Perform document extraction inference on the service

POST /_inference/document_extraction/{inference_id}

Auth

Extract the content of documents, such as PDFs or images of documents, into a textual format.

Required privileges

Cluster privileges monitor_inference

Path parameters

inference_id string required: The unique identifier for the inference endpoint.

Query parameters

timeout string · default: 120s: The amount of time to wait for the inference request to complete.

Request body

input union oneOf required

The documents to extract the content from. Either a content object or an array of content objects.

content object example:

		"input": {
  "content": {
    "type": "pdf",
    "format": "base64",
    "value": "data:application/pdf;base64,..."
  }
}
		
	

content object array example:

		"input": [
  {
    "content": {
      "type": "pdf",
      "format": "base64",
      "value": "data:application/pdf;base64,..."
    }
  },
  {
    "content": {
      "type": "image",
      "format": "url",
      "value": "https://example.com/scanned-page.png"
    }
  }
]
		
	

object or object[]

content object required: The document to extract the content from.

task_settings object

Task settings for the individual inference request. These settings are specific to the task type you specified and override the task settings specified when initializing the service.

output_format enum: The output format of the extracted content. Only markdown is supported.; Values: markdown
parameters map string to object: A free-form object of extraction options that is forwarded to the Elastic Inference Service as-is. The accepted parameters are defined by the Elastic Inference Service.

Response

application/json

document_extraction object[] required

Examples

Request Console 1 / 6 languages

Run POST _inference/document_extraction/my-document-extraction-endpoint to extract the content of the example PDF document

Console Kibana Dev Tools

POST _inference/document_extraction/my-document-extraction-endpoint
{
  "input": [
    {
      "content": {
        "type": "pdf",
        "format": "base64",
        "value": "data:application/pdf;base64,..."
      }
    }
  ]
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.documentExtraction({
  inference_id: "my-document-extraction-endpoint",
  input: [
    {
      content: {
        type: "pdf",
        format: "base64",
        value: "data:application/pdf;base64,...",
      },
    },
  ],
});

Python Elasticsearch Python Client

resp = client.inference.document_extraction(
    inference_id="my-document-extraction-endpoint",
    input=[
        {
            "content": {
                "type": "pdf",
                "format": "base64",
                "value": "data:application/pdf;base64,..."
            }
        }
    ],
)

curl Shell

curl -X POST "$ELASTICSEARCH_URL/_inference/document_extraction/my-document-extraction-endpoint" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": [
      {
        "content": {
          "type": "pdf",
          "format": "base64",
          "value": "data:application/pdf;base64,..."
        }
      }
    ]
  }'

PHP Elasticsearch PHP Client

$resp = $client->inference()->documentExtraction([
    "inference_id" => "my-document-extraction-endpoint",
    "body" => [
        "input" => array(
            [
                "content" => [
                    "type" => "pdf",
                    "format" => "base64",
                    "value" => "data:application/pdf;base64,...",
                ],
            ],
        ),
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.document_extraction(
  inference_id: "my-document-extraction-endpoint",
  body: {
    "input": [
      {
        "content": {
          "type": "pdf",
          "format": "base64",
          "value": "data:application/pdf;base64,..."
        }
      }
    ]
  }
)

Response

An abbreviated response from POST _inference/document_extraction/my-document-extraction-endpoint.

{
  "document_extraction": [
    {
      "content": "# Annual Report 2025\n\n...",
      "format": "markdown",
      "metadata": {
        "title": "Annual Report 2025"
      }
    }
  ]
}

Request Console 1 / 6 languages

Run POST _inference/document_extraction/my-document-extraction-endpoint to extract the content of an image of a document referenced by URL as markdown.

Console Kibana Dev Tools

POST _inference/document_extraction/my-document-extraction-endpoint
{
  "input": {
    "content": {
      "type": "image",
      "format": "url",
      "value": "https://example.com/scanned-page.png"
    }
  },
  "task_settings": {
    "output_format": "markdown"
  }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.documentExtraction({
  inference_id: "my-document-extraction-endpoint",
  input: {
    content: {
      type: "image",
      format: "url",
      value: "https://example.com/scanned-page.png",
    },
  },
  task_settings: {
    output_format: "markdown",
  },
});

Python Elasticsearch Python Client

resp = client.inference.document_extraction(
    inference_id="my-document-extraction-endpoint",
    input={
        "content": {
            "type": "image",
            "format": "url",
            "value": "https://example.com/scanned-page.png"
        }
    },
    task_settings={
        "output_format": "markdown"
    },
)

curl Shell

curl -X POST "$ELASTICSEARCH_URL/_inference/document_extraction/my-document-extraction-endpoint" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "content": {
        "type": "image",
        "format": "url",
        "value": "https://example.com/scanned-page.png"
      }
    },
    "task_settings": {
      "output_format": "markdown"
    }
  }'

PHP Elasticsearch PHP Client

$resp = $client->inference()->documentExtraction([
    "inference_id" => "my-document-extraction-endpoint",
    "body" => [
        "input" => [
            "content" => [
                "type" => "image",
                "format" => "url",
                "value" => "https://example.com/scanned-page.png",
            ],
        ],
        "task_settings" => [
            "output_format" => "markdown",
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.document_extraction(
  inference_id: "my-document-extraction-endpoint",
  body: {
    "input": {
      "content": {
        "type": "image",
        "format": "url",
        "value": "https://example.com/scanned-page.png"
      }
    },
    "task_settings": {
      "output_format": "markdown"
    }
  }
)

Response

No example