Extract Metadata

curl --request POST \
  --url https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "document_id": "<string>",
  "llm_model_prefix": "gemini-2.5-pro",
  "attachment_filters": [
    {
      "name": "<string>",
      "id": "<string>",
      "mime_type": "<string>"
    }
  ],
  "sources": [
    {
      "type": "description"
    }
  ],
  "instruction": "<string>",
  "provide_location": false,
  "fields": [
    {
      "name": "<string>",
      "id": "<string>",
      "instruction": "<string>",
      "barcode": false,
      "integer_decimal_handling": "error",
      "table_search": {
        "dataset_id": "<string>",
        "input_columns": [
          "<string>"
        ],
        "output_columns": [
          {
            "name": "<string>",
            "id_column": "<string>"
          }
        ]
      }
    }
  ],
  "example_documents": [
    "<string>"
  ],
  "registries": [
    {
      "name": "<string>",
      "library_id": "<string>",
      "document_class_id": "<string>",
      "field_mappings": [
        {
          "extracted_field": "<string>",
          "registry_field": "<string>",
          "key_field": false,
          "optional_key": false,
          "similarity_threshold": 1
        }
      ],
      "match_mode": "ALL"
    }
  ]
}
'

import requests

url = "https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract"

payload = {
    "document_id": "<string>",
    "llm_model_prefix": "gemini-2.5-pro",
    "attachment_filters": [
        {
            "name": "<string>",
            "id": "<string>",
            "mime_type": "<string>"
        }
    ],
    "sources": [{ "type": "description" }],
    "instruction": "<string>",
    "provide_location": False,
    "fields": [
        {
            "name": "<string>",
            "id": "<string>",
            "instruction": "<string>",
            "barcode": False,
            "integer_decimal_handling": "error",
            "table_search": {
                "dataset_id": "<string>",
                "input_columns": ["<string>"],
                "output_columns": [
                    {
                        "name": "<string>",
                        "id_column": "<string>"
                    }
                ]
            }
        }
    ],
    "example_documents": ["<string>"],
    "registries": [
        {
            "name": "<string>",
            "library_id": "<string>",
            "document_class_id": "<string>",
            "field_mappings": [
                {
                    "extracted_field": "<string>",
                    "registry_field": "<string>",
                    "key_field": False,
                    "optional_key": False,
                    "similarity_threshold": 1
                }
            ],
            "match_mode": "ALL"
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    document_id: '<string>',
    llm_model_prefix: 'gemini-2.5-pro',
    attachment_filters: [{name: '<string>', id: '<string>', mime_type: '<string>'}],
    sources: [{type: 'description'}],
    instruction: '<string>',
    provide_location: false,
    fields: [
      {
        name: '<string>',
        id: '<string>',
        instruction: '<string>',
        barcode: false,
        integer_decimal_handling: 'error',
        table_search: {
          dataset_id: '<string>',
          input_columns: ['<string>'],
          output_columns: [{name: '<string>', id_column: '<string>'}]
        }
      }
    ],
    example_documents: ['<string>'],
    registries: [
      {
        name: '<string>',
        library_id: '<string>',
        document_class_id: '<string>',
        field_mappings: [
          {
            extracted_field: '<string>',
            registry_field: '<string>',
            key_field: false,
            optional_key: false,
            similarity_threshold: 1
          }
        ],
        match_mode: 'ALL'
      }
    ]
  })
};

fetch('https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'document_id' => '<string>',
    'llm_model_prefix' => 'gemini-2.5-pro',
    'attachment_filters' => [
        [
                'name' => '<string>',
                'id' => '<string>',
                'mime_type' => '<string>'
        ]
    ],
    'sources' => [
        [
                'type' => 'description'
        ]
    ],
    'instruction' => '<string>',
    'provide_location' => false,
    'fields' => [
        [
                'name' => '<string>',
                'id' => '<string>',
                'instruction' => '<string>',
                'barcode' => false,
                'integer_decimal_handling' => 'error',
                'table_search' => [
                                'dataset_id' => '<string>',
                                'input_columns' => [
                                                                '<string>'
                                ],
                                'output_columns' => [
                                                                [
                                                                                                                                'name' => '<string>',
                                                                                                                                'id_column' => '<string>'
                                                                ]
                                ]
                ]
        ]
    ],
    'example_documents' => [
        '<string>'
    ],
    'registries' => [
        [
                'name' => '<string>',
                'library_id' => '<string>',
                'document_class_id' => '<string>',
                'field_mappings' => [
                                [
                                                                'extracted_field' => '<string>',
                                                                'registry_field' => '<string>',
                                                                'key_field' => false,
                                                                'optional_key' => false,
                                                                'similarity_threshold' => 1
                                ]
                ],
                'match_mode' => 'ALL'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract"

	payload := strings.NewReader("{\n  \"document_id\": \"<string>\",\n  \"llm_model_prefix\": \"gemini-2.5-pro\",\n  \"attachment_filters\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"mime_type\": \"<string>\"\n    }\n  ],\n  \"sources\": [\n    {\n      \"type\": \"description\"\n    }\n  ],\n  \"instruction\": \"<string>\",\n  \"provide_location\": false,\n  \"fields\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"instruction\": \"<string>\",\n      \"barcode\": false,\n      \"integer_decimal_handling\": \"error\",\n      \"table_search\": {\n        \"dataset_id\": \"<string>\",\n        \"input_columns\": [\n          \"<string>\"\n        ],\n        \"output_columns\": [\n          {\n            \"name\": \"<string>\",\n            \"id_column\": \"<string>\"\n          }\n        ]\n      }\n    }\n  ],\n  \"example_documents\": [\n    \"<string>\"\n  ],\n  \"registries\": [\n    {\n      \"name\": \"<string>\",\n      \"library_id\": \"<string>\",\n      \"document_class_id\": \"<string>\",\n      \"field_mappings\": [\n        {\n          \"extracted_field\": \"<string>\",\n          \"registry_field\": \"<string>\",\n          \"key_field\": false,\n          \"optional_key\": false,\n          \"similarity_threshold\": 1\n        }\n      ],\n      \"match_mode\": \"ALL\"\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"document_id\": \"<string>\",\n  \"llm_model_prefix\": \"gemini-2.5-pro\",\n  \"attachment_filters\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"mime_type\": \"<string>\"\n    }\n  ],\n  \"sources\": [\n    {\n      \"type\": \"description\"\n    }\n  ],\n  \"instruction\": \"<string>\",\n  \"provide_location\": false,\n  \"fields\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"instruction\": \"<string>\",\n      \"barcode\": false,\n      \"integer_decimal_handling\": \"error\",\n      \"table_search\": {\n        \"dataset_id\": \"<string>\",\n        \"input_columns\": [\n          \"<string>\"\n        ],\n        \"output_columns\": [\n          {\n            \"name\": \"<string>\",\n            \"id_column\": \"<string>\"\n          }\n        ]\n      }\n    }\n  ],\n  \"example_documents\": [\n    \"<string>\"\n  ],\n  \"registries\": [\n    {\n      \"name\": \"<string>\",\n      \"library_id\": \"<string>\",\n      \"document_class_id\": \"<string>\",\n      \"field_mappings\": [\n        {\n          \"extracted_field\": \"<string>\",\n          \"registry_field\": \"<string>\",\n          \"key_field\": false,\n          \"optional_key\": false,\n          \"similarity_threshold\": 1\n        }\n      ],\n      \"match_mode\": \"ALL\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"document_id\": \"<string>\",\n  \"llm_model_prefix\": \"gemini-2.5-pro\",\n  \"attachment_filters\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"mime_type\": \"<string>\"\n    }\n  ],\n  \"sources\": [\n    {\n      \"type\": \"description\"\n    }\n  ],\n  \"instruction\": \"<string>\",\n  \"provide_location\": false,\n  \"fields\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"instruction\": \"<string>\",\n      \"barcode\": false,\n      \"integer_decimal_handling\": \"error\",\n      \"table_search\": {\n        \"dataset_id\": \"<string>\",\n        \"input_columns\": [\n          \"<string>\"\n        ],\n        \"output_columns\": [\n          {\n            \"name\": \"<string>\",\n            \"id_column\": \"<string>\"\n          }\n        ]\n      }\n    }\n  ],\n  \"example_documents\": [\n    \"<string>\"\n  ],\n  \"registries\": [\n    {\n      \"name\": \"<string>\",\n      \"library_id\": \"<string>\",\n      \"document_class_id\": \"<string>\",\n      \"field_mappings\": [\n        {\n          \"extracted_field\": \"<string>\",\n          \"registry_field\": \"<string>\",\n          \"key_field\": false,\n          \"optional_key\": false,\n          \"similarity_threshold\": 1\n        }\n      ],\n      \"match_mode\": \"ALL\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "values": [
    {
      "id": "<string>",
      "name": "<string>",
      "type": "STRING",
      "quote": "<string>",
      "bounding_boxes": [
        {
          "attachment_id": "<string>",
          "page": 2,
          "x": 0.5,
          "y": 0.5,
          "width": 0,
          "height": 0
        }
      ],
      "confidence": "low",
      "value": [
        "<string>"
      ],
      "category_value": [
        {
          "hierarchy": [
            {
              "id": "<string>",
              "name": "<string>"
            }
          ]
        }
      ],
      "reference_catalog_value": [
        {
          "id": "<string>",
          "name": "<string>"
        }
      ],
      "person_value": [
        {
          "email": "<string>",
          "name": "<string>"
        }
      ],
      "table_value": [
        {
          "columns": {}
        }
      ],
      "error": "<string>",
      "note": "<string>"
    }
  ],
  "registry_matches": [
    {
      "name": "<string>",
      "document_id": "<string>",
      "key_matches": [
        {
          "extracted_field_name": "<string>",
          "extracted_field_id": "<string>",
          "extracted_value": [
            "<string>"
          ],
          "registry_value": [
            "<string>"
          ],
          "similarity": 123
        }
      ],
      "multiple_matches": false
    }
  ]
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

POST

assistant

api

tenants

{tenant}

metadata:extract

Extract Metadata

curl --request POST \
  --url https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "document_id": "<string>",
  "llm_model_prefix": "gemini-2.5-pro",
  "attachment_filters": [
    {
      "name": "<string>",
      "id": "<string>",
      "mime_type": "<string>"
    }
  ],
  "sources": [
    {
      "type": "description"
    }
  ],
  "instruction": "<string>",
  "provide_location": false,
  "fields": [
    {
      "name": "<string>",
      "id": "<string>",
      "instruction": "<string>",
      "barcode": false,
      "integer_decimal_handling": "error",
      "table_search": {
        "dataset_id": "<string>",
        "input_columns": [
          "<string>"
        ],
        "output_columns": [
          {
            "name": "<string>",
            "id_column": "<string>"
          }
        ]
      }
    }
  ],
  "example_documents": [
    "<string>"
  ],
  "registries": [
    {
      "name": "<string>",
      "library_id": "<string>",
      "document_class_id": "<string>",
      "field_mappings": [
        {
          "extracted_field": "<string>",
          "registry_field": "<string>",
          "key_field": false,
          "optional_key": false,
          "similarity_threshold": 1
        }
      ],
      "match_mode": "ALL"
    }
  ]
}
'

import requests

url = "https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract"

payload = {
    "document_id": "<string>",
    "llm_model_prefix": "gemini-2.5-pro",
    "attachment_filters": [
        {
            "name": "<string>",
            "id": "<string>",
            "mime_type": "<string>"
        }
    ],
    "sources": [{ "type": "description" }],
    "instruction": "<string>",
    "provide_location": False,
    "fields": [
        {
            "name": "<string>",
            "id": "<string>",
            "instruction": "<string>",
            "barcode": False,
            "integer_decimal_handling": "error",
            "table_search": {
                "dataset_id": "<string>",
                "input_columns": ["<string>"],
                "output_columns": [
                    {
                        "name": "<string>",
                        "id_column": "<string>"
                    }
                ]
            }
        }
    ],
    "example_documents": ["<string>"],
    "registries": [
        {
            "name": "<string>",
            "library_id": "<string>",
            "document_class_id": "<string>",
            "field_mappings": [
                {
                    "extracted_field": "<string>",
                    "registry_field": "<string>",
                    "key_field": False,
                    "optional_key": False,
                    "similarity_threshold": 1
                }
            ],
            "match_mode": "ALL"
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    document_id: '<string>',
    llm_model_prefix: 'gemini-2.5-pro',
    attachment_filters: [{name: '<string>', id: '<string>', mime_type: '<string>'}],
    sources: [{type: 'description'}],
    instruction: '<string>',
    provide_location: false,
    fields: [
      {
        name: '<string>',
        id: '<string>',
        instruction: '<string>',
        barcode: false,
        integer_decimal_handling: 'error',
        table_search: {
          dataset_id: '<string>',
          input_columns: ['<string>'],
          output_columns: [{name: '<string>', id_column: '<string>'}]
        }
      }
    ],
    example_documents: ['<string>'],
    registries: [
      {
        name: '<string>',
        library_id: '<string>',
        document_class_id: '<string>',
        field_mappings: [
          {
            extracted_field: '<string>',
            registry_field: '<string>',
            key_field: false,
            optional_key: false,
            similarity_threshold: 1
          }
        ],
        match_mode: 'ALL'
      }
    ]
  })
};

fetch('https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'document_id' => '<string>',
    'llm_model_prefix' => 'gemini-2.5-pro',
    'attachment_filters' => [
        [
                'name' => '<string>',
                'id' => '<string>',
                'mime_type' => '<string>'
        ]
    ],
    'sources' => [
        [
                'type' => 'description'
        ]
    ],
    'instruction' => '<string>',
    'provide_location' => false,
    'fields' => [
        [
                'name' => '<string>',
                'id' => '<string>',
                'instruction' => '<string>',
                'barcode' => false,
                'integer_decimal_handling' => 'error',
                'table_search' => [
                                'dataset_id' => '<string>',
                                'input_columns' => [
                                                                '<string>'
                                ],
                                'output_columns' => [
                                                                [
                                                                                                                                'name' => '<string>',
                                                                                                                                'id_column' => '<string>'
                                                                ]
                                ]
                ]
        ]
    ],
    'example_documents' => [
        '<string>'
    ],
    'registries' => [
        [
                'name' => '<string>',
                'library_id' => '<string>',
                'document_class_id' => '<string>',
                'field_mappings' => [
                                [
                                                                'extracted_field' => '<string>',
                                                                'registry_field' => '<string>',
                                                                'key_field' => false,
                                                                'optional_key' => false,
                                                                'similarity_threshold' => 1
                                ]
                ],
                'match_mode' => 'ALL'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract"

	payload := strings.NewReader("{\n  \"document_id\": \"<string>\",\n  \"llm_model_prefix\": \"gemini-2.5-pro\",\n  \"attachment_filters\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"mime_type\": \"<string>\"\n    }\n  ],\n  \"sources\": [\n    {\n      \"type\": \"description\"\n    }\n  ],\n  \"instruction\": \"<string>\",\n  \"provide_location\": false,\n  \"fields\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"instruction\": \"<string>\",\n      \"barcode\": false,\n      \"integer_decimal_handling\": \"error\",\n      \"table_search\": {\n        \"dataset_id\": \"<string>\",\n        \"input_columns\": [\n          \"<string>\"\n        ],\n        \"output_columns\": [\n          {\n            \"name\": \"<string>\",\n            \"id_column\": \"<string>\"\n          }\n        ]\n      }\n    }\n  ],\n  \"example_documents\": [\n    \"<string>\"\n  ],\n  \"registries\": [\n    {\n      \"name\": \"<string>\",\n      \"library_id\": \"<string>\",\n      \"document_class_id\": \"<string>\",\n      \"field_mappings\": [\n        {\n          \"extracted_field\": \"<string>\",\n          \"registry_field\": \"<string>\",\n          \"key_field\": false,\n          \"optional_key\": false,\n          \"similarity_threshold\": 1\n        }\n      ],\n      \"match_mode\": \"ALL\"\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"document_id\": \"<string>\",\n  \"llm_model_prefix\": \"gemini-2.5-pro\",\n  \"attachment_filters\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"mime_type\": \"<string>\"\n    }\n  ],\n  \"sources\": [\n    {\n      \"type\": \"description\"\n    }\n  ],\n  \"instruction\": \"<string>\",\n  \"provide_location\": false,\n  \"fields\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"instruction\": \"<string>\",\n      \"barcode\": false,\n      \"integer_decimal_handling\": \"error\",\n      \"table_search\": {\n        \"dataset_id\": \"<string>\",\n        \"input_columns\": [\n          \"<string>\"\n        ],\n        \"output_columns\": [\n          {\n            \"name\": \"<string>\",\n            \"id_column\": \"<string>\"\n          }\n        ]\n      }\n    }\n  ],\n  \"example_documents\": [\n    \"<string>\"\n  ],\n  \"registries\": [\n    {\n      \"name\": \"<string>\",\n      \"library_id\": \"<string>\",\n      \"document_class_id\": \"<string>\",\n      \"field_mappings\": [\n        {\n          \"extracted_field\": \"<string>\",\n          \"registry_field\": \"<string>\",\n          \"key_field\": false,\n          \"optional_key\": false,\n          \"similarity_threshold\": 1\n        }\n      ],\n      \"match_mode\": \"ALL\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://document-assistant.us.aodocs.app/assistant/api/v1/tenants/{tenant}/metadata:extract")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"document_id\": \"<string>\",\n  \"llm_model_prefix\": \"gemini-2.5-pro\",\n  \"attachment_filters\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"mime_type\": \"<string>\"\n    }\n  ],\n  \"sources\": [\n    {\n      \"type\": \"description\"\n    }\n  ],\n  \"instruction\": \"<string>\",\n  \"provide_location\": false,\n  \"fields\": [\n    {\n      \"name\": \"<string>\",\n      \"id\": \"<string>\",\n      \"instruction\": \"<string>\",\n      \"barcode\": false,\n      \"integer_decimal_handling\": \"error\",\n      \"table_search\": {\n        \"dataset_id\": \"<string>\",\n        \"input_columns\": [\n          \"<string>\"\n        ],\n        \"output_columns\": [\n          {\n            \"name\": \"<string>\",\n            \"id_column\": \"<string>\"\n          }\n        ]\n      }\n    }\n  ],\n  \"example_documents\": [\n    \"<string>\"\n  ],\n  \"registries\": [\n    {\n      \"name\": \"<string>\",\n      \"library_id\": \"<string>\",\n      \"document_class_id\": \"<string>\",\n      \"field_mappings\": [\n        {\n          \"extracted_field\": \"<string>\",\n          \"registry_field\": \"<string>\",\n          \"key_field\": false,\n          \"optional_key\": false,\n          \"similarity_threshold\": 1\n        }\n      ],\n      \"match_mode\": \"ALL\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "values": [
    {
      "id": "<string>",
      "name": "<string>",
      "type": "STRING",
      "quote": "<string>",
      "bounding_boxes": [
        {
          "attachment_id": "<string>",
          "page": 2,
          "x": 0.5,
          "y": 0.5,
          "width": 0,
          "height": 0
        }
      ],
      "confidence": "low",
      "value": [
        "<string>"
      ],
      "category_value": [
        {
          "hierarchy": [
            {
              "id": "<string>",
              "name": "<string>"
            }
          ]
        }
      ],
      "reference_catalog_value": [
        {
          "id": "<string>",
          "name": "<string>"
        }
      ],
      "person_value": [
        {
          "email": "<string>",
          "name": "<string>"
        }
      ],
      "table_value": [
        {
          "columns": {}
        }
      ],
      "error": "<string>",
      "note": "<string>"
    }
  ],
  "registry_matches": [
    {
      "name": "<string>",
      "document_id": "<string>",
      "key_matches": [
        {
          "extracted_field_name": "<string>",
          "extracted_field_id": "<string>",
          "extracted_value": [
            "<string>"
          ],
          "registry_value": [
            "<string>"
          ],
          "similarity": 123
        }
      ],
      "multiple_matches": false
    }
  ]
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

tenant

string | null

required

The domain of the customer

Example:

"example.com"

Body

application/json

document_id

string

required

The document ID of the files

llm_provider

enum<string> | null

The LLM provider to use. If not provided, the default provider will be used.

Available options:

OpenAI,

Google,

Altirnao,

MistralAI,

Anthropic

llm_model_prefix

string | null

The prefix of the LLM model name to use. If not provided, the default model will be used.

Example:

"gemini-2.5-pro"

attachment_filters

AttachmentFilter · object[] | null

deprecated

The attachments to extract metadata from. If provided then only the attachments matching one of the rules are used. If not provided then all attachments will be extracted. Deprecated: use sources with an attachments entry instead.

Show child attributes

sources

(DescriptionExtractionSource · object | AttachmentsExtractionSource · object)[] | null

The ordered document content sources to extract metadata from. If omitted, attachment-only extraction is used for backward compatibility. Description sources are opt-in.

Minimum array length: 1

DescriptionExtractionSource
AttachmentsExtractionSource

Show child attributes

instruction

string | null

The prompt extension for the metadata extraction

provide_location

boolean

default:false

Whether to calculate and return page locations (bounding boxes) for the quote supporting each extracted field. Quotes are matched against textual and scanned PDF attachments plus PNG, JPEG, and WebP images without changing extracted values. Unsupported attachment types and quotes that do not occur verbatim after normalization do not produce boxes.

fields

Specification which metadata to extract and how. If not provided, all fields will be extracted.

Show child attributes

example_documents

string[] | null

A list of example documents to use for metadata extraction. If provided, the LLM will use these documents to better understand the context and provide more accurate extractions.

registries

Registry · object[] | null

A list of metadata registries to use for metadata extraction. If provided, the LLM will use these registries to better understand the context and provide more accurate extractions.

Show child attributes

Response

Successful Response

values

ExtendedExtractedMetadata · object[]

required

Show child attributes

registry_matches

RegistryMatch · object[] | null

Information about the matched registry entries and the strength of the match

Show child attributes