Perform inference API | Elasticsearch Guide [master]

You are looking at preliminary documentation for a future release. Not what you want? See the current release documentation.

› › ›

« Get inference API Create inference API »

Perform inference APIedit

This functionality is in technical preview and may be changed or removed in a future release. Elastic will work to fix any issues, but features in technical preview are not subject to the support SLA of official GA features.

Performs an inference task on an input text by using an inference endpoint.

The inference APIs enable you to use certain services, such as built-in machine learning models (ELSER, E5), models uploaded through Eland, Cohere, OpenAI, or Hugging Face. For built-in models and models uploaded though Eland, the inference APIs offer an alternative way to use and manage trained models. However, if you do not plan to use the inference APIs to use these models or if you want to use non-NLP models, use the Machine learning trained model APIs.

Requestedit

POST /_inference/<inference_id>

POST /_inference/<task_type>/<inference_id>

Prerequisitesedit

Requires the monitor_inference cluster privilege (the built-in inference_admin and inference_user roles grant this privilege)

Descriptionedit

The perform inference API enables you to use machine learning models to perform specific tasks on data that you provide as an input. The API returns a response with the results of the tasks. The inference endpoint you use can perform one specific task that has been defined when the endpoint was created with the Create inference API.

Path parametersedit

<inference_id>: (Required, string) The unique identifier of the inference endpoint.
<task_type>: (Optional, string) The type of inference task that the model performs.

Query parametersedit

timeout: (Optional, timeout) Controls the amount of time to wait for the inference to complete. Defaults to 30 seconds.

Request bodyedit

input: (Required, string or array of strings) The text on which you want to perform the inference task. input can be a single string or an array.

Inference endpoints for the completion task type currently only support a single string as input.
query: (Required, string) Only for rerank inference endpoints. The search query text.

Examplesedit

Completion exampleedit

The following example performs a completion on the example question.

POST _inference/completion/openai_chat_completions
{
  "input": "What is Elastic?"
}

The API returns the following response:

{
  "completion": [
    {
      "result": "Elastic is a company that provides a range of software solutions for search, logging, security, and analytics. Their flagship product is Elasticsearch, an open-source, distributed search engine that allows users to search, analyze, and visualize large volumes of data in real-time. Elastic also offers products such as Kibana, a data visualization tool, and Logstash, a log management and pipeline tool, as well as various other tools and solutions for data analysis and management."
    }
  ]
}

Rerank exampleedit

The following example performs reranking on the example input.

POST _inference/rerank/cohere_rerank
{
  "input": ["luke", "like", "leia", "chewy","r2d2", "star", "wars"],
  "query": "star wars main character"
}

The API returns the following response:

{
  "rerank": [
    {
      "index": "2",
      "relevance_score": "0.011597361",
      "text": "leia"
    },
    {
      "index": "0",
      "relevance_score": "0.006338922",
      "text": "luke"
    },
    {
      "index": "5",
      "relevance_score": "0.0016166499",
      "text": "star"
    },
    {
      "index": "4",
      "relevance_score": "0.0011695103",
      "text": "r2d2"
    },
    {
      "index": "1",
      "relevance_score": "5.614787E-4",
      "text": "like"
    },
    {
      "index": "6",
      "relevance_score": "3.7850367E-4",
      "text": "wars"
    },
    {
      "index": "3",
      "relevance_score": "1.2508839E-5",
      "text": "chewy"
    }
  ]
}

Sparse embedding exampleedit

The following example performs sparse embedding on the example sentence.

resp = client.inference.inference(
    task_type="sparse_embedding",
    inference_id="my-elser-model",
    body={
        "input": "The sky above the port was the color of television tuned to a dead channel."
    },
)
print(resp)

response = client.inference.inference(
  task_type: 'sparse_embedding',
  model_id: 'my-elser-model',
  body: {
    input: 'The sky above the port was the color of television tuned to a dead channel.'
  }
)
puts response

POST _inference/sparse_embedding/my-elser-model
{
  "input": "The sky above the port was the color of television tuned to a dead channel."
}

The API returns the following response:

{
  "sparse_embedding": [
    {
      "port": 2.1259406,
      "sky": 1.7073475,
      "color": 1.6922266,
      "dead": 1.6247464,
      "television": 1.3525393,
      "above": 1.2425821,
      "tuned": 1.1440028,
      "colors": 1.1218185,
      "tv": 1.0111054,
      "ports": 1.0067928,
      "poem": 1.0042328,
      "channel": 0.99471164,
      "tune": 0.96235967,
      "scene": 0.9020516,
      (...)
    },
    (...)
  ]
}

« Get inference API Create inference API »