="cURL">
    ```sh theme={null}
    curl https://api.portkey.ai/v1/chat/completions \
      -H "Content-Type: application/json" \
      -H "x-portkey-api-key: $PORTKEY_API_KEY" \
      -H "x-portkey-provider: sagemaker" \
      -H "x-portkey-aws-access-key-id: $AWS_ACCESS_KEY_ID" \
      -H "x-portkey-aws-secret-access-key: $AWS_SECRET_ACCESS_KEY" \
      -H "x-portkey-aws-region: $AWS_REGION" \
      -H "x-portkey-amzn-sagemaker-inference-component: $SAGEMAKER_INFERENCE_COMPONENT" \
      -d '{
        # You can pass any key value pair apart from `url` required by the model, they are passed as kwargs to the Sagemaker endpoint
        "inputs": "my_custom_value",
        "my_custom_key": "my_custom_value"
      }'
    ```
  </Tab>
</Tabs>

## Next Steps

The complete list of features supported in the SDK are available on the link below.

<Card title="SDK" href="/api-reference/portkey-sdk-client" />

You'll find more information in the relevant sections:

1. [Add metadata to your requests](/product/observability/metadata)
2. [Add gateway configs to your Sagemaker requests](/product/ai-gateway/configs)
3. [Tracing Sagemaker requests](/product/observability/traces)