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

# Amazon SageMaker

> Configure Amazon SageMaker with Gobi to use deployed LLM endpoints for both chat and embedding models, supporting LMI and HuggingFace TEI deployments with AWS credentials

SageMaker can be used for both chat and embedding models. Chat models are supported for endpoints deployed with [LMI](https://docs.djl.ai/docs/serving/serving/docs/lmi/index.html), and embedding models are supported for endpoints deployed with [HuggingFace TEI](https://huggingface.co/blog/sagemaker-huggingface-embedding)

Here is an example Sagemaker configuration setup:

<Tabs>
  <Tab title="YAML">
    ```yaml title="config.yaml" theme={null}
    models:
      - name: deepseek-6.7b-instruct
        provider: sagemaker
        model: lmi-model-deepseek-coder-xxxxxxx
        region: us-west-2
        roles:
          - chat
      - name: mxbai-embed
        provider: sagemaker
        model: mxbai-embed-large-v1-endpoint
        roles:
          - embed
    ```
  </Tab>

  <Tab title="JSON">
    ```json title="config.json" theme={null}
    {
      "models": [
        {
          "title": "deepseek-6.7b-instruct",
          "provider": "sagemaker",
          "model": "lmi-model-deepseek-coder-xxxxxxx",
          "region": "us-west-2"
        }
      ],
      "embeddingsProvider": {
        "provider": "sagemaker",
        "model": "mxbai-embed-large-v1-endpoint"
      }
    }
    ```
  </Tab>
</Tabs>

The value in model should be the SageMaker endpoint name you deployed.

Authentication will be through temporary or long-term credentials in
\~/.aws/credentials under a profile called "sagemaker".

```title="~/.aws/credentials theme={null}
[sagemaker]
aws_access_key_id = abcdefg
aws_secret_access_key = hijklmno
aws_session_token = pqrstuvwxyz # Optional: means short term creds.
```