AI_EXTRACT¶

Syntax¶

Extract information from an input string:

AI_EXTRACT( <text>, <responseFormat> )

AI_EXTRACT( text => <text>,
            responseFormat => <responseFormat> )

Extract information from a file:

AI_EXTRACT( <file>, <responseFormat> )

AI_EXTRACT( file => <file>,
            responseFormat => <responseFormat> )

Arguments¶

text

An input string for extraction.

file

A FILE for extraction.

Supported file formats:

• PDF

• PNG

• PPTX, PPT

• EML

• DOC, DOCX

• JPEG, JPG

• HTM, HTML

• TEXT, TXT

• TIF, TIFF

• BMP, GIF, WEBP

• MD

The files must be less than 100 MB in size.

responseFormat

Information to be extracted in one of the following response formats:

• Simple object schema that maps the label and information to be extracted; for example:

  {'name': 'What is the last name of the employee?', 'address': 'What is the address of the employee?'}
  

• An array of strings that contain the information to be extracted, for example:

  ['What is the last name of the employee?', 'What is the address of the employee?']
  

• An array of arrays that contain two strings (label and the information to be extracted); for example:

  [['name', 'What is the last name of the employee?'], ['address', 'What is the address of the employee?']]
  

• A JSON schema that defines the structure of the extracted information. Supports entity and table extraction. For example:

  {
    'schema': {
      'type': 'object',
      'properties': {
        'income_table': {
          'description': 'Income for FY2026Q2',
          'type': 'object',
          'properties': {
            'month': {
              'type': 'array'
            },
            'income': {
              'type': 'array'
            }
          }
        },
        'title': {
          'description': 'What is the title of the document?',
          'type': 'string'
        },
        'employees': {
          'description': 'What are the names of employees?',
          'type': 'array'
        }
      }
    }
  }
  

  Note

  • You can’t combine the JSON schema format with other response formats. If responseFormat contains the schema key, you must define all questions within the JSON schema. Additional keys are not supported.

  • The model only accepts certain shapes of JSON schema. Top level type must always be an object, which contains independently extracted sub-objects. Sub-objects may be a table (object of lists of strings representing columns), a list of strings, or a string.

    String is currently the only supported scalar type.

  • The description field is optional.

    Use the description field to provide context to the model; for example, to help the model localize the right table in a document.

Returns¶

A JSON object containing the extracted information.

Example of an output that includes array, table, and single value extraction:

{
  "error": null,
  "response": {
    "employees": [
      "Smith",
      "Johnson",
      "Doe"
    ],
    "income_table": {
      "income": ["$120 678","$130 123","$150 998"],
      "month": ["February", "March", "April"]
    },
    "title": "Financial report"
  }
}

Access control requirements¶

Users must use a role that has been granted the SNOWFLAKE.CORTEX_USER database role. For information about granting this privilege, see Cortex LLM privileges.

Usage notes¶

• You can’t use both text and file parameters simultaneously in the same function call.

• You can either ask questions in natural language or describe information to be extracted (such as city, street, ZIP code); for example:

  ['address': 'City, street, ZIP', 'name': 'First and last name']
  

• The following languages are supported:

  • Arabic

  • Bengali

  • Burmese

  • Cebuano

  • Chinese

  • Czech

  • Dutch

  • English

  • French

  • German

  • Hebrew

  • Hindi

  • Indonesian

  • Italian

  • Japanese

  • Khmer

  • Korean

  • Lao

  • Malay

  • Persian

  • Polish

  • Portuguese

  • Russian

  • Spanish

  • Tagalog

  • Thai

  • Turkish

  • Urdu

  • Vietnamese

• The documents must be no more than 125 pages long.

• In a single AI_EXTRACT call, you can ask a maximum of 100 questions for entity extraction, and a maximum of 10 questions for table extraction.

  A table extraction question is equal to 10 entity extraction questions. For example, you can ask 4 table extraction questions and 60 entity extraction questions in a single AI_EXTRACT call.

• The maximum output length for entity extraction is 512 tokens per question. For table extraction, the model returns answers that are a maximum of 4096 tokens.

• Client-side encrypted stages are not supported.

• Confidence scores are not supported.

Examples¶

SELECT AI_EXTRACT(
 text => 'John Smith lives in San Francisco and works for Snowflake',
 responseFormat => {'name': 'What is the first name of the employee?', 'city': 'What is the address of the employee?'}
);

SELECT AI_EXTRACT(
 text => 'John Smith lives in San Francisco and works for Snowflake',
 responseFormat => PARSE_JSON('{"name": "What is the first name of the employee?", "address": "What is the address of the employee?"}')
);

SELECT AI_EXTRACT(
  file => TO_FILE('@db.schema.files','document.pdf'),
  responseFormat => [['name', 'What is the first name of the employee?'], ['city', 'Where does the employee live?']]
);

SELECT AI_EXTRACT(
  file => TO_FILE('@db.schema.files', relative_path),
  responseFormat => [
    'What is this document?',
    'How would you classify this document?'
  ]
) FROM DIRECTORY (@db.schema.files);

SELECT AI_EXTRACT(
  file => TO_FILE('@db.schema.files', 'report.pdf'),
  responseFormat => {
    'schema': {
      'type': 'object',
      'properties': {
        'income_table': {
          'description': 'Income for FY2026Q2',
          'type': 'object',
          'properties': {
            'month': {
              'type': 'array'
            },
            'income': {
              'type': 'array'
            }
          }
        }
      }
    }
  }
);

SELECT AI_EXTRACT(
  file => TO_FILE('@db.schema.files', 'report.pdf'),
  responseFormat => {
    'schema': {
      'type': 'object',
      'properties': {
        'income_table': {
          'description': 'Income for FY2026Q2',
          'type': 'object',
          'properties': {
            'month': {
              'type': 'array'
            },
            'income': {
              'type': 'array'
            }
          }
        },
        'title': {
          'description': 'What is the title of document?',
          'type': 'string'
        },
        'employees': {
          'description': 'What are the surnames of employees?',
          'type': 'array'
        }
      }
    }
  }
);

Regional availability¶

See Regional availability.

Legal notices¶

Refer to Snowflake AI and ML for legal notices.