Oracle Cloud Infrastructure Documentation

Pretrained Document AI Models

Document Understanding provides pretrained models that allow you to organize and extract text and structure from business documents.

Pretrained models let you use AI with no data science experience. Simply provide a file to the Document Understanding service and, without having to create your own model, get back information about your document.

Use Cases

Pretrained models let you automate back-office tasks, and process documents more accurately and quickly.

Intelligent search
Enrich document files with metadata, including document type and key fields, for easier retrieval.
Invoice automation
Extract data from invoices, such as the amounts, dates, and payment terms to automatically process the invoices for payment. This data can save time and effort, and can improve the accuracy and reliability of the invoicing process.
Document analysis
Extract data from documents like invoices or insurance claims to identify trends or identify opportunities for cost savings.
Human resources management
Extract employee record data, such as names, addresses, and job titles, to populate a human resources management system. This data makes it easier to store and manage employee information, and can reduce the risk of errors.

Supported Formats

Document Understanding supports several document formats.

You can upload documents from a local file or Oracle Cloud Infrastructure Object Storage. They can be in the following formats:
  • JPEG
  • PDF
  • PNG
  • TIFF

Pretrained Models

There are five types of pretrained model with Document Understanding.

The pretrained models are:

Optical Character Recognition (OCR)

Document Understanding can detect and recognize text in a document. OCR draws bounding boxes around the printed or hand-written text that it locates in a document, and digitizes the text.

If you have a PDF with text, Document Understanding locates the text in that document and extracts the text. It then provides bounding boxes for the identified text. Text Detection can be used with Document AI or Image Analysis models.

Document Understanding provides a confidence score for each text grouping. The confidence score is a decimal number. Scores closer to 1 indicate a higher confidence in the extracted text, while lower scores indicate lower confidence score. The range of the confidence score for each label is from 0 to 1.

Supported features are:
  • Word extraction
  • Text line extraction
  • Confidence score
  • Bounding polygons
  • Single request
  • Batch request
Limitations are:
  • OCR is limited to English.
OCR Example
An example of OCR use in Document Understanding.
Input document
Figure 1. OCR Input
Receipt from a fictitious cafe, including two line items, tax, subtotal and total amounts.
API Request: 
{ "analyzeDocumentDetails":
                { "compartmentId": "",
                "document": { "namespaceName": "",
                "bucketName": "",
                "objectName": "",
                "source": "OBJECT_STORAGE" },
                "features":
                [ { "featureType": "TEXT_DETECTION" },
                { "featureType": "LANGUAGE_CLASSIFICATION",
                "maxResults": 5 } ]
                } 
                }
.
Output:
Figure 2. OCR Output
The receipt with all the fields identifed
API Response: 
{ "documentMetadata":
              { "pageCount": 1,
              "mimeType": "image/jpeg" },
              "pages":
              [ { "pageNumber": 1,
              "dimensions":
              { "width": 361, 
              "height": 600,
              "unit": "PIXEL" },
              "detectedLanguages":
              [ { "languageCode": "ENG",
              "confidence": 0.9999994 },
              { "languageCode": "ARA", 
              "confidence": 4.7619238e-7 },
              { "languageCode": "NLD",
              "confidence": 7.2325456e-8 },
              { "languageCode": "CHI_SIM",
              "confidence": 3.0645523e-8 },
              { "languageCode": "ITA",
              "confidence": 8.6900076e-10 } ],
              "words":
              [ { "text": "Example",
              "confidence": 0.99908227,
              "boundingPolygon":
              { "normalizedVertices": 
              [ { "x": 0.0664819944598338, 
              "y": 0.011666666666666667 },
              { "x": 0.22160664819944598,
              "y": 0.011666666666666667 },
              { "x": 0.22160664819944598,
              "y": 0.035 },
              { "x": 0.0664819944598338,
              "y": 0.035 } ]
              } ... "detectedLanguages":
              [ { "languageCode": "ENG", 
              "confidence": 0.9999994 } ], ...

Document Classification

Document Classification can be used to classify a document.

Document Understanding provides a list of possible document types for the analyzed document. Each document type has a confidence score. The confidence score is a decimal number. Scores closer to 1 indicate a higher confidence in the extracted text, while lower scores indicate lower confidence score. The range of the confidence score for each label is between 0-1. The list of possible document types is:
  • Invoice
  • Receipt
  • Resume or CV
  • Tax form
  • Driver's license
  • Passport
  • Bank statement
  • Check
  • Payslip
  • Other
Supported features are:
  • Classify document
  • Confidence score
  • Single request
  • Batch request
Document Classification Example
An example of document classification use in Document Understanding.
Input document
Figure 3. Document Classification Input
Receipt from a fictitious cafe, including two line items, tax, subtotal and total amounts.
API Request:
{ 
            "processorConfig": {   
            "processorType": "GENERAL",  
            "features": [    
            {   
            "featureType": "DOCUMENT_CLASSIFICATION",    
            "maxResults": 5   
            }  
            ] 
            }, 
            "inputLocation": {  
            "sourceType": "OBJECT_STORAGE_LOCATIONS",  
            "objectLocations": [  
            {    
            "source": "OBJECT_STORAGE",   
            "namespaceName": "",   
            "bucketName": "",    
            "objectName": ""  
            }  
            ] 
            }, 
            "compartmentId": "", 
            "outputLocation": {  
            "namespaceName": "",  
            "bucketName": "",  
            "prefix": "" 
            }
            }
Output:
API Response:
{ "documentMetadata":
            { "pageCount": 1,
            "mimeType": "image/jpeg" },
            "pages":
            [ { "pageNumber": 1,
            "dimensions": 
            { "width": 361,
            "height": 600,
            "unit": "PIXEL" },
            "detectedDocumentTypes":
            [ { "documentType": "RECEIPT",
            "confidence": 1 },
            { "documentType": "TAX_FORM",
            "confidence": 6.465067e-9 },
            { "documentType": "CHECK",
            "confidence": 6.031838e-9 },
            { "documentType": "BANK_STATEMENT",
            "confidence": 5.413888e-9 },
            { "documentType": "PASSPORT",
            "confidence": 1.5554872e-9 } ],
            ...
            detectedDocumentTypes":
            [ { "documentType": "RECEIPT",
            "confidence": 1 } ], ...

Table Extraction

Table extraction can be used to identify tables in a document and extract their contents. For example, if a PDF receipt contains a table that includes the taxes and total amount, Document Understanding identifies the table and extracts the table structure.

Document Understanding provides the number of rows and columns for the table and the contents in each table cell. Each cell has a confidence score. The confidence score is a decimal number. Scores closer to 1 indicate a higher confidence in the extracted text, while lower scores indicate lower confidence score. The range of the confidence score for each label is from 0 to 1.

Supported features are:
  • Table extraction for tables with and without borders
  • Bounding polygons
  • Confidence score
  • Single request
  • Batch request
Limitations are:
  • English language only
Table Extraction Example
An example of table extraction use in Document Understanding.
Input document
Figure 4. Table Extraction Input
Fictitious balance sheet for eight quarters
API Request:
{ 
                  "processorConfig": {  
                  "processorType": "GENERAL",  
                  "features": [   
                  {    
                  "featureType": "TABLE_EXTRACTION"   
                  }  
                  ] 
                  }, 
                  "inputLocation": {  
                  "sourceType": "OBJECT_STORAGE_LOCATIONS",  
                  "objectLocations": [   
                  {    
                  "source": "OBJECT_STORAGE",    
                  "namespaceName": "",    
                  "bucketName": "",    
                  "objectName": ""   
                  }  
                  ] 
                  }, 
                  "compartmentId": "", 
                  "outputLocation": {  
                  "namespaceName": "",  
                  "bucketName": "",  
                  "prefix": "" 
                  }
                  }
Output:
Figure 5. Table Extraction Output
The balance sheet with cell, column header and row identifer highlighted
API Response:
{ "documentMetadata":
                  { "pageCount": 1,
                  "mimeType": "application/pdf" },
                  "pages":
                  [ { "pageNumber": 1,
                  "dimensions": 
                  { "width": 2575, 
                  "height": 1013,
                  "unit": "PIXEL" },
                  ... 
                  "tables":
                  [ { "rowCount": 15,
                  "columnCount": 9,
                  "bodyRows":
                  [ { "cells":
                  [ { "text": "Qtr1-12",
                  "rowIndex": 0,
                  "columnIndex": 1,
                  "confidence": 0.92011595,
                  "boundingPolygon":
                  { "normalizedVertices": 
                  [ { "x": 0.2532038834951456,
                  "y": 0.022704837117472853 },
                  { "x": 0.3005825242718447,
                  "y": 0.022704837117472853 },
                  { "x": 0.3005825242718447,
                  "y": 0.05330700888450148 },
                  { "x": 0.2532038834951456,
                  "y": 0.05330700888450148 } ]
                  },
                  "wordIndexes": [ 0 ] },
                  { "text": "Qtr2-12",
                  "rowIndex": 0,
                  "columnIndex": 2,
                  "confidence": 0.919653,
                  "boundingPolygon":
                  { "normalizedVertices":
                  [ { "x": 0.33048543689320387,
                  "y": 0.022704837117472853 },
                  { "x": 0.3724271844660194,
                  "y": 0.022704837117472853 },
                  { "x": 0.3724271844660194,
                  "y": 0.05330700888450148 },
                  { "x": 0.33048543689320387,
                  "y": 0.05330700888450148 } ]
                  }, "wordIndexes": [ 1 ] },
                  ...

Key Value Extraction (Receipts)

Key value extraction can be used to identify values for predefined keys in a receipt. For example, if a receipt includes a merchant name, merchant address, or merchant phone number, Document Understanding can identify these values and return them as a key value pair.

The supported features are:
  • Extract values for predefined key value pairs
  • Bounding polygons
  • Single request
  • Batch request
Limitations:
  • Supports receipts in English only.
The supported fields are:
Supported Fields
Field Description
MerchantName The name of the merchant issuing the receipt.
MerchantPhoneNumber The telephone number of the merchant.
MerchantAddress The address of the merchant.
TransactionDate The date the receipt was issued.
TransactionTime The time the receipt was issued.
Total The total amount of the receipt, after all charges and taxes have been applied.
Subtotal The subtotal before taxes.
Tax Any sales taxes.
Tip The amount of tip given by the purchaser.

The supported line item information is:
Supported Line Items
Line Item Description
ItemName Name of the item.
ItemPrice Unit price of the item.
ItemQuantity The number of each item purchased.
ItemTotalPrice The total price of the line item.
Key Value Extraction (Receipts) Example
An example of key value extraction use in Document Understanding.
Input document
Figure 6. Key Value Extraction (Receipts) Input
Receipt from a fictitious cafe, including two line items, tax, subtotal and total amounts.
API Request:
{ 
            "processorConfig": {  
            "processorType": "GENERAL",  
            "features": [   
            {    
            "featureType": "KEY_VALUE_EXTRACTION"   
            },  
            "documentType": "RECEIPT" 
            }, 
            "inputLocation": {  
            "sourceType": "OBJECT_STORAGE_LOCATIONS",  
            "objectLocations": [   
            {    
            "source": "OBJECT_STORAGE",    
            "namespaceName": "",   
            "bucketName": "",    
            "objectName": ""   
            }  
            ] 
            }, 
            "compartmentId": "", 
            "outputLocation": {  
            "namespaceName": "",  
            "bucketName": "",  
            "prefix": "" 
            }
            }
Output:
Figure 7. Key Value Extraction (Receipts) Output
The fictitious receipt with only specific lines and fields highighted
API Response:
{ "documentMetadata":
            { "pageCount": 1,
            "mimeType": "image/jpeg" },
            "pages":
            [ { "pageNumber": 1, 
            "dimensions":
            { "width": 361,
            "height": 600,
            "unit": "PIXEL" },
            ...
            "documentFields":
            [ { "fieldType": "KEY_VALUE",
            "fieldLabel":
            { "name": "MerchantName" },
            "fieldValue":
            { "valueType": "STRING",
            "boundingPolygon":
            { "normalizedVertices":
            [ { "x": 0.0664819944598338,
            "y": 0.011666666666666667 },
            { "x": 0.3157894736842105,
            "y": 0.011666666666666667 },
            { "x": 0.3157894736842105,
            "y": 0.035 },
            { "x": 0.0664819944598338,
            "y": 0.035 } ]
            },
            "wordIndexes":
            [ 0, 1 ],
            "value": "Example cafe" } },
            ...

Key Value Extraction (Invoices)

Key value extraction can be used to identify values for predefined keys in an invoice. For example, if an invoice includes a vendor name, total, and invoice ID, Document Understanding can identify these values and return them as a key value pair.

The supported features are:
  • Extract values for predefined key value pairs
  • Bounding polygons
  • Confidence score
The supported fields are:
Supported Fields
Field Description
CustomerName Name of invoiced customer.
CustomerId Customer reference identifier.
PurchaseOrder Purchase order number.
InvoiceId Identifier for the specific invoice.
InvoiceDate Date of issue on the invoice.
DueDate Date when payment is due on this invoice.
VendorName Name of vendor.
VendorAddress Vendor mailing address.
VendorAddressRecipient Name referenced with the VendorAddress.
CustomerAddress Mailing address for the Customer.
CustomerAddressRecipient Name referenced with the CustomerAddress.
BillingAddress Explicit billing address for the customer.
BillingAddressRecipient Name referenced with the BillingAddress.
ShippingAddress Explicit shipping address for the customer.
ShippingAddressRecipient Name referenced with the ShippingAddress.
PaymentTerm The terms of payment for the invoice.
Subtotal Subtotal field identified on this invoice.
TotalTax Total tax value identified on this invoice.
InvoiceTotal Total charge amount associated with the invoice.
AmountDue Total amount due to the vendor.
ServiceAddress Explicit service address or property address for the customer.
ServiceAddressRecipient Name referenced with the ServiceAddress.
RemittanceAddress Explicit remittance or payment address for the customer.
RemittanceAddressRecipient Name referenced with the RemittanceAddress.
ShippingCost Total shipping or shipping and handling costs associated with an invoice.
ServiceStartDate First date for the service period.
ServiceEndDate End date for the service period.
PreviousUnpaidBalance Explicit previously unpaid balance.

The supported line items are:
Supported Line Items
Line Item Description
Items Concatenation of all other line item values (that is, the entire line of the line item).
Name The name listed for a product or service, for example, t-shirt.
Amount The amount of the line item.
Description The text description for the invoice line item, for example, men's rayon shirt, sizes small, medium, and large.
Quantity The quantity for this invoice line item.
UnitPrice The price per item identified on the invoice.
ProductCode Product code, product number, or SKU referenced in the line item. For example, 123456.
Unit The unit of the line item, for example, kg, lb.
Tax Tax explicitly referenced on the line item.
Date Date corresponding to each line item.
Key Value Extraction (Invoice) Example
An example of the use of key value extraction from an invoice in Document Understanding.
Input document
Figure 8. Key Value Extraction (Invoice) Input
Fictitious invoice for cable and wire.
API Request:
{ 
       "processorConfig": {  
       "processorType": "GENERAL", 
       "features": [   
       {    
       "featureType": "KEY_VALUE_EXTRACTION"  
       }, 
       "documentType": "INVOICE" 
       }, 
       "inputLocation": {  
       "sourceType": "OBJECT_STORAGE_LOCATIONS",  
       "objectLocations": [   
       {    
       "source": "OBJECT_STORAGE",   
       "namespaceName": "",    
       "bucketName": "",    
       "objectName": ""   
       }  
       ] 
       }, 
       "compartmentId": "", 
       "outputLocation": {  
       "namespaceName": "",  
       "bucketName": "",  
       "prefix": "" 
       }
       }
Output:
API Response:
{ 
       "documentMetadata": {  
       "pageCount": 1,  
       "mimeType": "image/png" 
       },  "pages": [  
       {   
       "pageNumber": 1,   
       "dimensions": {    
       "width": 1372,    
       "height": 1732,    
       "unit": "PIXEL"      },   
       "documentFields": [    
       {     
       "fieldType": "KEY_VALUE",     
       "fieldLabel": {      
       "name": "VendorAddress",      
       "confidence": 0.99862003    
       },     
       "fieldValue": {      
       "valueType": "STRING",      
       "text": "657 Clifford Street Allentown, PA",      
       "boundingPolygon": {       
       "normalizedVertices": [        
       {         
       "x": 0.08454810495626822,         
       "y": 0.10219399538106236        
       },        
       {         
       "x": 0.21793002915451895,          
       "y": 0.10219399538106236        
       },       
       {         
       "x": 0.21793002915451895,         
       "y": 0.13048498845265588        
       },       
       {         
       "x": 0.08454810495626822,
       "y": 0.13048498845265588        
       }       
       ]      
       },      
       "wordIndexes": [       
       3,      
       4,      
       5,      
       9,       
       10      
       ],      
       "value": "657 Clifford Street Allentown, PA"     
       }    
       },    
       {     
       "fieldType": "LINE_ITEM_GROUP",     
       "fieldLabel": {      
       "name": "Items"     
       },     
       "fieldValue": {      
       "valueType": "ARRAY",      
       "items": [       
       {        
       "fieldType": "LINE_ITEM",        
       "fieldValue": {         
       "valueType": "ARRAY",          
       "text": "1 Cable165XZ3654681 12.75 $12.75",         
       "items": [          
       {            
       "fieldType": "LINE_ITEM_FIELD",           
       "fieldLabel": {            
       "name": "Quantity",            
       "confidence": 0.9989789           
       },           
       "fieldValue": {             
       "valueType": "NUMBER",            
       "text": "1",           
       "boundingPolygon": {             
       "normalizedVertices": [
       {             
       "x": 0.39941690962099125,                 
       "y": 0.5075057736720554             
       },             
       {               
       "x": 0.39941690962099125,               
       "y": 0.5184757505773672              
       },             
       {              
       "x": 0.24927113702623907,               
       "y": 0.5184757505773672             
       }             
       ]            
       },            
       "wordIndexes": [             
       68           
       ],           
       "value": "Cable165XZ3654681"          
       }          
       },         
       {           
       "fieldType": "LINE_ITEM_FIELD",           
       "fieldLabel": {            
       "name": "UnitPrice",             
       "confidence": 0.9375645           
       },           
       "fieldValue": {            
       "valueType": "NUMBER",            
       "text": "12.75",            
       "boundingPolygon": {            
       "normalizedVertices": [             
       {                
       "x": 0.7594752186588921,              
       "y": 0.50635103926097             
       },            
       {              
       "x": 0.8024781341107872,               
       "y": 0.50635103926097             
       },
       {               
       "x": 0.8024781341107872,              
       "y": 0.5196304849884527              
       },             
       {                
       "x": 0.7594752186588921,              
       "y": 0.5196304849884527              
       }             
       ]            
       },            
       "wordIndexes": [             
       69           
       ],            
       "value": 12.75           
       }          
       },        
       ]        
       }       
       }      
       ]     
       }    
       }   
       ]  
       } 
       ],
       }

Key Value Extraction (Driver ID)

Key value extraction can be used to identify values for predefined keys in a US or UK driver's documentation. For example, if a Driver ID includes an issue date, region, and expiry date, Document Understanding can identify these values and return them as a key value pair.

The supported features are:

  • Extract values for predefined key value pairs
  • Bounding polygons
  • Confidence score
The supported fields are:
Supported Fields
Field Description API Response Value
FirstName First name (given name) listed on the document. Extracted Text
LastName Last name (family name) listed on the document. Extracted Text
Country Country listed on the document. Extracted ISO 3166-1 country code
BirthDate Date of birth. Date in YYYY/MM/DD format
ExpiryDate Date of expiration listed on the document. Date in YYYY/MM/DD format
IssueDate Date of issue listed on the document. Date in YYYY/MM/DD format
Gender Gender listed on the document. Extracted Text
DocumentNumber Document identification number. Extracted Text
Address Address listed on the document. Extracted Text
Region Region listed on the document. For example, state or territory. Extracted Text
Key Value Extraction (Driver ID) Example
An example of the use of key value extraction from driving documentation in Document Understanding.
Input document
Figure 9. Key Value Extraction (Driver ID) Input
Fictitious Minnesotan driver's license.
API Request:
{ 
       "processorConfig": {  
       "processorType": "GENERAL", 
       "features": [   
       {    
       "featureType": "KEY_VALUE_EXTRACTION"  
       }, 
       "documentType": "DRIVER_LICENSE" 
       }, 
       "inputLocation": {  
       "sourceType": "OBJECT_STORAGE_LOCATIONS",  
       "objectLocations": [   
       {    
       "source": "OBJECT_STORAGE",   
       "namespaceName": "",    
       "bucketName": "",    
       "objectName": ""   
       }  
       ] 
       }, 
       "compartmentId": "", 
       "outputLocation": {  
       "namespaceName": "",  
       "bucketName": "",  
       "prefix": "" 
       }
       }
Output:
API Response:
{ 
       "documentMetadata": {  
       "pageCount": 1,  
       "mimeType": "image/png" 
       }, 
       "pages": [  
       {   
       "pageNumber": 1,   
       "documentFields": [    
       {     
       "fieldType": "KEY_VALUE",     
       "fieldLabel": {     
       "name": "Region",     
       "confidence": 0.92     
       },     
       "fieldValue": {      
       "valueType": "STRING",      
       "boundingPolygon": {       
       "normalizedVertices": [        
       {        
       "x": 0.04892966360856269,        
       "y": 0.025        
       },        
       {         
       "x": 0.5091743119266054,         
       "y": 0.025        
       },        
       {         
       "x": 0.5091743119266054,         
       "y": 0.0925        
       },        
       {         
       "x": 0.04892966360856269,         
       "y": 0.0925        
       }       
       ]      
       },      
       "value": "MINNESOTA"     
       }
       },   
       ]  
       } 
       ],
       }

Key Value Extraction (Passport)

Key value extraction can be used to identify values for predefined keys in a MRZ-supported passport. For example, if a passport includes nationality and date of issue, Document Understanding can identify these values and return them as a key value pair.

The supported features are:

  • Extract values for predefined key value pairs
  • Confidence score
The supported fields are:
Supported Fields
Field Description API Response Value
FirstName First name (given name) listed on the document. Extracted Text
LastName Last name (family name) listed on the document. Extracted Text
Country Country listed on the document. Extracted ISO 3166-1 country code
Nationality Nationality of the document owner. Extracted ISO 3166-1 country code
BirthDate Date of birth.
  • Date in YYYY/MM/DD format
  • Else: <
ExpiryDate Date of expiration listed on the document.
  • Date in YYYY/MM/DD format
  • Else: <
Gender Gender listed on the document. Extracted Text
DocumentType Document type, often listed as a single character, such as "P" for passport or "V" for Visa. Extracted Text
DocumentNumber Document identification number. Extracted Text
Key Value Extraction (Passport) Example
An example of the use of key value extraction from a passport in Document Understanding.
Input document
Figure 10. Key Value Extraction (Passport) Input
Fictitious passport.
API Request:
{ 
       "processorConfig": {  
       "processorType": "GENERAL",  
       "features": [   
       {    
       "featureType": "KEY_VALUE_EXTRACTION"   
       },  
       "documentType": "PASSPORT" 
       }, 
       "inputLocation": {  
       "sourceType": "OBJECT_STORAGE_LOCATIONS",  
       "objectLocations": [   
       {    
       "source": "OBJECT_STORAGE",    
       "namespaceName": "",    
       "bucketName": "",    
       "objectName": ""   
       }  
       ] 
       }, 
       "compartmentId": "", 
       "outputLocation": {  
       "namespaceName": "",  
       "bucketName": "",  
       "prefix": "" 
       }
       }
Output:
API Response:
{ 
       "documentMetadata": {  
       "pageCount": 1,  
       "mimeType": "image/png" 
       }, 
       "pages": [  
       {   
       "pageNumber": 1,   
       "documentFields": [    
       {     
       "fieldType": "KEY_VALUE",     
       "fieldLabel": {      
       "name": "FirstName",      
       "confidence": 0.9999514     
       },     
       "fieldValue": {       
       "valueType": "STRING",      
       "value": "GISELLE OROZCO"     
       }    
       },    
       {     
       "fieldType": "KEY_VALUE",     
       "fieldLabel": {      
       "name": "LastName",      
       "confidence": 0.9999514     
       },     
       "fieldValue": {      
       "valueType": "STRING",      
       "value": "OLIVERAS"     
       }    
       },   
       ]  
       } 
       ],
       }

Optical Character Recognition (OCR) PDF

OCR PDF generates a searchable PDF file in your Object Storage. For example, Document Understanding can take a PDF file with text and images, and return a PDF file where you can search for the text in the PDF.

Supported features:
  • Generate searchable PDF
  • Single request
  • Batch request
OCR PDF Example
An example of OCR PDF use in Document Understanding.
Input
Figure 11. OCR PDF Input
Page from a PDF document
API Request:
{ 
            "processorConfig": {  
            "processorType": "GENERAL",  
            "features": [   
            {    
            "featureType": "TEXT_EXTRACTION",    
            "generateSearchablePdf": true   
            }  
            ] 
            }, 
            "inputLocation": {  
            "sourceType": "OBJECT_STORAGE_LOCATIONS",  
            "objectLocations": [   
            {    
            "source": "OBJECT_STORAGE",    
            "namespaceName": "",    
            "bucketName": "",    
            "objectName": ""   
            }  
            ] 
            }, 
            "compartmentId": "", 
            "outputLocation": {  
            "namespaceName": "",  
            "bucketName": "",  
            "prefix": "" 
            }
            }
Output:
Searchable PDF.

Using the Pretrained Document AI Models

Document Understanding provides pretrained models for customers to extract insights about their documents without needing data scientists.

You need the following before using a pretrained model:

  • A paid tenancy account in Oracle Cloud Infrastructure.

  • Familiarity with Oracle Cloud Infrastructure Object Storage.

You can call the pretrained Document AI models as a batch request using Rest APIs, SDK, or CLI. You can call the pretrained Document AI models as a single request using the Console, Rest APIs, SDK, or CLI.

See the Limits section for information on what is allowed in batch requests.

For more information about using the Document AI models with the REST API, see Analyzing with the API.

For more information about using the Document AI models in the Console, see Using the Console.