Create an Amazon Bedrock inference endpoint | Elasticsearch Serverless API documentation

Create an Amazon Bedrock inference endpoint Added in 8.12.0

PUT /_inference/{task_type}/{amazonbedrock_inference_id}

Creates an inference endpoint to perform an inference task with the amazonbedrock service.

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

When you create an inference endpoint, the associated machine learning model is automatically deployed if it is not already running. After creating the endpoint, wait for the model deployment to complete before using it. To verify the deployment status, use the get trained model statistics API. Look for "state": "fully_allocated" in the response and ensure that the "allocation_count" matches the "target_allocation_count". Avoid creating multiple endpoints for the same model unless required, as each endpoint consumes significant resources.

Path parameters

task_type string Required

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

Values are completion or text_embedding.
amazonbedrock_inference_id string Required

The unique identifier of the inference endpoint.

application/json

Body

chunking_settings object
Hide chunking_settings attributes Show chunking_settings attributes object
- service string Required
  
  The service type
- service_settings object Required
- task_settings 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).
- 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.
- 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.
- strategy string
  
  The chunking strategy: sentence or word.
service string Required

Value is amazonbedrock.
service_settings object Required
Hide service_settings attributes Show service_settings attributes object
- access_key string Required
  
  A valid AWS access key that has permissions to use Amazon Bedrock and access to models for inference requests.
- model string Required
  
  The base model ID or an ARN to a custom model based on a foundational model. The base model IDs can be found in the Amazon Bedrock documentation. Note that the model ID must be available for the provider chosen and your IAM user must have access to the model.
  
  External documentation
- provider string
  The model provider for your deployment. Note that some providers may support only certain task types. Supported providers include:
  
  amazontitan - available for text_embedding and completion task types
  
  anthropic - available for completion task type only
  
  ai21labs - available for completion task type only
  
  cohere - available for text_embedding and completion task types
  
  meta - available for completion task type only
  
  mistral - available for completion task type only
- region string Required
  
  The region that your model or ARN is deployed in. The list of available regions per model can be found in the Amazon Bedrock documentation.
  
  External documentation
- rate_limit object
  Hide rate_limit attribute Show rate_limit attribute object
  
  requests_per_minute number
  
  The number of requests allowed per minute.
- secret_key string Required
  
  A valid AWS secret key that is paired with the access_key. For informationg about creating and managing access and secret keys, refer to the AWS documentation.
  
  External documentation
task_settings object
Hide task_settings attributes Show task_settings attributes object
- max_new_tokens number
  
  For a completion task, it sets the maximum number for the output tokens to be generated.
- temperature number
  
  For a completion task, it is a number between 0.0 and 1.0 that controls the apparent creativity of the results. At temperature 0.0 the model is most deterministic, at temperature 1.0 most random. It should not be used if top_p or top_k is specified.
- top_k number
  
  For a completion task, it limits samples to the top-K most likely words, balancing coherence and variability. It is only available for anthropic, cohere, and mistral providers. It is an alternative to temperature; it should not be used if temperature is specified.
- top_p number
  
  For a completion task, it is a number in the range of 0.0 to 1.0, to eliminate low-probability tokens. Top-p uses nucleus sampling to select top tokens whose sum of likelihoods does not exceed a certain value, ensuring both variety and coherence. It is an alternative to temperature; it should not be used if temperature is specified.

Responses

200 application/json
Hide response attributes Show response attributes object
- Hide attributes Show 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).
  
  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.
  
  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.
  
  strategy string
  
  The chunking strategy: sentence or word.
- 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 sparse_embedding, text_embedding, rerank, completion, or chat_completion.

PUT /_inference/{task_type}/{amazonbedrock_inference_id}

curl \
 --request PUT 'http://api.example.com/_inference/{task_type}/{amazonbedrock_inference_id}' \
 --header "Authorization: $API_KEY" \
 --header "Content-Type: application/json" \
 --data '"{\n    \"service\": \"amazonbedrock\",\n    \"service_settings\": {\n        \"access_key\": \"AWS-access-key\",\n        \"secret_key\": \"AWS-secret-key\",\n        \"region\": \"us-east-1\",\n        \"provider\": \"amazontitan\",\n        \"model\": \"amazon.titan-embed-text-v2:0\"\n    }\n}"'

Request examples

Run `PUT _inference/text_embedding/amazon_bedrock_embeddings` to create an inference endpoint that performs a text embedding task.

{
    "service": "amazonbedrock",
    "service_settings": {
        "access_key": "AWS-access-key",
        "secret_key": "AWS-secret-key",
        "region": "us-east-1",
        "provider": "amazontitan",
        "model": "amazon.titan-embed-text-v2:0"
    }
}

Run `PUT _inference/completion/openai-completion` to create an inference endpoint to perform a completion task type.

{
    "service": "openai",
    "service_settings": {
        "api_key": "OpenAI-API-Key",
        "model_id": "gpt-3.5-turbo"
    }
}