Create a Llama inference endpoint | Elasticsearch API documentation

Create a Llama inference endpoint Generally available; Added in 9.2.0

PUT /_inference/{task_type}/{llama_inference_id}

Api key auth Basic auth Bearer auth

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

Required authorization

Cluster privileges: manage_inference

Path parameters

task_type string

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

Values are text_embedding, completion, or chat_completion.
llama_inference_id string Required

The unique identifier of the inference endpoint.

Query parameters

timeout string

Specifies the amount of time to wait for the inference endpoint to be created.

Values are -1 or 0.

application/json

Body

chunking_settings object

The 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.
- separator_group string
  
  Only applicable to the recursive strategy and required when using it.
  
  Sets a predefined list of separators in the saved chunking settings based on the selected text type. Values can be markdown or plaintext.
  
  Using this parameter is an alternative to manually specifying a custom separators list.
- separators array[string]
  
  Only applicable to the recursive strategy and required when using it.
  
  A list of strings used as possible split points when chunking text.
  
  Each string can be a plain string or a regular expression (regex) pattern. The system tries each separator in order to split the text, starting from the first item in the list.
  
  After splitting, it attempts to recombine smaller pieces into larger chunks that stay within the max_chunk_size limit, to reduce the total number of chunks generated.
- strategy string
  The chunking strategy: sentence, word, none or recursive.
  
  If strategy is set to recursive, you must also specify:
  
  max_chunk_size
  
  either separators orseparator_group
  
  Learn more about different chunking strategies in the linked documentation.
  Default value is sentence.
  
  External documentation
service string Required

The type of service supported for the specified task type. In this case, llama.

Value is llama.
service_settings object Required

Settings used to install the inference model. These settings are specific to the llama service.
Hide service_settings attributes Show service_settings attributes object
- url string Required
  The URL endpoint of the Llama stack endpoint. URL must contain:
  
  For text_embedding task - /v1/inference/embeddings.
  
  For completion and chat_completion tasks - /v1/openai/v1/chat/completions.
- model_id string Required
  The name of the model to use for the inference task. Refer to the Llama downloading models documentation for different ways of getting a list of available models and downloading them. Service has been tested and confirmed to be working with the following models:
  
  For text_embedding task - all-MiniLM-L6-v2.
  
  For completion and chat_completion tasks - llama3.2:3b.
  External documentation
- max_input_tokens number
  
  For a text_embedding task, the maximum number of tokens per input before chunking occurs.
- similarity string
  
  For a text_embedding task, the similarity measure. One of cosine, dot_product, l2_norm.
  
  Values are cosine, dot_product, or l2_norm.
- rate_limit object
  
  This setting helps to minimize the number of rate limit errors returned from the Llama API. By default, the llama service sets the number of requests allowed per minute to 3000.
  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
  
  llama service: 3000
  
  mistral service: 240
  
  openai service and task type text_embedding: 3000
  
  openai service and task type completion: 500
  
  voyageai service: 2000
  
  watsonxai service: 120

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.
  
  separator_group string
  
  Only applicable to the recursive strategy and required when using it.
  
  Sets a predefined list of separators in the saved chunking settings based on the selected text type. Values can be markdown or plaintext.
  
  Using this parameter is an alternative to manually specifying a custom separators list.
  
  separators array[string]
  
  Only applicable to the recursive strategy and required when using it.
  
  A list of strings used as possible split points when chunking text.
  
  Each string can be a plain string or a regular expression (regex) pattern. The system tries each separator in order to split the text, starting from the first item in the list.
  
  After splitting, it attempts to recombine smaller pieces into larger chunks that stay within the max_chunk_size limit, to reduce the total number of chunks generated.
  
  strategy string
  
  The chunking strategy: sentence, word, none or recursive.
  
  If strategy is set to recursive, you must also specify:
  
  max_chunk_size
  
  either separators orseparator_group
  
  Learn more about different chunking strategies in the linked documentation.
  
  Default value is sentence.
  
  External documentation
- 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 string Required
  
  The task type
  
  Values are text_embedding, chat_completion, or completion.

PUT /_inference/{task_type}/{llama_inference_id}

PUT _inference/text_embedding/llama-text-embedding
{
  "service": "llama",
  "service_settings": {
    "url": "http://localhost:8321/v1/inference/embeddings",
    "dimensions": 384,
    "model_id": "all-MiniLM-L6-v2" 
  }
}

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="llama-text-embedding",
    inference_config={
        "service": "llama",
        "service_settings": {
            "url": "http://localhost:8321/v1/inference/embeddings",
            "dimensions": 384,
            "model_id": "all-MiniLM-L6-v2"
        }
    },
)

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "llama-text-embedding",
  inference_config: {
    service: "llama",
    service_settings: {
      url: "http://localhost:8321/v1/inference/embeddings",
      dimensions: 384,
      model_id: "all-MiniLM-L6-v2",
    },
  },
});

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "llama-text-embedding",
  body: {
    "service": "llama",
    "service_settings": {
      "url": "http://localhost:8321/v1/inference/embeddings",
      "dimensions": 384,
      "model_id": "all-MiniLM-L6-v2"
    }
  }
)

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "llama-text-embedding",
    "body" => [
        "service" => "llama",
        "service_settings" => [
            "url" => "http://localhost:8321/v1/inference/embeddings",
            "dimensions" => 384,
            "model_id" => "all-MiniLM-L6-v2",
        ],
    ],
]);

curl -X PUT -H "Authorization: ApiKey $ELASTIC_API_KEY" -H "Content-Type: application/json" -d '{"service":"llama","service_settings":{"url":"http://localhost:8321/v1/inference/embeddings","dimensions":384,"model_id":"all-MiniLM-L6-v2"}}' "$ELASTICSEARCH_URL/_inference/text_embedding/llama-text-embedding"

Request examples

Run `PUT _inference/text_embedding/llama-text-embedding` to create a Llama inference endpoint that performs a `text_embedding` task.

{
  "service": "llama",
  "service_settings": {
    "url": "http://localhost:8321/v1/inference/embeddings",
    "dimensions": 384,
    "model_id": "all-MiniLM-L6-v2" 
  }
}

Run `PUT _inference/completion/llama-completion` to create a Llama inference endpoint that performs a `completion` task.

{
  "service": "llama",
  "service_settings": {
    "url": "http://localhost:8321/v1/openai/v1/chat/completions",
    "model_id": "llama3.2:3b" 
  }
}

Run `PUT _inference/chat-completion/llama-chat-completion` to create a Llama inference endpoint that performs a `chat_completion` task.

{
  "service": "llama",
  "service_settings": {
    "url": "http://localhost:8321/v1/openai/v1/chat/completions",
    "model_id": "llama3.2:3b" 
  }
}