Create a Hugging Face inference endpoint Generally available; Added in 8.12.0

PUT /_inference/{task_type}/{huggingface_inference_id}
Api key auth Basic auth Bearer auth

Create an inference endpoint to perform an inference task with the hugging_face service. Supported tasks include: text_embedding, completion, and chat_completion.

To configure the endpoint, first visit the Hugging Face Inference Endpoints page and create a new endpoint. Select a model that supports the task you intend to use.

For Elastic's text_embedding task: The selected model must support the Sentence Embeddings task. On the new endpoint creation page, select the Sentence Embeddings task under the Advanced Configuration section. After the endpoint has initialized, copy the generated endpoint URL. Recommended models for text_embedding task:

  • all-MiniLM-L6-v2
  • all-MiniLM-L12-v2
  • all-mpnet-base-v2
  • e5-base-v2
  • e5-small-v2
  • multilingual-e5-base
  • multilingual-e5-small

For Elastic's chat_completion and completion tasks: The selected model must support the Text Generation task and expose OpenAI API. HuggingFace supports both serverless and dedicated endpoints for Text Generation. When creating dedicated endpoint select the Text Generation task. After the endpoint is initialized (for dedicated) or ready (for serverless), ensure it supports the OpenAI API and includes /v1/chat/completions part in URL. Then, copy the full endpoint URL for use. Recommended models for chat_completion and completion tasks:

  • Mistral-7B-Instruct-v0.2
  • QwQ-32B
  • Phi-3-mini-128k-instruct

For Elastic's rerank task: The selected model must support the sentence-ranking task and expose OpenAI API. HuggingFace supports only dedicated (not serverless) endpoints for Rerank so far. After the endpoint is initialized, copy the full endpoint URL for use. Tested models for rerank task:

  • bge-reranker-base
  • jina-reranker-v1-turbo-en-GGUF

Required authorization

  • Cluster privileges: manage_inference

Path parameters

  • task_type string

    The type of the inference task that the model will perform.

    Values are chat_completion, completion, rerank, or text_embedding.

  • huggingface_inference_id string Required

    The unique identifier of the inference endpoint.

application/json

Body

  • chunking_settings object

    Chunking configuration object

    Hide chunking_settings attributes Show chunking_settings attributes object
    • max_chunk_size number

      The maximum size of a chunk in words. This value cannot be higher than 300 or lower than 20 (for sentence strategy) or 10 (for word strategy).

      Default value is 250.

    • overlap number

      The number of overlapping words for chunks. It is applicable only to a word chunking strategy. This value cannot be higher than half the max_chunk_size value.

      Default value is 100.

    • sentence_overlap number

      The number of overlapping sentences for chunks. It is applicable only for a sentence chunking strategy. It can be either 1 or 0.

      Default value is 1.

    • strategy string

      The chunking strategy: sentence or word.

      Default value is sentence.

  • service string Required

    Value is hugging_face.

  • service_settings object Required
    Hide service_settings attributes Show service_settings attributes object
    • api_key string Required

      A valid access token for your HuggingFace account. You can create or find your access tokens on the HuggingFace settings page.

      IMPORTANT: You need to provide the API key only once, during the inference model creation. The get inference endpoint API does not retrieve your API key. After creating the inference model, you cannot change the associated API key. If you want to use a different API key, delete the inference model and recreate it with the same name and the updated API key.

      External documentation
    • rate_limit object

      This setting helps to minimize the number of rate limit errors returned from the service.

      Hide rate_limit attribute Show rate_limit attribute object
      • requests_per_minute number

        The number of requests allowed per minute. By default, the number of requests allowed per minute is set by each service as follows:

        • alibabacloud-ai-search service: 1000
        • anthropic service: 50
        • azureaistudio service: 240
        • azureopenai service and task type text_embedding: 1440
        • azureopenai service and task type completion: 120
        • cohere service: 10000
        • elastic service and task type chat_completion: 240
        • googleaistudio service: 360
        • googlevertexai service: 30000
        • hugging_face service: 3000
        • jinaai service: 2000
        • mistral service: 240
        • openai service and task type text_embedding: 3000
        • openai service and task type completion: 500
        • voyageai service: 2000
        • watsonxai service: 120
    • url string Required

      The URL endpoint to use for the requests. For completion and chat_completion tasks, the deployed model must be compatible with the Hugging Face Chat Completion interface (see the linked external documentation for details). The endpoint URL for the request must include /v1/chat/completions. If the model supports the OpenAI Chat Completion schema, a toggle should appear in the interface. Enabling this toggle doesn't change any model behavior, it reveals the full endpoint URL needed (which should include /v1/chat/completions) when configuring the inference endpoint in Elasticsearch. If the model doesn't support this schema, the toggle may not be shown.

      External documentation
    • model_id string

      The name of the HuggingFace model to use for the inference task. For completion and chat_completion tasks, this field is optional but may be required for certain models — particularly when using serverless inference endpoints. For the text_embedding task, this field should not be included. Otherwise, the request will fail.

  • task_settings object
    Hide task_settings attributes Show task_settings attributes object
    • return_documents boolean

      For a rerank task, return doc text within the results.

    • top_n number

      For a rerank task, the number of most relevant documents to return. It defaults to the number of the documents.

Responses

  • 200 application/json
    Hide response attributes Show response attributes object
    • chunking_settings object

      Chunking configuration object

      Hide chunking_settings attributes Show chunking_settings attributes object
      • max_chunk_size number

        The maximum size of a chunk in words. This value cannot be higher than 300 or lower than 20 (for sentence strategy) or 10 (for word strategy).

        Default value is 250.

      • overlap number

        The number of overlapping words for chunks. It is applicable only to a word chunking strategy. This value cannot be higher than half the max_chunk_size value.

        Default value is 100.

      • sentence_overlap number

        The number of overlapping sentences for chunks. It is applicable only for a sentence chunking strategy. It can be either 1 or 0.

        Default value is 1.

      • strategy string

        The chunking strategy: sentence or word.

        Default value is sentence.

    • service string Required

      The service type

    • service_settings object Required
    • task_settings object
    • inference_id string Required

      The inference Id

    • task_type string Required

      Values are chat_completion, completion, rerank, or text_embedding.
PUT /_inference/{task_type}/{huggingface_inference_id} 
PUT _inference/text_embedding/hugging-face-embeddings
{
    "service": "hugging_face",
    "service_settings": {
        "api_key": "hugging-face-access-token", 
        "url": "url-endpoint" 
    }
}
resp = client.inference.put(
    task_type="text_embedding",
    inference_id="hugging-face-embeddings",
    inference_config={
        "service": "hugging_face",
        "service_settings": {
            "api_key": "hugging-face-access-token",
            "url": "url-endpoint"
        }
    },
)
const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "hugging-face-embeddings",
  inference_config: {
    service: "hugging_face",
    service_settings: {
      api_key: "hugging-face-access-token",
      url: "url-endpoint",
    },
  },
});
response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "hugging-face-embeddings",
  body: {
    "service": "hugging_face",
    "service_settings": {
      "api_key": "hugging-face-access-token",
      "url": "url-endpoint"
    }
  }
)
$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "hugging-face-embeddings",
    "body" => [
        "service" => "hugging_face",
        "service_settings" => [
            "api_key" => "hugging-face-access-token",
            "url" => "url-endpoint",
        ],
    ],
]);
curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"service":"hugging_face","service_settings":{"api_key":"hugging-face-access-token","url":"url-endpoint"}}' "$ELASTICSEARCH_URL/_inference/text_embedding/hugging-face-embeddings"
client.inference().put(p -> p
    .inferenceId("hugging-face-embeddings")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("hugging_face")
        .serviceSettings(JsonData.fromJson("{\"api_key\":\"hugging-face-access-token\",\"url\":\"url-endpoint\"}"))
    )
);
Request examples
Run `PUT _inference/text_embedding/hugging-face-embeddings` to create an inference endpoint that performs a `text_embedding` task type. 
{
    "service": "hugging_face",
    "service_settings": {
        "api_key": "hugging-face-access-token", 
        "url": "url-endpoint" 
    }
}
Run `PUT _inference/rerank/hugging-face-rerank` to create an inference endpoint that performs a `rerank` task type. 
{
    "service": "hugging_face",
    "service_settings": {
        "api_key": "hugging-face-access-token", 
        "url": "url-endpoint" 
    },
    "task_settings": {
        "return_documents": true,
        "top_n": 3
    }
}