opensearch-docs-cn/_ml-commons-plugin/extensibility/index.md

layout	title	has_children	has_toc	nav_order
default	Connecting to remote models	true	false	60

Connecting to remote models

Machine learning (ML) extensibility enables ML developers to create integrations with other ML services, such as Amazon SageMaker or OpenAI. These integrations provide system administrators and data scientists the ability to run ML workloads outside of their OpenSearch cluster.

To get started with ML extensibility, choose from the following options:

• If you're an ML developer wanting to integrate with your specific ML services, see Connector blueprints.
• If you're a system administrator or data scientist wanting to create a connection to an ML service, see Connectors.

Prerequisites

If you're an admin deploying an ML connector, make sure that the target model of the connector has already been deployed on your chosen platform. Furthermore, make sure that you have permissions to send and receive data to the third-party API for your connector.

When access control is enabled on your third-party platform, you can enter your security settings using the authorization or credential settings inside the connector API.

Adding trusted endpoints

To configure connectors in OpenSearch, add the trusted endpoints to your cluster settings by using the plugins.ml_commons.trusted_connector_endpoints_regex setting, which supports Java regex expressions:

PUT /_cluster/settings
{
    "persistent": {
        "plugins.ml_commons.trusted_connector_endpoints_regex": [
          "^https://runtime\\.sagemaker\\..*[a-z0-9-]\\.amazonaws\\.com/.*$",
          "^https://api\\.openai\\.com/.*$",
          "^https://api\\.cohere\\.ai/.*$"
        ]
    }
}

{% include copy-curl.html %}

Setting up connector access control

If you plan on using a remote connector, make sure to use an OpenSearch cluster with the Security plugin enabled. Using the Security plugin gives you access to connector access control, which is required when using a remote connector. {: .warning}

If you require granular access control for your connectors, use the following cluster setting:

PUT /_cluster/settings
{
    "persistent": {
        "plugins.ml_commons.connector_access_control_enabled": true
    }
}

{% include copy-curl.html %}

When access control is enabled, you can install the Security plugin. This makes the backend_roles, add_all_backend_roles, or access_model options required in order to use the connector API. If successful, OpenSearch returns the following response:

{
  "acknowledged": true,
  "persistent": {
    "plugins": {
      "ml_commons": {
        "connector_access_control_enabled": "true"
      }
    }
  },
  "transient": {}
}

Node settings

Remote models based on external connectors consume fewer resources. Therefore, you can deploy any model from a standalone connector using data nodes. To make sure that your standalone connection uses data nodes, set plugins.ml_commons.only_run_on_ml_node to false:

PUT /_cluster/settings
{
    "persistent": {
        "plugins.ml_commons.only_run_on_ml_node": false
    }
}

{% include copy-curl.html %}

Step 1: Register a model group

To register a model, you have the following options:

• You can use model_group_id to register a model version to an existing model group.
• If you do not use model_group_id, ML Commons creates a model with a new model group.

To register a model group, send the following request:

POST /_plugins/_ml/model_groups/_register
{
  "name": "remote_model_group",
  "description": "A model group for remote models"
}

{% include copy-curl.html %}

The response contains the model group ID that you'll use to register a model to this model group:

{
 "model_group_id": "wlcnb4kBJ1eYAeTMHlV6",
 "status": "CREATED"
}

To learn more about model groups, see Model access control.

Step 2: Create a connector

You can create a standalone connector or an internal connector as part of a specific model. For more information about connectors and connector examples, see Connectors.

The Connectors Create API, /_plugins/_ml/connectors/_create, creates connectors that facilitate registering and deploying external models in OpenSearch. Using the endpoint parameter, you can connect ML Commons to any supported ML tool by using its specific API endpoint. For example, you can connect to a ChatGPT model by using the api.openai.com endpoint:

POST /_plugins/_ml/connectors/_create
{
    "name": "OpenAI Chat Connector",
    "description": "The connector to public OpenAI model service for GPT 3.5",
    "version": 1,
    "protocol": "http",
    "parameters": {
        "endpoint": "api.openai.com",
        "model": "gpt-3.5-turbo"
    },
    "credential": {
        "openAI_key": "..."
    },
    "actions": [
        {
            "action_type": "predict",
            "method": "POST",
            "url": "https://${parameters.endpoint}/v1/chat/completions",
            "headers": {
                "Authorization": "Bearer ${credential.openAI_key}"
            },
            "request_body": "{ \"model\": \"${parameters.model}\", \"messages\": ${parameters.messages} }"
        }
    ]
}

{% include copy-curl.html %}

The response contains the connector ID for the newly created connector:

{
  "connector_id": "a1eMb4kBJ1eYAeTMAljY"
}

Step 3: Register a remote model

To register a remote model to the model group created in step 1, provide the model group ID from step 1 and the connector ID from step 2 in the following request:

POST /_plugins/_ml/models/_register
{
    "name": "openAI-gpt-3.5-turbo",
    "function_name": "remote",
    "model_group_id": "1jriBYsBq7EKuKzZX131",
    "description": "test model",
    "connector_id": "a1eMb4kBJ1eYAeTMAljY"
}

{% include copy-curl.html %}

OpenSearch returns the task ID of the register operation:

{
  "task_id": "cVeMb4kBJ1eYAeTMFFgj",
  "status": "CREATED"
}

To check the status of the operation, provide the task ID to the Tasks API:

GET /_plugins/_ml/tasks/cVeMb4kBJ1eYAeTMFFgj

{% include copy-curl.html %}

When the operation is complete, the state changes to COMPLETED:

{
  "model_id": "cleMb4kBJ1eYAeTMFFg4",
  "task_type": "REGISTER_MODEL",
  "function_name": "REMOTE",
  "state": "COMPLETED",
  "worker_node": [
    "XPcXLV7RQoi5m8NI_jEOVQ"
  ],
  "create_time": 1689793598499,
  "last_update_time": 1689793598530,
  "is_async": false
}

Step 4: Deploy the remote model

To deploy the registered model, provide its model ID from step 3 in the following request:

POST /_plugins/_ml/models/cleMb4kBJ1eYAeTMFFg4/_deploy

{% include copy-curl.html %}

The response contains the task ID that you can use to check the status of the deploy operation:

{
  "task_id": "vVePb4kBJ1eYAeTM7ljG",
  "status": "CREATED"
}

As in the previous step, check the status of the operation by calling the Tasks API:

GET /_plugins/_ml/tasks/vVePb4kBJ1eYAeTM7ljG

{% include copy-curl.html %}

When the operation is complete, the state changes to COMPLETED:

{
  "model_id": "cleMb4kBJ1eYAeTMFFg4",
  "task_type": "DEPLOY_MODEL",
  "function_name": "REMOTE",
  "state": "COMPLETED",
  "worker_node": [
    "n-72khvBTBi3bnIIR8FTTw"
  ],
  "create_time": 1689793851077,
  "last_update_time": 1689793851101,
  "is_async": true
}

Step 5: Make predictions

Use the Predict API to make predictions:

POST /_plugins/_ml/models/cleMb4kBJ1eYAeTMFFg4/_predict
{
  "parameters": {
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }
}

{% include copy-curl.html %}

To learn more about chat functionality within OpenAI, see the OpenAI Chat API.

The response contains the inference results provided by the OpenAI model:

{
  "inference_results": [
    {
      "output": [
        {
          "name": "response",
          "dataAsMap": {
            "id": "chatcmpl-7e6s5DYEutmM677UZokF9eH40dIY7",
            "object": "chat.completion",
            "created": 1689793889,
            "model": "gpt-3.5-turbo-0613",
            "choices": [
              {
                "index": 0,
                "message": {
                  "role": "assistant",
                  "content": "Hello! How can I assist you today?"
                },
                "finish_reason": "stop"
              }
            ],
            "usage": {
              "prompt_tokens": 19,
              "completion_tokens": 9,
              "total_tokens": 28
            }
          }
        }
      ]
    }
  ]
}

Next steps

• For more information about connectors, including connector examples, see Connectors.
• For more information about connector parameters, see Connector blueprints.
• For more information about managing ML models in OpenSearch, see Using custom models within OpenSearch.
• For more information about interacting with ML models in OpenSearch, see Managing ML models in OpenSearch Dashboards