Create an Contextual AI inference endpoint

PUT /_inference/{task_type}/{contextualai_inference_id}

Auth

Create an inference endpoint to perform an inference task with the contexualai service.

To review the available rerank models, refer to https://docs.contextual.ai/api-reference/rerank/rerank#body-model.

Required privileges

Cluster privileges manage_inference

Path parameters

task_type enum required: The type of the inference task that the model will perform.; Values: rerank
contextualai_inference_id string required: The unique identifier of the inference endpoint.

Query parameters

timeout union oneOf · default: 30s: Specifies the amount of time to wait for the inference endpoint to be created.; Values: -1 0

Request body

service enum required: The type of service supported for the specified task type. In this case, contextualai.; Values: contextualai
service_settings object required: Settings used to install the inference model. These settings are specific to the contextualai service.
task_settings object: Settings to configure the inference task. These settings are specific to the task type you specified.

Response

application/json

chunking_settings object: The chunking configuration object. Applies only to the embedding, sparse_embedding and text_embedding task types. Not applicable to the rerank, completion, or chat_completion task types.
service string required: The service type
service_settings object required: Settings specific to the service
task_settings object: Task settings specific to the service and task type
inference_id string required: The inference Id
task_type enum required: The task type; Values: rerank

Examples

Request Console 1 / 8 languages

Run PUT _inference/rerank/contextualai-rerank to create an inference endpoint for rerank tasks using the Contextual AI service.

Console Kibana Dev Tools

PUT _inference/rerank/contextualai-rerank
{
    "service": "contextualai",
    "service_settings": {
        "api_key": "ContextualAI-Api-key",
        "model_id": "ctxl-rerank-v2-instruct-multilingual-mini"
    },
    "task_settings": {
        "instruction": "Rerank the following documents based on their relevance to the query.",
        "top_k": 3
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "rerank",
  inference_id: "contextualai-rerank",
  inference_config: {
    service: "contextualai",
    service_settings: {
      api_key: "ContextualAI-Api-key",
      model_id: "ctxl-rerank-v2-instruct-multilingual-mini",
    },
    task_settings: {
      instruction:
        "Rerank the following documents based on their relevance to the query.",
      top_k: 3,
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="rerank",
    inference_id="contextualai-rerank",
    inference_config={
        "service": "contextualai",
        "service_settings": {
            "api_key": "ContextualAI-Api-key",
            "model_id": "ctxl-rerank-v2-instruct-multilingual-mini"
        },
        "task_settings": {
            "instruction": "Rerank the following documents based on their relevance to the query.",
            "top_k": 3
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/rerank/contextualai-rerank" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "contextualai",
    "service_settings": {
      "api_key": "ContextualAI-Api-key",
      "model_id": "ctxl-rerank-v2-instruct-multilingual-mini"
    },
    "task_settings": {
      "instruction": "Rerank the following documents based on their relevance to the query.",
      "top_k": 3
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("contextualai-rerank")
    .taskType(TaskType.Rerank)
    .inferenceConfig(i -> i
        .service("contextualai")
        .serviceSettings(JsonData.fromJson("""
{"api_key":"ContextualAI-Api-key","model_id":"ctxl-rerank-v2-instruct-multilingual-mini"}
"""))
        .taskSettings(JsonData.fromJson("""
{"instruction":"Rerank the following documents based on their relevance to the query.","top_k":3}
"""))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "contextualai-rerank",
        TaskType = TaskType.Rerank,
        InferenceConfig = new()
        {
            Service = "contextualai",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "ContextualAI-Api-key",
              "model_id": "ctxl-rerank-v2-instruct-multilingual-mini"
            }
            """),
            TaskSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "instruction": "Rerank the following documents based on their relevance to the query.",
              "top_k": 3
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "rerank",
    "inference_id" => "contextualai-rerank",
    "body" => [
        "service" => "contextualai",
        "service_settings" => [
            "api_key" => "ContextualAI-Api-key",
            "model_id" => "ctxl-rerank-v2-instruct-multilingual-mini",
        ],
        "task_settings" => [
            "instruction" => "Rerank the following documents based on their relevance to the query.",
            "top_k" => 3,
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "rerank",
  inference_id: "contextualai-rerank",
  body: {
    "service": "contextualai",
    "service_settings": {
      "api_key": "ContextualAI-Api-key",
      "model_id": "ctxl-rerank-v2-instruct-multilingual-mini"
    },
    "task_settings": {
      "instruction": "Rerank the following documents based on their relevance to the query.",
      "top_k": 3
    }
  }
)

Response

{
  "chunking_settings": {
    "max_chunk_size": 250,
    "overlap": 100,
    "sentence_overlap": 1,
    "separator_group": "string",
    "separators": [
      "string"
    ],
    "strategy": "sentence"
  },
  "service": "string",
  "service_settings": {},
  "task_settings": {},
  "inference_id": "string",
  "task_type": "rerank"
}

Generated from the API spec