1. Create a [standalone connector](#standalone-connector): A standalone connector can be reused and shared by multiple remote models but requires access to both the model and connector in OpenSearch and the third-party platform, such as OpenAI or Amazon SageMaker, that the connector is accessing. Standalone connectors are saved in a connector index.
2. Create a remote model with an [internal connector](#internal-connector): An internal connector can only be used with the remote model in which it was created. To access an internal connector, you only need access to the model itself because the connection is established inside the model. Internal connectors are saved in the model index.
As of OpenSearch 2.9, connectors have been tested for the following ML services, though it is possible to create connectors for other platforms not listed here:
- [Amazon SageMaker](https://aws.amazon.com/sagemaker/) allows you to host and manage the lifecycle of text embedding models, powering semantic search queries in OpenSearch. When connected, Amazon SageMaker hosts your models and OpenSearch is used to query inferences. This benefits Amazon SageMaker users who value its functionality, such as model monitoring, serverless hosting, and workflow automation for continuous training and deployment.
- [Cohere](https://cohere.com/) allows you to use data from OpenSearch to power the Cohere large language models.
- The [Bedrock Titan Embeddings](https://aws.amazon.com/bedrock/titan/) model can drive semantic search and retrieval-augmented generation in OpenSearch.
All connectors consist of a JSON blueprint created by machine learning (ML) developers. The blueprint allows administrators and data scientists to make connections between OpenSearch and an AI service or model-serving technology.
You can find blueprints for each connector in the [ML Commons repository](https://github.com/opensearch-project/ml-commons/tree/2.x/docs/remote_inference_blueprints).
Admins are only required to enter their `credential` settings, such as `"openAI_key"`, for the service they are connecting to. All other parameters are defined within the [blueprint]({{site.url}}{{site.baseurl}}/ml-commons-plugin/extensibility/blueprints/).
To create a standalone connector, send a request to the `connectors/_create` endpoint and provide all of the parameters described in [Connector blueprints]({{site.url}}{{site.baseurl}}/ml-commons-plugin/extensibility/blueprints/):
To create an internal connector, provide all of the parameters described in [Connector blueprints]({{site.url}}{{site.baseurl}}/ml-commons-plugin/extensibility/blueprints/) within the `connector` object of a request to the `models/_register` endpoint:
The following example creates a standalone OpenAI chat connector. The same options can be used for an internal connector under the `connector` parameter:
```json
POST /_plugins/_ml/connectors/_create
{
"name": "OpenAI Chat Connector",
"description": "The connector to public OpenAI model service for GPT 3.5",
After creating the connector, you can retrieve the `task_id` and `connector_id` to register and deploy the model and then use the Predict API, similarly to a standalone connector.
The following example creates a standalone Amazon SageMaker connector. The same options can be used for an internal connector under the `connector` parameter:
```json
POST /_plugins/_ml/connectors/_create
{
"name": "sagemaker: embedding",
"description": "Test connector for Sagemaker embedding model",
- To learn more about using models in OpenSearch, see [Using custom models within OpenSearch]({{site.url}}{{site.baseurl}}/ml-commons-plugin/ml-framework/).
- To learn more about model access control and model groups, see [Model access control]({{site.url}}{{site.baseurl}}/ml-commons-plugin/model-access-control/).
