mindee 3.11.0 → 3.13.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.rubocop.yml +1 -1
- data/CHANGELOG.md +27 -0
- data/README.md +23 -23
- data/Rakefile +5 -0
- data/bin/mindee.rb +7 -1
- data/docs/bank_account_details_v2.md +5 -1
- data/docs/bank_check_v1.md +6 -2
- data/docs/bank_statement_fr_v1.md +3 -0
- data/docs/barcode_reader_v1.md +5 -1
- data/docs/bill_of_lading_v1.md +202 -0
- data/docs/carte_grise_v1.md +5 -1
- data/docs/carte_vitale_v1.md +5 -1
- data/docs/code_samples/bill_of_lading_v1_async.txt +19 -0
- data/docs/code_samples/energy_bill_fra_v1_async.txt +19 -0
- data/docs/code_samples/financial_document_v1_async.txt +19 -0
- data/docs/code_samples/invoices_v4_async.txt +19 -0
- data/docs/code_samples/nutrition_facts_v1_async.txt +19 -0
- data/docs/code_samples/payslip_fra_v2_async.txt +19 -0
- data/docs/code_samples/us_healthcare_cards_v1_async.txt +19 -0
- data/docs/cropper_v1.md +6 -2
- data/docs/custom_v1.md +5 -3
- data/docs/energy_bill_fra_v1.md +249 -0
- data/docs/eu_driver_license_v1.md +6 -2
- data/docs/expense_receipts_v5.md +38 -11
- data/docs/financial_document_v1.md +80 -23
- data/docs/generated_v1.md +3 -0
- data/docs/getting_started.md +3 -0
- data/docs/idcard_fr_v2.md +15 -2
- data/docs/international_id_v2.md +13 -1
- data/docs/invoice_splitter_v1.md +16 -13
- data/docs/invoices_v4.md +57 -23
- data/docs/license_plates_v1.md +5 -1
- data/docs/multi_receipts_detector_v1.md +5 -1
- data/docs/nutrition_facts_v1.md +295 -0
- data/docs/passport_v1.md +5 -1
- data/docs/payslip_fra_v2.md +218 -0
- data/docs/proof_of_address_v1.md +5 -1
- data/docs/resume_v1.md +24 -1
- data/docs/us_driver_license_v1.md +6 -2
- data/docs/us_healthcare_cards_v1.md +208 -0
- data/docs/us_mail_v2.md +5 -1
- data/docs/us_w9_v1.md +6 -2
- data/examples/auto_invoice_splitter_extraction.rb +43 -0
- data/lib/mindee/client.rb +20 -8
- data/lib/mindee/extraction/common/extracted_image.rb +73 -0
- data/lib/mindee/extraction/common/image_extractor.rb +189 -0
- data/lib/mindee/extraction/common.rb +4 -0
- data/lib/mindee/extraction/multi_receipts_extractor/multi_receipts_extractor.rb +26 -0
- data/lib/mindee/extraction/multi_receipts_extractor.rb +3 -0
- data/lib/mindee/extraction/pdf_extractor/extracted_pdf.rb +55 -0
- data/lib/mindee/extraction/pdf_extractor/pdf_extractor.rb +111 -0
- data/lib/mindee/extraction/pdf_extractor.rb +4 -0
- data/lib/mindee/extraction/tax_extractor/tax_extractor.rb +322 -0
- data/lib/mindee/extraction/tax_extractor.rb +1 -320
- data/lib/mindee/extraction.rb +3 -0
- data/lib/mindee/http/endpoint.rb +18 -6
- data/lib/mindee/input/sources.rb +8 -0
- data/lib/mindee/parsing/common/api_response.rb +1 -1
- data/lib/mindee/parsing/common/document.rb +31 -1
- data/lib/mindee/parsing/common/extras/cropper_extra.rb +29 -0
- data/lib/mindee/parsing/common/extras/extras.rb +50 -0
- data/lib/mindee/parsing/common/extras/full_text_ocr_extra.rb +32 -0
- data/lib/mindee/parsing/common/extras.rb +5 -0
- data/lib/mindee/parsing/common/page.rb +5 -0
- data/lib/mindee/parsing/standard/base_field.rb +1 -0
- data/lib/mindee/parsing/standard/company_registration_field.rb +17 -0
- data/lib/mindee/product/bill_of_lading/bill_of_lading_v1.rb +39 -0
- data/lib/mindee/product/bill_of_lading/bill_of_lading_v1_carrier.rb +52 -0
- data/lib/mindee/product/bill_of_lading/bill_of_lading_v1_carrier_item.rb +95 -0
- data/lib/mindee/product/bill_of_lading/bill_of_lading_v1_consignee.rb +58 -0
- data/lib/mindee/product/bill_of_lading/bill_of_lading_v1_document.rb +136 -0
- data/lib/mindee/product/bill_of_lading/bill_of_lading_v1_notify_party.rb +58 -0
- data/lib/mindee/product/bill_of_lading/bill_of_lading_v1_page.rb +32 -0
- data/lib/mindee/product/bill_of_lading/bill_of_lading_v1_shipper.rb +58 -0
- data/lib/mindee/product/financial_document/financial_document_v1_document.rb +3 -1
- data/lib/mindee/product/financial_document/financial_document_v1_line_item.rb +22 -1
- data/lib/mindee/product/financial_document/financial_document_v1_page.rb +1 -1
- data/lib/mindee/product/fr/bank_account_details/bank_account_details_v2_bban.rb +4 -15
- data/lib/mindee/product/fr/energy_bill/energy_bill_v1.rb +41 -0
- data/lib/mindee/product/fr/energy_bill/energy_bill_v1_document.rb +235 -0
- data/lib/mindee/product/fr/energy_bill/energy_bill_v1_energy_consumer.rb +48 -0
- data/lib/mindee/product/fr/energy_bill/energy_bill_v1_energy_supplier.rb +48 -0
- data/lib/mindee/product/fr/energy_bill/energy_bill_v1_energy_usage.rb +97 -0
- data/lib/mindee/product/fr/energy_bill/energy_bill_v1_meter_detail.rb +54 -0
- data/lib/mindee/product/fr/energy_bill/energy_bill_v1_page.rb +34 -0
- data/lib/mindee/product/fr/energy_bill/energy_bill_v1_subscription.rb +97 -0
- data/lib/mindee/product/fr/energy_bill/energy_bill_v1_taxes_and_contribution.rb +97 -0
- data/lib/mindee/product/fr/payslip/payslip_v2.rb +41 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_bank_account_detail.rb +54 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_document.rb +128 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_employee.rb +78 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_employer.rb +78 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_employment.rb +72 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_page.rb +34 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_pay_detail.rb +100 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_pay_period.rb +66 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_pto.rb +56 -0
- data/lib/mindee/product/fr/payslip/payslip_v2_salary_detail.rb +81 -0
- data/lib/mindee/product/international_id/international_id_v2_document.rb +1 -1
- data/lib/mindee/product/international_id/international_id_v2_page.rb +1 -1
- data/lib/mindee/product/invoice/invoice_v4_document.rb +3 -1
- data/lib/mindee/product/invoice/invoice_v4_line_item.rb +22 -1
- data/lib/mindee/product/invoice/invoice_v4_page.rb +1 -1
- data/lib/mindee/product/invoice_splitter/invoice_splitter_v1_document.rb +1 -1
- data/lib/mindee/product/multi_receipts_detector/multi_receipts_detector_v1_document.rb +1 -1
- data/lib/mindee/product/multi_receipts_detector/multi_receipts_detector_v1_page.rb +1 -1
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1.rb +39 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_added_sugar.rb +52 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_calorie.rb +52 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_cholesterol.rb +52 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_dietary_fiber.rb +52 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_document.rb +173 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_nutrient.rb +87 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_page.rb +32 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_protein.rb +52 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_saturated_fat.rb +52 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_serving_size.rb +46 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_sodium.rb +58 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_total_carbohydrate.rb +52 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_total_fat.rb +52 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_total_sugar.rb +52 -0
- data/lib/mindee/product/nutrition_facts_label/nutrition_facts_label_v1_trans_fat.rb +52 -0
- data/lib/mindee/product/receipt/receipt_v5_document.rb +1 -1
- data/lib/mindee/product/receipt/receipt_v5_line_item.rb +11 -1
- data/lib/mindee/product/receipt/receipt_v5_page.rb +1 -1
- data/lib/mindee/product/resume/resume_v1_certificate.rb +11 -1
- data/lib/mindee/product/resume/resume_v1_education.rb +14 -1
- data/lib/mindee/product/resume/resume_v1_language.rb +9 -1
- data/lib/mindee/product/resume/resume_v1_professional_experience.rb +15 -1
- data/lib/mindee/product/resume/resume_v1_social_networks_url.rb +9 -1
- data/lib/mindee/product/us/healthcare_card/healthcare_card_v1.rb +41 -0
- data/lib/mindee/product/us/healthcare_card/healthcare_card_v1_copay.rb +65 -0
- data/lib/mindee/product/us/healthcare_card/healthcare_card_v1_document.rb +127 -0
- data/lib/mindee/product/us/healthcare_card/healthcare_card_v1_page.rb +34 -0
- data/lib/mindee/product/us/us_mail/us_mail_v2_recipient_address.rb +14 -1
- data/lib/mindee/product/us/us_mail/us_mail_v2_sender_address.rb +5 -17
- data/lib/mindee/product.rb +6 -1
- data/lib/mindee/version.rb +1 -1
- data/mindee.gemspec +1 -0
- metadata +91 -3
- /data/lib/mindee/extraction/{ocr_extractor.rb → tax_extractor/ocr_extractor.rb} +0 -0
@@ -0,0 +1,218 @@
|
|
1
|
+
---
|
2
|
+
title: FR Payslip OCR Ruby
|
3
|
+
category: 622b805aaec68102ea7fcbc2
|
4
|
+
slug: ruby-fr-payslip-ocr
|
5
|
+
parentDoc: 6294d97ee723f1008d2ab28e
|
6
|
+
---
|
7
|
+
The Ruby OCR SDK supports the [Payslip API](https://platform.mindee.com/mindee/payslip_fra).
|
8
|
+
|
9
|
+
The [sample below](https://github.com/mindee/client-lib-test-data/blob/main/products/payslip_fra/default_sample.jpg) can be used for testing purposes.
|
10
|
+

|
11
|
+
|
12
|
+
# Quick-Start
|
13
|
+
```rb
|
14
|
+
require 'mindee'
|
15
|
+
|
16
|
+
# Init a new client
|
17
|
+
mindee_client = Mindee::Client.new(api_key: 'my-api-key')
|
18
|
+
|
19
|
+
# Load a file from disk
|
20
|
+
input_source = mindee_client.source_from_path('/path/to/the/file.ext')
|
21
|
+
|
22
|
+
# Parse the file
|
23
|
+
result = mindee_client.enqueue_and_parse(
|
24
|
+
input_source,
|
25
|
+
Mindee::Product::FR::Payslip::PayslipV2
|
26
|
+
)
|
27
|
+
|
28
|
+
# Print a full summary of the parsed data in RST format
|
29
|
+
puts result.document
|
30
|
+
|
31
|
+
# Print the document-level parsed data
|
32
|
+
# puts result.document.inference.prediction
|
33
|
+
|
34
|
+
```
|
35
|
+
# Field Types
|
36
|
+
## Standard Fields
|
37
|
+
These fields are generic and used in several products.
|
38
|
+
|
39
|
+
### Basic Field
|
40
|
+
Each prediction object contains a set of fields that inherit from the generic `Field` class.
|
41
|
+
A typical `Field` object will have the following attributes:
|
42
|
+
|
43
|
+
* **value** (`String`, `Float`, `Integer`, `Boolean`): corresponds to the field value. Can be `nil` if no value was extracted.
|
44
|
+
* **confidence** (Float, nil): the confidence score of the field prediction.
|
45
|
+
* **bounding_box** (`Mindee::Geometry::Quadrilateral`, `nil`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
|
46
|
+
* **polygon** (`Mindee::Geometry::Polygon`, `nil`): contains the relative vertices coordinates (`Point`) of a polygon containing the field in the image.
|
47
|
+
* **page_id** (`Integer`, `nil`): the ID of the page, always `nil` when at document-level.
|
48
|
+
* **reconstructed** (`Boolean`): indicates whether an object was reconstructed (not extracted as the API gave it).
|
49
|
+
|
50
|
+
|
51
|
+
Aside from the previous attributes, all basic fields have access to a `to_s` method that can be used to print their value as a string.
|
52
|
+
|
53
|
+
## Specific Fields
|
54
|
+
Fields which are specific to this product; they are not used in any other product.
|
55
|
+
|
56
|
+
### Bank Account Details Field
|
57
|
+
Information about the employee's bank account.
|
58
|
+
|
59
|
+
A `PayslipV2BankAccountDetail` implements the following attributes:
|
60
|
+
|
61
|
+
* `bank_name` (String): The name of the bank.
|
62
|
+
* `iban` (String): The IBAN of the bank account.
|
63
|
+
* `swift` (String): The SWIFT code of the bank.
|
64
|
+
Fields which are specific to this product; they are not used in any other product.
|
65
|
+
|
66
|
+
### Employee Field
|
67
|
+
Information about the employee.
|
68
|
+
|
69
|
+
A `PayslipV2Employee` implements the following attributes:
|
70
|
+
|
71
|
+
* `address` (String): The address of the employee.
|
72
|
+
* `date_of_birth` (String): The date of birth of the employee.
|
73
|
+
* `first_name` (String): The first name of the employee.
|
74
|
+
* `last_name` (String): The last name of the employee.
|
75
|
+
* `phone_number` (String): The phone number of the employee.
|
76
|
+
* `registration_number` (String): The registration number of the employee.
|
77
|
+
* `social_security_number` (String): The social security number of the employee.
|
78
|
+
Fields which are specific to this product; they are not used in any other product.
|
79
|
+
|
80
|
+
### Employer Field
|
81
|
+
Information about the employer.
|
82
|
+
|
83
|
+
A `PayslipV2Employer` implements the following attributes:
|
84
|
+
|
85
|
+
* `address` (String): The address of the employer.
|
86
|
+
* `company_id` (String): The company ID of the employer.
|
87
|
+
* `company_site` (String): The site of the company.
|
88
|
+
* `naf_code` (String): The NAF code of the employer.
|
89
|
+
* `name` (String): The name of the employer.
|
90
|
+
* `phone_number` (String): The phone number of the employer.
|
91
|
+
* `urssaf_number` (String): The URSSAF number of the employer.
|
92
|
+
Fields which are specific to this product; they are not used in any other product.
|
93
|
+
|
94
|
+
### Employment Field
|
95
|
+
Information about the employment.
|
96
|
+
|
97
|
+
A `PayslipV2Employment` implements the following attributes:
|
98
|
+
|
99
|
+
* `category` (String): The category of the employment.
|
100
|
+
* `coefficient` (Float): The coefficient of the employment.
|
101
|
+
* `collective_agreement` (String): The collective agreement of the employment.
|
102
|
+
* `job_title` (String): The job title of the employee.
|
103
|
+
* `position_level` (String): The position level of the employment.
|
104
|
+
* `start_date` (String): The start date of the employment.
|
105
|
+
Fields which are specific to this product; they are not used in any other product.
|
106
|
+
|
107
|
+
### Pay Detail Field
|
108
|
+
Detailed information about the pay.
|
109
|
+
|
110
|
+
A `PayslipV2PayDetail` implements the following attributes:
|
111
|
+
|
112
|
+
* `gross_salary` (Float): The gross salary of the employee.
|
113
|
+
* `gross_salary_ytd` (Float): The year-to-date gross salary of the employee.
|
114
|
+
* `income_tax_rate` (Float): The income tax rate of the employee.
|
115
|
+
* `income_tax_withheld` (Float): The income tax withheld from the employee's pay.
|
116
|
+
* `net_paid` (Float): The net paid amount of the employee.
|
117
|
+
* `net_paid_before_tax` (Float): The net paid amount before tax of the employee.
|
118
|
+
* `net_taxable` (Float): The net taxable amount of the employee.
|
119
|
+
* `net_taxable_ytd` (Float): The year-to-date net taxable amount of the employee.
|
120
|
+
* `total_cost_employer` (Float): The total cost to the employer.
|
121
|
+
* `total_taxes_and_deductions` (Float): The total taxes and deductions of the employee.
|
122
|
+
Fields which are specific to this product; they are not used in any other product.
|
123
|
+
|
124
|
+
### Pay Period Field
|
125
|
+
Information about the pay period.
|
126
|
+
|
127
|
+
A `PayslipV2PayPeriod` implements the following attributes:
|
128
|
+
|
129
|
+
* `end_date` (String): The end date of the pay period.
|
130
|
+
* `month` (String): The month of the pay period.
|
131
|
+
* `payment_date` (String): The date of payment for the pay period.
|
132
|
+
* `start_date` (String): The start date of the pay period.
|
133
|
+
* `year` (String): The year of the pay period.
|
134
|
+
Fields which are specific to this product; they are not used in any other product.
|
135
|
+
|
136
|
+
### PTO Field
|
137
|
+
Information about paid time off.
|
138
|
+
|
139
|
+
A `PayslipV2Pto` implements the following attributes:
|
140
|
+
|
141
|
+
* `accrued_this_period` (Float): The amount of paid time off accrued in this period.
|
142
|
+
* `balance_end_of_period` (Float): The balance of paid time off at the end of the period.
|
143
|
+
* `used_this_period` (Float): The amount of paid time off used in this period.
|
144
|
+
Fields which are specific to this product; they are not used in any other product.
|
145
|
+
|
146
|
+
### Salary Details Field
|
147
|
+
Detailed information about the earnings.
|
148
|
+
|
149
|
+
A `PayslipV2SalaryDetail` implements the following attributes:
|
150
|
+
|
151
|
+
* `amount` (Float): The amount of the earnings.
|
152
|
+
* `base` (Float): The base value of the earnings.
|
153
|
+
* `description` (String): The description of the earnings.
|
154
|
+
* `rate` (Float): The rate of the earnings.
|
155
|
+
|
156
|
+
# Attributes
|
157
|
+
The following fields are extracted for Payslip V2:
|
158
|
+
|
159
|
+
## Bank Account Details
|
160
|
+
**bank_account_details** ([PayslipV2BankAccountDetail](#bank-account-details-field)): Information about the employee's bank account.
|
161
|
+
|
162
|
+
```rb
|
163
|
+
puts result.document.inference.prediction.bank_account_details.value
|
164
|
+
```
|
165
|
+
|
166
|
+
## Employee
|
167
|
+
**employee** ([PayslipV2Employee](#employee-field)): Information about the employee.
|
168
|
+
|
169
|
+
```rb
|
170
|
+
puts result.document.inference.prediction.employee.value
|
171
|
+
```
|
172
|
+
|
173
|
+
## Employer
|
174
|
+
**employer** ([PayslipV2Employer](#employer-field)): Information about the employer.
|
175
|
+
|
176
|
+
```rb
|
177
|
+
puts result.document.inference.prediction.employer.value
|
178
|
+
```
|
179
|
+
|
180
|
+
## Employment
|
181
|
+
**employment** ([PayslipV2Employment](#employment-field)): Information about the employment.
|
182
|
+
|
183
|
+
```rb
|
184
|
+
puts result.document.inference.prediction.employment.value
|
185
|
+
```
|
186
|
+
|
187
|
+
## Pay Detail
|
188
|
+
**pay_detail** ([PayslipV2PayDetail](#pay-detail-field)): Detailed information about the pay.
|
189
|
+
|
190
|
+
```rb
|
191
|
+
puts result.document.inference.prediction.pay_detail.value
|
192
|
+
```
|
193
|
+
|
194
|
+
## Pay Period
|
195
|
+
**pay_period** ([PayslipV2PayPeriod](#pay-period-field)): Information about the pay period.
|
196
|
+
|
197
|
+
```rb
|
198
|
+
puts result.document.inference.prediction.pay_period.value
|
199
|
+
```
|
200
|
+
|
201
|
+
## PTO
|
202
|
+
**pto** ([PayslipV2Pto](#pto-field)): Information about paid time off.
|
203
|
+
|
204
|
+
```rb
|
205
|
+
puts result.document.inference.prediction.pto.value
|
206
|
+
```
|
207
|
+
|
208
|
+
## Salary Details
|
209
|
+
**salary_details** (Array<[PayslipV2SalaryDetail](#salary-details-field)>): Detailed information about the earnings.
|
210
|
+
|
211
|
+
```rb
|
212
|
+
for salary_details_elem in result.document.inference.prediction.salary_details do
|
213
|
+
puts salary_details_elem.value
|
214
|
+
end
|
215
|
+
```
|
216
|
+
|
217
|
+
# Questions?
|
218
|
+
[Join our Slack](https://join.slack.com/t/mindee-community/shared_invite/zt-2d0ds7dtz-DPAF81ZqTy20chsYpQBW5g)
|
data/docs/proof_of_address_v1.md
CHANGED
@@ -1,5 +1,8 @@
|
|
1
1
|
---
|
2
2
|
title: Proof of Address OCR Ruby
|
3
|
+
category: 622b805aaec68102ea7fcbc2
|
4
|
+
slug: ruby-proof-of-address-ocr
|
5
|
+
parentDoc: 6294d97ee723f1008d2ab28e
|
3
6
|
---
|
4
7
|
The Ruby OCR SDK supports the [Proof of Address API](https://platform.mindee.com/mindee/proof_of_address).
|
5
8
|
|
@@ -27,6 +30,7 @@ puts result.document
|
|
27
30
|
|
28
31
|
# Print the document-level parsed data
|
29
32
|
# puts result.document.inference.prediction
|
33
|
+
|
30
34
|
```
|
31
35
|
|
32
36
|
**Output (RST):**
|
@@ -104,7 +108,7 @@ A typical `Field` object will have the following attributes:
|
|
104
108
|
* **confidence** (Float, nil): the confidence score of the field prediction.
|
105
109
|
* **bounding_box** (`Mindee::Geometry::Quadrilateral`, `nil`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
|
106
110
|
* **polygon** (`Mindee::Geometry::Polygon`, `nil`): contains the relative vertices coordinates (`Point`) of a polygon containing the field in the image.
|
107
|
-
* **page_id** (`Integer`, `nil`): the ID of the page,
|
111
|
+
* **page_id** (`Integer`, `nil`): the ID of the page, always `nil` when at document-level.
|
108
112
|
* **reconstructed** (`Boolean`): indicates whether an object was reconstructed (not extracted as the API gave it).
|
109
113
|
|
110
114
|
|
data/docs/resume_v1.md
CHANGED
@@ -1,5 +1,8 @@
|
|
1
1
|
---
|
2
2
|
title: Resume OCR Ruby
|
3
|
+
category: 622b805aaec68102ea7fcbc2
|
4
|
+
slug: ruby-resume-ocr
|
5
|
+
parentDoc: 6294d97ee723f1008d2ab28e
|
3
6
|
---
|
4
7
|
The Ruby OCR SDK supports the [Resume API](https://platform.mindee.com/mindee/resume).
|
5
8
|
|
@@ -27,6 +30,7 @@ puts result.document
|
|
27
30
|
|
28
31
|
# Print the document-level parsed data
|
29
32
|
# puts result.document.inference.prediction
|
33
|
+
|
30
34
|
```
|
31
35
|
|
32
36
|
**Output (RST):**
|
@@ -115,7 +119,7 @@ A typical `Field` object will have the following attributes:
|
|
115
119
|
* **confidence** (Float, nil): the confidence score of the field prediction.
|
116
120
|
* **bounding_box** (`Mindee::Geometry::Quadrilateral`, `nil`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
|
117
121
|
* **polygon** (`Mindee::Geometry::Polygon`, `nil`): contains the relative vertices coordinates (`Point`) of a polygon containing the field in the image.
|
118
|
-
* **page_id** (`Integer`, `nil`): the ID of the page,
|
122
|
+
* **page_id** (`Integer`, `nil`): the ID of the page, always `nil` when at document-level.
|
119
123
|
* **reconstructed** (`Boolean`): indicates whether an object was reconstructed (not extracted as the API gave it).
|
120
124
|
|
121
125
|
|
@@ -165,6 +169,13 @@ A `ResumeV1Language` implements the following attributes:
|
|
165
169
|
|
166
170
|
* `language` (String): The language's ISO 639 code.
|
167
171
|
* `level` (String): The candidate's level for the language.
|
172
|
+
|
173
|
+
#### Possible values include:
|
174
|
+
- Fluent
|
175
|
+
- Proficient
|
176
|
+
- Intermediate
|
177
|
+
- Beginner
|
178
|
+
|
168
179
|
Fields which are specific to this product; they are not used in any other product.
|
169
180
|
|
170
181
|
### Professional Experiences Field
|
@@ -173,6 +184,13 @@ The list of the candidate's professional experiences.
|
|
173
184
|
A `ResumeV1ProfessionalExperience` implements the following attributes:
|
174
185
|
|
175
186
|
* `contract_type` (String): The type of contract for the professional experience.
|
187
|
+
|
188
|
+
#### Possible values include:
|
189
|
+
- Full-Time
|
190
|
+
- Part-Time
|
191
|
+
- Internship
|
192
|
+
- Freelance
|
193
|
+
|
176
194
|
* `department` (String): The specific department or division within the company.
|
177
195
|
* `employer` (String): The name of the company or organization.
|
178
196
|
* `end_month` (String): The month when the professional experience ended.
|
@@ -219,6 +237,11 @@ puts result.document.inference.prediction.document_language.value
|
|
219
237
|
## Document Type
|
220
238
|
**document_type** ([ClassificationField](#classification-field)): The type of the document sent.
|
221
239
|
|
240
|
+
#### Possible values include:
|
241
|
+
- RESUME
|
242
|
+
- MOTIVATION_LETTER
|
243
|
+
- RECOMMENDATION_LETTER
|
244
|
+
|
222
245
|
```rb
|
223
246
|
puts result.document.inference.prediction.document_type.value
|
224
247
|
```
|
@@ -1,5 +1,8 @@
|
|
1
1
|
---
|
2
2
|
title: US Driver License OCR Ruby
|
3
|
+
category: 622b805aaec68102ea7fcbc2
|
4
|
+
slug: ruby-us-driver-license-ocr
|
5
|
+
parentDoc: 6294d97ee723f1008d2ab28e
|
3
6
|
---
|
4
7
|
The Ruby OCR SDK supports the [Driver License API](https://platform.mindee.com/mindee/us_driver_license).
|
5
8
|
|
@@ -27,6 +30,7 @@ puts result.document
|
|
27
30
|
|
28
31
|
# Print the document-level parsed data
|
29
32
|
# puts result.document.inference.prediction
|
33
|
+
|
30
34
|
```
|
31
35
|
|
32
36
|
**Output (RST):**
|
@@ -100,7 +104,7 @@ A typical `Field` object will have the following attributes:
|
|
100
104
|
* **confidence** (Float, nil): the confidence score of the field prediction.
|
101
105
|
* **bounding_box** (`Mindee::Geometry::Quadrilateral`, `nil`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
|
102
106
|
* **polygon** (`Mindee::Geometry::Polygon`, `nil`): contains the relative vertices coordinates (`Point`) of a polygon containing the field in the image.
|
103
|
-
* **page_id** (`Integer`, `nil`): the ID of the page,
|
107
|
+
* **page_id** (`Integer`, `nil`): the ID of the page, always `nil` when at document-level.
|
104
108
|
* **reconstructed** (`Boolean`): indicates whether an object was reconstructed (not extracted as the API gave it).
|
105
109
|
|
106
110
|
|
@@ -122,7 +126,7 @@ The position field `PositionField` does not implement all the basic `Field` attr
|
|
122
126
|
The text field `StringField` only has one constraint: it's **value** is a `String` (or `nil`).
|
123
127
|
|
124
128
|
## Page-Level Fields
|
125
|
-
Some fields are constrained to the page level, and so will not be retrievable
|
129
|
+
Some fields are constrained to the page level, and so will not be retrievable at document level.
|
126
130
|
|
127
131
|
# Attributes
|
128
132
|
The following fields are extracted for Driver License V1:
|
@@ -0,0 +1,208 @@
|
|
1
|
+
---
|
2
|
+
title: US Healthcare Card OCR Ruby
|
3
|
+
category: 622b805aaec68102ea7fcbc2
|
4
|
+
slug: ruby-us-healthcare-card-ocr
|
5
|
+
parentDoc: 6294d97ee723f1008d2ab28e
|
6
|
+
---
|
7
|
+
The Ruby OCR SDK supports the [Healthcare Card API](https://platform.mindee.com/mindee/us_healthcare_cards).
|
8
|
+
|
9
|
+
Using the [sample below](https://github.com/mindee/client-lib-test-data/blob/main/products/us_healthcare_cards/default_sample.jpg), we are going to illustrate how to extract the data that we want using the OCR SDK.
|
10
|
+

|
11
|
+
|
12
|
+
# Quick-Start
|
13
|
+
```rb
|
14
|
+
require 'mindee'
|
15
|
+
|
16
|
+
# Init a new client
|
17
|
+
mindee_client = Mindee::Client.new(api_key: 'my-api-key')
|
18
|
+
|
19
|
+
# Load a file from disk
|
20
|
+
input_source = mindee_client.source_from_path('/path/to/the/file.ext')
|
21
|
+
|
22
|
+
# Parse the file
|
23
|
+
result = mindee_client.enqueue_and_parse(
|
24
|
+
input_source,
|
25
|
+
Mindee::Product::US::HealthcareCard::HealthcareCardV1
|
26
|
+
)
|
27
|
+
|
28
|
+
# Print a full summary of the parsed data in RST format
|
29
|
+
puts result.document
|
30
|
+
|
31
|
+
# Print the document-level parsed data
|
32
|
+
# puts result.document.inference.prediction
|
33
|
+
|
34
|
+
```
|
35
|
+
|
36
|
+
**Output (RST):**
|
37
|
+
```rst
|
38
|
+
########
|
39
|
+
Document
|
40
|
+
########
|
41
|
+
:Mindee ID: 0ced9f49-00c0-4a1d-8221-4a1538813a95
|
42
|
+
:Filename: default_sample.jpg
|
43
|
+
|
44
|
+
Inference
|
45
|
+
#########
|
46
|
+
:Product: mindee/us_healthcare_cards v1.0
|
47
|
+
:Rotation applied: No
|
48
|
+
|
49
|
+
Prediction
|
50
|
+
==========
|
51
|
+
:Company Name: UnitedHealthcare
|
52
|
+
:Member Name: SUBSCRIBER SMITH
|
53
|
+
:Member ID: 123456789
|
54
|
+
:Issuer 80840:
|
55
|
+
:Dependents: SPOUSE SMITH
|
56
|
+
CHILD1 SMITH
|
57
|
+
CHILD2 SMITH
|
58
|
+
CHILD3 SMITH
|
59
|
+
:Group Number: 98765
|
60
|
+
:Payer ID: 87726
|
61
|
+
:RX BIN: 610279
|
62
|
+
:RX GRP: UHEALTH
|
63
|
+
:RX PCN: 9999
|
64
|
+
:copays:
|
65
|
+
+--------------+--------------+
|
66
|
+
| Service Fees | Service Name |
|
67
|
+
+==============+==============+
|
68
|
+
| 20.00 | office visit |
|
69
|
+
+--------------+--------------+
|
70
|
+
| 300.00 | emergency |
|
71
|
+
+--------------+--------------+
|
72
|
+
| 75.00 | urgent care |
|
73
|
+
+--------------+--------------+
|
74
|
+
| 30.00 | specialist |
|
75
|
+
+--------------+--------------+
|
76
|
+
:Enrollment Date: 2023-09-13
|
77
|
+
```
|
78
|
+
|
79
|
+
# Field Types
|
80
|
+
## Standard Fields
|
81
|
+
These fields are generic and used in several products.
|
82
|
+
|
83
|
+
### Basic Field
|
84
|
+
Each prediction object contains a set of fields that inherit from the generic `Field` class.
|
85
|
+
A typical `Field` object will have the following attributes:
|
86
|
+
|
87
|
+
* **value** (`String`, `Float`, `Integer`, `Boolean`): corresponds to the field value. Can be `nil` if no value was extracted.
|
88
|
+
* **confidence** (Float, nil): the confidence score of the field prediction.
|
89
|
+
* **bounding_box** (`Mindee::Geometry::Quadrilateral`, `nil`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
|
90
|
+
* **polygon** (`Mindee::Geometry::Polygon`, `nil`): contains the relative vertices coordinates (`Point`) of a polygon containing the field in the image.
|
91
|
+
* **page_id** (`Integer`, `nil`): the ID of the page, always `nil` when at document-level.
|
92
|
+
* **reconstructed** (`Boolean`): indicates whether an object was reconstructed (not extracted as the API gave it).
|
93
|
+
|
94
|
+
|
95
|
+
Aside from the previous attributes, all basic fields have access to a `to_s` method that can be used to print their value as a string.
|
96
|
+
|
97
|
+
### Date Field
|
98
|
+
Aside from the basic `Field` attributes, the date field `DateField` also implements the following:
|
99
|
+
|
100
|
+
* **date_object** (`Date`): an accessible representation of the value as a JavaScript object.
|
101
|
+
|
102
|
+
### String Field
|
103
|
+
The text field `StringField` only has one constraint: it's **value** is a `String` (or `nil`).
|
104
|
+
|
105
|
+
## Specific Fields
|
106
|
+
Fields which are specific to this product; they are not used in any other product.
|
107
|
+
|
108
|
+
### copays Field
|
109
|
+
Is a fixed amount for a covered service.
|
110
|
+
|
111
|
+
A `HealthcareCardV1Copay` implements the following attributes:
|
112
|
+
|
113
|
+
* `service_fees` (Float): The price of service.
|
114
|
+
* `service_name` (String): The name of service of the copay.
|
115
|
+
|
116
|
+
# Attributes
|
117
|
+
The following fields are extracted for Healthcare Card V1:
|
118
|
+
|
119
|
+
## Company Name
|
120
|
+
**company_name** ([StringField](#string-field)): The name of the company that provides the healthcare plan.
|
121
|
+
|
122
|
+
```rb
|
123
|
+
puts result.document.inference.prediction.company_name.value
|
124
|
+
```
|
125
|
+
|
126
|
+
## copays
|
127
|
+
**copays** (Array<[HealthcareCardV1Copay](#copays-field)>): Is a fixed amount for a covered service.
|
128
|
+
|
129
|
+
```rb
|
130
|
+
for copays_elem in result.document.inference.prediction.copays do
|
131
|
+
puts copays_elem.value
|
132
|
+
end
|
133
|
+
```
|
134
|
+
|
135
|
+
## Dependents
|
136
|
+
**dependents** (Array<[StringField](#string-field)>): The list of dependents covered by the healthcare plan.
|
137
|
+
|
138
|
+
```rb
|
139
|
+
for dependents_elem in result.document.inference.prediction.dependents do
|
140
|
+
puts dependents_elem.value
|
141
|
+
end
|
142
|
+
```
|
143
|
+
|
144
|
+
## Enrollment Date
|
145
|
+
**enrollment_date** ([DateField](#date-field)): The date when the member enrolled in the healthcare plan.
|
146
|
+
|
147
|
+
```rb
|
148
|
+
puts result.document.inference.prediction.enrollment_date.value
|
149
|
+
```
|
150
|
+
|
151
|
+
## Group Number
|
152
|
+
**group_number** ([StringField](#string-field)): The group number associated with the healthcare plan.
|
153
|
+
|
154
|
+
```rb
|
155
|
+
puts result.document.inference.prediction.group_number.value
|
156
|
+
```
|
157
|
+
|
158
|
+
## Issuer 80840
|
159
|
+
**issuer80840** ([StringField](#string-field)): The organization that issued the healthcare plan.
|
160
|
+
|
161
|
+
```rb
|
162
|
+
puts result.document.inference.prediction.issuer80840.value
|
163
|
+
```
|
164
|
+
|
165
|
+
## Member ID
|
166
|
+
**member_id** ([StringField](#string-field)): The unique identifier for the member in the healthcare system.
|
167
|
+
|
168
|
+
```rb
|
169
|
+
puts result.document.inference.prediction.member_id.value
|
170
|
+
```
|
171
|
+
|
172
|
+
## Member Name
|
173
|
+
**member_name** ([StringField](#string-field)): The name of the member covered by the healthcare plan.
|
174
|
+
|
175
|
+
```rb
|
176
|
+
puts result.document.inference.prediction.member_name.value
|
177
|
+
```
|
178
|
+
|
179
|
+
## Payer ID
|
180
|
+
**payer_id** ([StringField](#string-field)): The unique identifier for the payer in the healthcare system.
|
181
|
+
|
182
|
+
```rb
|
183
|
+
puts result.document.inference.prediction.payer_id.value
|
184
|
+
```
|
185
|
+
|
186
|
+
## RX BIN
|
187
|
+
**rx_bin** ([StringField](#string-field)): The BIN number for prescription drug coverage.
|
188
|
+
|
189
|
+
```rb
|
190
|
+
puts result.document.inference.prediction.rx_bin.value
|
191
|
+
```
|
192
|
+
|
193
|
+
## RX GRP
|
194
|
+
**rx_grp** ([StringField](#string-field)): The group number for prescription drug coverage.
|
195
|
+
|
196
|
+
```rb
|
197
|
+
puts result.document.inference.prediction.rx_grp.value
|
198
|
+
```
|
199
|
+
|
200
|
+
## RX PCN
|
201
|
+
**rx_pcn** ([StringField](#string-field)): The PCN number for prescription drug coverage.
|
202
|
+
|
203
|
+
```rb
|
204
|
+
puts result.document.inference.prediction.rx_pcn.value
|
205
|
+
```
|
206
|
+
|
207
|
+
# Questions?
|
208
|
+
[Join our Slack](https://join.slack.com/t/mindee-community/shared_invite/zt-2d0ds7dtz-DPAF81ZqTy20chsYpQBW5g)
|
data/docs/us_mail_v2.md
CHANGED
@@ -1,5 +1,8 @@
|
|
1
1
|
---
|
2
2
|
title: US US Mail OCR Ruby
|
3
|
+
category: 622b805aaec68102ea7fcbc2
|
4
|
+
slug: ruby-us-us-mail-ocr
|
5
|
+
parentDoc: 6294d97ee723f1008d2ab28e
|
3
6
|
---
|
4
7
|
The Ruby OCR SDK supports the [US Mail API](https://platform.mindee.com/mindee/us_mail).
|
5
8
|
|
@@ -27,6 +30,7 @@ puts result.document
|
|
27
30
|
|
28
31
|
# Print the document-level parsed data
|
29
32
|
# puts result.document.inference.prediction
|
33
|
+
|
30
34
|
```
|
31
35
|
|
32
36
|
**Output (RST):**
|
@@ -59,7 +63,7 @@ A typical `Field` object will have the following attributes:
|
|
59
63
|
* **confidence** (Float, nil): the confidence score of the field prediction.
|
60
64
|
* **bounding_box** (`Mindee::Geometry::Quadrilateral`, `nil`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
|
61
65
|
* **polygon** (`Mindee::Geometry::Polygon`, `nil`): contains the relative vertices coordinates (`Point`) of a polygon containing the field in the image.
|
62
|
-
* **page_id** (`Integer`, `nil`): the ID of the page,
|
66
|
+
* **page_id** (`Integer`, `nil`): the ID of the page, always `nil` when at document-level.
|
63
67
|
* **reconstructed** (`Boolean`): indicates whether an object was reconstructed (not extracted as the API gave it).
|
64
68
|
|
65
69
|
|
data/docs/us_w9_v1.md
CHANGED
@@ -1,5 +1,8 @@
|
|
1
1
|
---
|
2
2
|
title: US W9 OCR Ruby
|
3
|
+
category: 622b805aaec68102ea7fcbc2
|
4
|
+
slug: ruby-us-w9-ocr
|
5
|
+
parentDoc: 6294d97ee723f1008d2ab28e
|
3
6
|
---
|
4
7
|
The Ruby OCR SDK supports the [W9 API](https://platform.mindee.com/mindee/us_w9).
|
5
8
|
|
@@ -24,6 +27,7 @@ result = mindee_client.parse(
|
|
24
27
|
|
25
28
|
# Print a full summary of the parsed data in RST format
|
26
29
|
puts result.document
|
30
|
+
|
27
31
|
```
|
28
32
|
|
29
33
|
**Output (RST):**
|
@@ -73,7 +77,7 @@ A typical `Field` object will have the following attributes:
|
|
73
77
|
* **confidence** (Float, nil): the confidence score of the field prediction.
|
74
78
|
* **bounding_box** (`Mindee::Geometry::Quadrilateral`, `nil`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
|
75
79
|
* **polygon** (`Mindee::Geometry::Polygon`, `nil`): contains the relative vertices coordinates (`Point`) of a polygon containing the field in the image.
|
76
|
-
* **page_id** (`Integer`, `nil`): the ID of the page,
|
80
|
+
* **page_id** (`Integer`, `nil`): the ID of the page, always `nil` when at document-level.
|
77
81
|
* **reconstructed** (`Boolean`): indicates whether an object was reconstructed (not extracted as the API gave it).
|
78
82
|
|
79
83
|
|
@@ -90,7 +94,7 @@ The position field `PositionField` does not implement all the basic `Field` attr
|
|
90
94
|
The text field `StringField` only has one constraint: it's **value** is a `String` (or `nil`).
|
91
95
|
|
92
96
|
## Page-Level Fields
|
93
|
-
Some fields are constrained to the page level, and so will not be retrievable
|
97
|
+
Some fields are constrained to the page level, and so will not be retrievable at document level.
|
94
98
|
|
95
99
|
# Attributes
|
96
100
|
The following fields are extracted for W9 V1:
|
@@ -0,0 +1,43 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'mindee'
|
4
|
+
|
5
|
+
# Init a new client
|
6
|
+
mindee_client = Mindee::Client.new(api_key: 'my-api-key')
|
7
|
+
|
8
|
+
# Load a file from disk
|
9
|
+
input_source = mindee_client.source_from_path('/path/to/the/file.ext')
|
10
|
+
|
11
|
+
if input_source.pdf?
|
12
|
+
pdf_extractor = Mindee::Extraction::PdfExtractor.new(input_source)
|
13
|
+
if pdf_extractor.page_count > 1
|
14
|
+
invoice_splitter_response = mindee_client.enqueue_and_parse(
|
15
|
+
input_source,
|
16
|
+
Mindee::Product::InvoiceSplitter::InvoiceSplitterV1
|
17
|
+
)
|
18
|
+
page_groups = invoice_splitter_response.document.inference.prediction.invoice_page_groups
|
19
|
+
extracted_pdfs = pdf_extractor.extract_invoices(page_groups, strict: false)
|
20
|
+
extracted_pdfs.each do |extracted_pdf|
|
21
|
+
# Optional: Save the files locally
|
22
|
+
# extracted_pdf.write_to_file("output/path")
|
23
|
+
|
24
|
+
invoice_result = mindee_client.parse(
|
25
|
+
InvoiceV4,
|
26
|
+
extracted_pdf.as_source
|
27
|
+
)
|
28
|
+
puts invoice_result
|
29
|
+
end
|
30
|
+
else
|
31
|
+
invoice_result = mindee_client.parse(
|
32
|
+
input_source,
|
33
|
+
Mindee::Product::Invoice::InvoiceV4
|
34
|
+
)
|
35
|
+
puts invoice_result.document
|
36
|
+
end
|
37
|
+
else
|
38
|
+
invoice_result = mindee_client.parse(
|
39
|
+
input_source,
|
40
|
+
Mindee::Product::Invoice::InvoiceV4
|
41
|
+
)
|
42
|
+
puts invoice_result.document
|
43
|
+
end
|