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

• EML

• DOC, DOCX

• JPEG, JPG

• HTM, HTML

• TEXT, TXT

• TIF, TIFF

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 feature name 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 (feature name 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?']]
  

• An array of strings that contain the feature name and the information to be extracted, separated with a colon (“:”), for example:

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

Note

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']

Returns¶

A JSON object containing the extracted information.

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 Required privileges.

Usage notes¶

• 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.

• The maximum number of features that can be extracted is 100.

• The maximum output length is 512 tokens per question.

• To extract a list, add List: at the beginning of each question. For example:

  [['languages', 'List: What languages are supported for AI_EXTRACT?']]
  

• You can’t use a colon (“:”) inside of a feature name when using the response format that uses a colon to separate the feature name and the information to be extracted, for example:

  ['location: Where does the employee live?', 'name:employee: What is the first name of the employee?']
  

• Confidence scores are not supported.

Examples¶

The following example extracts information from the input text:

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?'}
);

The following example extracts and parses information from the input text:

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?"}')
);

The following example extracts information from the document.pdf file:

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?']]
);

The following example extracts information from all files on a stage:

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);

Legal notices¶

Refer to Snowflake AI and ML for legal notices.