Machine Learning (ML) connectors provide the ability to integrate OpenSearch ML capabilities with third-party ML tools and platforms. Through connectors, OpenSearch can invoke these third-party endpoints to enrich query results and data pipelines.
1. An [external connector](#external-connector), saved in a connector index, which can be reused and shared with multiple remote models but requires access to both the model, the connector inside of OpenSearch, and the third party being accessed by the connector, such as OpenAI or SageMaker.
2. A [local connector](#local-connector), saved in the model index, which can only be used with one remote model. Unlike a standalone connector, users only need access to the model itself to access an internal connector because the connection is established inside the model.
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.
- [OpenAI ChatGPT](https://openai.com/blog/chatgpt) enables you to invoke an OpenAI chat model from inside an OpenSearch cluster.
- [Cohere](https://cohere.com/) allows you to use data from OpenSearch to power Cohere's large language models.
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/).
The connector creation API, `/_plugins/_ml/connectors/_create`, creates connections that allow users to deploy and register external models through OpenSearch. Using the `endpoint` parameter, you can connect ML Commons to any supported ML tool using its specific API endpoint. For example, to connect to a ChatGPT model, you can connect using `api.openai.com`, as shown in the following example:
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/).
{: .note}
To create an internal connector, add the `connector` parameter to the Register model API, as shown in the following example:
```json
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",
After a successful deployment, you can test the model using the Predict API set in the connector's `action` settings, as shown in the following example:
```json
POST /_plugins/_ml/models/cleMb4kBJ1eYAeTMFFg4/_predict
{
"parameters": {
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}
}
```
The Predict API returns inference results for the connected model, as shown in the following example response:
```json
{
"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
}
}
}
]
}
]
}
```
## Examples
The following example connector requests show how to create a connector with supported third-party tools.
### OpenAI chat connector
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 [ML Framework]({{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/).
