Register a model

All versions of a particular model are held in a model group. You can either register a model group before registering a model to the group or register a first version of a model, thereby creating the group. Each model group name in the cluster must be globally unique.

If you are registering the first version of a model without first registering the model group, a new model group is created automatically with the following name and access level:

• Name: The new model group will have the same name as the model. Because the model group name must be unique, ensure that your model name does not have the same name as any model groups in the cluster.
• Access level: The access level for the new model group is determined using the access_mode, backend_roles, and add_all_backend_roles parameters that you pass in the request. If you provide none of the three parameters, the new model group will be private if model access control is enabled on your cluster and public if model access control is disabled. The newly registered model is the first model version assigned to that model group.

Once a model group is created, provide its model_group_id to register a new model version to the model group. In this case, the model name does not need to be unique.

If you’re using pretrained models provided by OpenSearch, we recommend that you first register a model group with a unique name for these models. Then register the pretrained models as versions to that model group. This ensures that every model group has a globally unique model group name.

For information about user access for this API, see Model access control considerations.

If the model is more than 10 MB in size, ML Commons splits it into smaller chunks and saves those chunks in the model’s index.

Path and HTTP methods

POST /_plugins/_ml/models/_register

Query parameters

The following table lists the available query parameters. All query parameters are optional.

Register an OpenSearch-provided pretrained model

OpenSearch provides several pretrained models. For more information, see OpenSearch-provided pretrained models.

Register a pretrained text embedding model

To register a pretrained text embedding model, the only required parameters are name, version, and model_format.

Request fields

The following table lists the available request fields.

Example request: OpenSearch-provided text embedding model

POST /_plugins/_ml/models/_register
{
  "name": "huggingface/sentence-transformers/msmarco-distilbert-base-tas-b",
  "version": "1.0.1",
  "model_group_id": "Z1eQf4oB5Vm0Tdw8EIP2",
  "model_format": "TORCH_SCRIPT"
}

copy

Register a pretrained sparse encoding model

To register a pretrained sparse encoding model, you must set the function name to SPARSE_ENCODING or SPARSE_TOKENIZE.

Request fields

The following table lists the available request fields.

Example request: OpenSearch-provided sparse encoding model

POST /_plugins/_ml/models/_register
{
    "name": "amazon/neural-sparse/opensearch-neural-sparse-encoding-doc-v1",
    "version": "1.0.1",
    "model_group_id": "Z1eQf4oB5Vm0Tdw8EIP2",
    "model_format": "TORCH_SCRIPT"
}

copy

Register a custom model

To use a custom model locally within the OpenSearch cluster, you need to provide a URL and a config object for that model. For more information, see Custom local models.

Request fields

The following table lists the available request fields.

The model_config object

You can further customize a pretrained sentence transformer model’s post-processing logic with the following optional fields in the model_config object.

Example request: Custom model

The following example request registers a version 1.0.0 of an NLP sentence transformation model named all-MiniLM-L6-v2.

POST /_plugins/_ml/models/_register
{
    "name": "all-MiniLM-L6-v2",
    "version": "1.0.0",
    "description": "test model",
    "model_format": "TORCH_SCRIPT",
    "model_group_id": "FTNlQ4gBYW0Qyy5ZoxfR",
    "model_content_hash_value": "c15f0d2e62d872be5b5bc6c84d2e0f4921541e29fefbef51d59cc10a8ae30e0f",
    "model_config": {
        "model_type": "bert",
        "embedding_dimension": 384,
        "framework_type": "sentence_transformers",
       "all_config": "{\"_name_or_path\":\"nreimers/MiniLM-L6-H384-uncased\",\"architectures\":[\"BertModel\"],\"attention_probs_dropout_prob\":0.1,\"gradient_checkpointing\":false,\"hidden_act\":\"gelu\",\"hidden_dropout_prob\":0.1,\"hidden_size\":384,\"initializer_range\":0.02,\"intermediate_size\":1536,\"layer_norm_eps\":1e-12,\"max_position_embeddings\":512,\"model_type\":\"bert\",\"num_attention_heads\":12,\"num_hidden_layers\":6,\"pad_token_id\":0,\"position_embedding_type\":\"absolute\",\"transformers_version\":\"4.8.2\",\"type_vocab_size\":2,\"use_cache\":true,\"vocab_size\":30522}"
    },
    "url": "https://artifacts.opensearch.org/models/ml-models/huggingface/sentence-transformers/all-MiniLM-L6-v2/1.0.1/torch_script/sentence-transformers_all-MiniLM-L6-v2-1.0.1-torch_script.zip"
}

copy

Register a model hosted on a third-party platform

To register a model hosted on a third-party platform, you can either first create a standalone connector and provide the ID of that connector or specify an internal connector for the model. For more information, see Creating connectors for third-party ML platforms.

Request fields

The following table lists the available request fields.

Example request: Externally hosted with a standalone connector

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

copy

Example request: Externally hosted with a connector specified as part of the model

POST /_plugins/_ml/models/_register
{
    "name": "openAI-GPT-3.5: internal connector",
    "function_name": "remote",
    "model_group_id": "lEFGL4kB4ubqQRzegPo2",
    "description": "test model",
    "connector": {
        "name": "OpenAI Connector",
        "description": "The connector to public OpenAI model service for GPT 3.5",
        "version": 1,
        "protocol": "http",
        "parameters": {
            "endpoint": "api.openai.com",
            "max_tokens": 7,
            "temperature": 0,
            "model": "text-davinci-003"
        },
        "credential": {
            "openAI_key": "..."
        },
        "actions": [
            {
                "action_type": "predict",
                "method": "POST",
                "url": "https://${parameters.endpoint}/v1/completions",
                "headers": {
                    "Authorization": "Bearer ${credential.openAI_key}"
                },
                "request_body": "{ \"model\": \"${parameters.model}\", \"prompt\": \"${parameters.prompt}\", \"max_tokens\": ${parameters.max_tokens}, \"temperature\": ${parameters.temperature} }"
            }
        ]
    }
}

copy

Example response

OpenSearch responds with the task_id, task status, and model_id:

{
  "task_id" : "ew8I44MBhyWuIwnfvDIH", 
  "status" : "CREATED",
  "model_id": "t8qvDY4BChVAiNVEuo8q"
}

The guardrails parameter

Guardrails are safety measures for large language models (LLMs). They provide a set of rules and boundaries that control how an LLM behaves and what kind of output it generates.

To register an externally hosted model with guardrails, provide the guardrails parameter, which supports the following fields. All fields are optional.

Examples

The following examples configure an externally hosted model with guardrails.

Example request: Regex and stopword validation

The following example uses a regular expression and a set of stopwords to validate the LLM response:

POST /_plugins/_ml/models/_register
{
  "name": "openAI-gpt-3.5-turbo",
  "function_name": "remote",
  "model_group_id": "1jriBYsBq7EKuKzZX131",
  "description": "test model",
  "connector_id": "a1eMb4kBJ1eYAeTMAljY",
  "guardrails": {
    "type": "local_regex",
    "input_guardrail": {
      "stop_words": [
        {
          "index_name": "stop_words_input",
          "source_fields": ["title"]
        }
      ],
      "regex": ["regex1", "regex2"]
    },
    "output_guardrail": {
      "stop_words": [
        {
          "index_name": "stop_words_output",
          "source_fields": ["title"]
        }
      ],
      "regex": ["regex1", "regex2"]
    }
  }
}

copy

For a complete example, see Validating input/output using stopwords and regex.

Example request: Guardrail model validation

The following example uses a guardrail model to validate the LLM response:

POST /_plugins/_ml/models/_register?deploy=true
{
    "name": "Bedrock Claude V2 model with guardrails model",
    "function_name": "remote",
    "model_group_id": "ppSmpo8Bi-GZ0tf1i7cD",
    "description": "Bedrock Claude V2 model with guardrails model",
    "connector_id": "xnJjDZABNFJeYR3IPvTO",
    "guardrails": {
        "input_guardrail": {
            "model_id": "o3JaDZABNFJeYR3I2fRV",
            "response_validation_regex": "^\\s*\"[Aa]ccept\"\\s*$"
        },
        "output_guardrail": {
            "model_id": "o3JaDZABNFJeYR3I2fRV",
            "response_validation_regex": "^\\s*\"[Aa]ccept\"\\s*$"
        },
        "type": "model"
    }
}

copy

For a complete example, see Validating input/output using a guardrail model.

Example response

OpenSearch responds with the task_id, task status, and model_id:

{
    "task_id": "tsqvDY4BChVAiNVEuo8F",
    "status": "CREATED",
    "model_id": "t8qvDY4BChVAiNVEuo8q"
}

The interface parameter

The model interface provides a highly flexible way to add arbitrary metadata annotations to all local deep learning models and externally hosted models in a JSON schema syntax. This annotation initiates a validation check on the input and output fields of the model during the model’s invocation. The validation check ensures that the input and output fields are in the correct format both before and after the model performs inference.

To register a model with a model interface, provide the interface parameter, which supports the following fields.

The input and output fields are evaluated against the provided JSON schema. You do not need to provide both fields simultaneously.

Connector model interfaces

To simplify your workflow, you can register an externally hosted model using a connector in one of the connector blueprint formats. If you do so, a predefined model interface for this connector is generated automatically during model registration. The predefined model interface is generated based on the connector blueprint and the model’s metadata, so you must strictly follow the blueprint when creating the connector in order to avoid errors.

The following connector blueprints currently support creating predefined model interfaces:

• Amazon Comprehend
• Amazon Textract (Note that a predefined model interface is only available for the DetectDocumentText API; the DetectEnities API is not currently supported).
• Amazon Bedrock AI21 Labs Jurassic
• Amazon Bedrock Anthropic Claude 3
• Amazon Bedrock Anthropic Claude
• Amazon Bedrock Cohere Embed English v3
• Amazon Bedrock Cohere Embed Multilingual v3
• Amazon Bedrock Titan Text Embeddings
• Amazon Bedrock Titan Multimodal Embeddings

To learn more about connector blueprints, see Connector blueprints.

Example request: Externally hosted model with an interface

POST /_plugins/_ml/models/_register
{
    "name": "openAI-gpt-3.5-turbo",
    "function_name": "remote",
    "description": "test model",
    "connector_id": "A-j7K48BZzNMh1sWVdJu",
    "interface": {
        "input": {
            "properties": {
                "parameters": {
                    "properties": {
                        "messages": {
                            "type": "string",
                            "description": "This is a test description field"
                        }
                    }
                }
            }
        },
        "output": {
            "properties": {
                "inference_results": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {
                            "output": {
                                "type": "array",
                                "items": {
                                    "properties": {
                                        "name": {
                                            "type": "string",
                                            "description": "This is a test description field"
                                        },
                                        "dataAsMap": {
                                            "type": "object",
                                            "description": "This is a test description field"
                                        }
                                    }
                                },
                                "description": "This is a test description field"
                            },
                            "status_code": {
                                "type": "integer",
                                "description": "This is a test description field"
                            }
                        }
                    },
                    "description": "This is a test description field"
                }
            }
        }
    }
}

copy

Example response

OpenSearch responds with the task_id, task status, and model_id:

{
    "task_id": "tsqvDY4BChVAiNVEuo8F",
    "status": "CREATED",
    "model_id": "t8qvDY4BChVAiNVEuo8q"
}

Check the status of model registration

To see the status of your model registration and retrieve the model ID created for the new model version, pass the task_id as a path parameter to the Tasks API:

GET /_plugins/_ml/tasks/<task_id>

copy

The response contains the model ID of the model version:

{
  "model_id": "Qr1YbogBYOqeeqR7sI9L",
  "task_type": "DEPLOY_MODEL",
  "function_name": "TEXT_EMBEDDING",
  "state": "COMPLETED",
  "worker_node": [
    "N77RInqjTSq_UaLh1k0BUg"
  ],
  "create_time": 1685478486057,
  "last_update_time": 1685478491090,
  "is_async": true
}