cloudmersive-documentai-api-client 2.2.0 → 2.2.1
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/README.md +24 -10
- data/cloudmersive-documentai-api-client.gemspec +3 -3
- data/docs/AdvancedExtractClassificationRequest.md +3 -0
- data/docs/AdvancedExtractFieldsRequest.md +3 -0
- data/docs/AnalyzeApi.md +58 -2
- data/docs/DocumentAdvancedClassificationResult.md +1 -0
- data/docs/DocumentPolicyRequest.md +1 -0
- data/docs/DocumentQuestionAnswerItem.md +11 -0
- data/docs/DocumentQuestionAnswersResult.md +10 -0
- data/docs/DocumentQuestionBoolean.md +9 -0
- data/docs/DocumentQuestionChoiceItem.md +9 -0
- data/docs/DocumentQuestionFreeResponse.md +9 -0
- data/docs/DocumentQuestionMultipleChoice.md +10 -0
- data/docs/DocumentQuestionsRequest.md +12 -0
- data/docs/ExtractApi.md +76 -14
- data/docs/ExtractFieldsAdvancedResponse.md +10 -0
- data/docs/FieldAdvancedValue.md +9 -0
- data/docs/FieldValue.md +2 -1
- data/docs/RunBatchJobApi.md +9 -9
- data/docs/SplitDocumentResponse.md +9 -0
- data/docs/SubDocument.md +11 -0
- data/lib/cloudmersive-documentai-api-client/api/analyze_api.rb +54 -4
- data/lib/cloudmersive-documentai-api-client/api/extract_api.rb +85 -25
- data/lib/cloudmersive-documentai-api-client/api/run_batch_job_api.rb +14 -14
- data/lib/cloudmersive-documentai-api-client/api_client.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/api_error.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/configuration.rb +3 -3
- data/lib/cloudmersive-documentai-api-client/models/advanced_extract_classification_request.rb +36 -6
- data/lib/cloudmersive-documentai-api-client/models/advanced_extract_fields_request.rb +36 -6
- data/lib/cloudmersive-documentai-api-client/models/document_advanced_classification_result.rb +16 -6
- data/lib/cloudmersive-documentai-api-client/models/document_categories.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/document_classification_result.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/document_policy_request.rb +16 -6
- data/lib/cloudmersive-documentai-api-client/models/document_policy_result.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/document_question_answer_item.rb +216 -0
- data/lib/cloudmersive-documentai-api-client/models/document_question_answers_result.rb +207 -0
- data/lib/cloudmersive-documentai-api-client/models/document_question_boolean.rb +196 -0
- data/lib/cloudmersive-documentai-api-client/models/document_question_choice_item.rb +196 -0
- data/lib/cloudmersive-documentai-api-client/models/document_question_free_response.rb +196 -0
- data/lib/cloudmersive-documentai-api-client/models/document_question_multiple_choice.rb +208 -0
- data/lib/cloudmersive-documentai-api-client/models/document_questions_request.rb +246 -0
- data/lib/cloudmersive-documentai-api-client/models/extract_barcodes_ai_response.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/extract_document_batch_job_result.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/extract_document_job_status_result.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/extract_fields_advanced_response.rb +208 -0
- data/lib/cloudmersive-documentai-api-client/models/extract_fields_and_tables_response.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/extract_fields_response.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/extract_tables_response.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/extract_text_response.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/extracted_barcode_item.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/extracted_text_page.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/field_advanced_value.rb +196 -0
- data/lib/cloudmersive-documentai-api-client/models/field_to_extract.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/field_value.rb +19 -7
- data/lib/cloudmersive-documentai-api-client/models/policy_rule.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/policy_rule_violation.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/split_document_response.rb +198 -0
- data/lib/cloudmersive-documentai-api-client/models/sub_document.rb +231 -0
- data/lib/cloudmersive-documentai-api-client/models/summarize_document_response.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/table_result.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/table_result_cell.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/models/table_result_row.rb +2 -2
- data/lib/cloudmersive-documentai-api-client/version.rb +3 -3
- data/lib/cloudmersive-documentai-api-client.rb +13 -2
- data/spec/api/analyze_api_spec.rb +15 -3
- data/spec/api/extract_api_spec.rb +28 -13
- data/spec/api/run_batch_job_api_spec.rb +8 -8
- data/spec/api_client_spec.rb +2 -2
- data/spec/configuration_spec.rb +5 -5
- data/spec/models/advanced_extract_classification_request_spec.rb +20 -2
- data/spec/models/advanced_extract_fields_request_spec.rb +20 -2
- data/spec/models/document_advanced_classification_result_spec.rb +8 -2
- data/spec/models/document_categories_spec.rb +2 -2
- data/spec/models/document_classification_result_spec.rb +2 -2
- data/spec/models/document_policy_request_spec.rb +8 -2
- data/spec/models/document_policy_result_spec.rb +2 -2
- data/spec/models/document_question_answer_item_spec.rb +59 -0
- data/spec/models/document_question_answers_result_spec.rb +53 -0
- data/spec/models/document_question_boolean_spec.rb +47 -0
- data/spec/models/document_question_choice_item_spec.rb +47 -0
- data/spec/models/document_question_free_response_spec.rb +47 -0
- data/spec/models/document_question_multiple_choice_spec.rb +53 -0
- data/spec/models/document_questions_request_spec.rb +65 -0
- data/spec/models/extract_barcodes_ai_response_spec.rb +2 -2
- data/spec/models/extract_document_batch_job_result_spec.rb +2 -2
- data/spec/models/extract_document_job_status_result_spec.rb +2 -2
- data/spec/models/extract_fields_advanced_response_spec.rb +53 -0
- data/spec/models/extract_fields_and_tables_response_spec.rb +2 -2
- data/spec/models/extract_fields_response_spec.rb +2 -2
- data/spec/models/extract_tables_response_spec.rb +2 -2
- data/spec/models/extract_text_response_spec.rb +2 -2
- data/spec/models/extracted_barcode_item_spec.rb +2 -2
- data/spec/models/extracted_text_page_spec.rb +2 -2
- data/spec/models/field_advanced_value_spec.rb +47 -0
- data/spec/models/field_to_extract_spec.rb +2 -2
- data/spec/models/field_value_spec.rb +8 -2
- data/spec/models/policy_rule_spec.rb +2 -2
- data/spec/models/policy_rule_violation_spec.rb +2 -2
- data/spec/models/split_document_response_spec.rb +47 -0
- data/spec/models/sub_document_spec.rb +59 -0
- data/spec/models/summarize_document_response_spec.rb +2 -2
- data/spec/models/table_result_cell_spec.rb +2 -2
- data/spec/models/table_result_row_spec.rb +2 -2
- data/spec/models/table_result_spec.rb +2 -2
- data/spec/spec_helper.rb +2 -2
- metadata +36 -3
data/docs/RunBatchJobApi.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# CloudmersiveDocumentaiApiClient::RunBatchJobApi
|
|
2
2
|
|
|
3
|
-
All URIs are relative to *https://
|
|
3
|
+
All URIs are relative to *https://api.cloudmersive.com*
|
|
4
4
|
|
|
5
5
|
Method | HTTP request | Description
|
|
6
6
|
------------- | ------------- | -------------
|
|
@@ -16,7 +16,7 @@ Method | HTTP request | Description
|
|
|
16
16
|
|
|
17
17
|
Extract All Fields and Tables of Data from a Document using AI as a Batch Job
|
|
18
18
|
|
|
19
|
-
Creates an async batch job for processing a large document as an AI batch job. Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
19
|
+
Creates an async batch job for processing a large document as an AI batch job. Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.
|
|
20
20
|
|
|
21
21
|
### Example
|
|
22
22
|
```ruby
|
|
@@ -73,7 +73,7 @@ Name | Type | Description | Notes
|
|
|
73
73
|
|
|
74
74
|
Extract Classification or Category from a Document using AI as a Batch Job
|
|
75
75
|
|
|
76
|
-
Creates an async batch job for processing a large document as an AI batch job. Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
76
|
+
Creates an async batch job for processing a large document as an AI batch job. Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.
|
|
77
77
|
|
|
78
78
|
### Example
|
|
79
79
|
```ruby
|
|
@@ -132,7 +132,7 @@ Name | Type | Description | Notes
|
|
|
132
132
|
|
|
133
133
|
Extract Field Values from a Document using Advanced AI as a Batch Job
|
|
134
134
|
|
|
135
|
-
Creates an async batch job for processing a large document as an AI batch job. Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
135
|
+
Creates an async batch job for processing a large document as an AI batch job. Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.
|
|
136
136
|
|
|
137
137
|
### Example
|
|
138
138
|
```ruby
|
|
@@ -150,7 +150,7 @@ api_instance = CloudmersiveDocumentaiApiClient::RunBatchJobApi.new
|
|
|
150
150
|
|
|
151
151
|
opts = {
|
|
152
152
|
recognition_mode: 'recognition_mode_example', # String | Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
153
|
-
body: CloudmersiveDocumentaiApiClient::AdvancedExtractFieldsRequest.new # AdvancedExtractFieldsRequest |
|
|
153
|
+
body: CloudmersiveDocumentaiApiClient::AdvancedExtractFieldsRequest.new # AdvancedExtractFieldsRequest | Input document and parameters
|
|
154
154
|
}
|
|
155
155
|
|
|
156
156
|
begin
|
|
@@ -167,7 +167,7 @@ end
|
|
|
167
167
|
Name | Type | Description | Notes
|
|
168
168
|
------------- | ------------- | ------------- | -------------
|
|
169
169
|
**recognition_mode** | **String**| Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images | [optional]
|
|
170
|
-
**body** | [**AdvancedExtractFieldsRequest**](AdvancedExtractFieldsRequest.md)|
|
|
170
|
+
**body** | [**AdvancedExtractFieldsRequest**](AdvancedExtractFieldsRequest.md)| Input document and parameters | [optional]
|
|
171
171
|
|
|
172
172
|
### Return type
|
|
173
173
|
|
|
@@ -189,7 +189,7 @@ Name | Type | Description | Notes
|
|
|
189
189
|
|
|
190
190
|
Extract Text from a Document using AI as a Batch Job
|
|
191
191
|
|
|
192
|
-
Creates an async batch job for processing a large document as an AI batch job. Input document formats supported include DOCX, PDF, PNG and JPG. Supports a wide range of languages.
|
|
192
|
+
Creates an async batch job for processing a large document as an AI batch job. Input document formats supported include DOCX, PDF, PNG and JPG. Supports a wide range of languages. Requires Managed Instance or Private Cloud deployment.
|
|
193
193
|
|
|
194
194
|
### Example
|
|
195
195
|
```ruby
|
|
@@ -263,7 +263,7 @@ end
|
|
|
263
263
|
api_instance = CloudmersiveDocumentaiApiClient::RunBatchJobApi.new
|
|
264
264
|
|
|
265
265
|
opts = {
|
|
266
|
-
async_job_id: 'async_job_id_example' # String |
|
|
266
|
+
async_job_id: 'async_job_id_example' # String | Job ID for the batch job to get the status of
|
|
267
267
|
}
|
|
268
268
|
|
|
269
269
|
begin
|
|
@@ -279,7 +279,7 @@ end
|
|
|
279
279
|
|
|
280
280
|
Name | Type | Description | Notes
|
|
281
281
|
------------- | ------------- | ------------- | -------------
|
|
282
|
-
**async_job_id** | **String**|
|
|
282
|
+
**async_job_id** | **String**| Job ID for the batch job to get the status of | [optional]
|
|
283
283
|
|
|
284
284
|
### Return type
|
|
285
285
|
|
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
# CloudmersiveDocumentaiApiClient::SplitDocumentResponse
|
|
2
|
+
|
|
3
|
+
## Properties
|
|
4
|
+
Name | Type | Description | Notes
|
|
5
|
+
------------ | ------------- | ------------- | -------------
|
|
6
|
+
**successful** | **BOOLEAN** | True if successful, false otherwise | [optional]
|
|
7
|
+
**sub_documents** | [**Array<SubDocument>**](SubDocument.md) | The sub-documents that were identified and extracted from the input document | [optional]
|
|
8
|
+
|
|
9
|
+
|
data/docs/SubDocument.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
# CloudmersiveDocumentaiApiClient::SubDocument
|
|
2
|
+
|
|
3
|
+
## Properties
|
|
4
|
+
Name | Type | Description | Notes
|
|
5
|
+
------------ | ------------- | ------------- | -------------
|
|
6
|
+
**start_page** | **Integer** | Starting page number (1-indexed) of this sub-document in the original document | [optional]
|
|
7
|
+
**end_page** | **Integer** | Ending page number (1-indexed) of this sub-document in the original document | [optional]
|
|
8
|
+
**document_description** | **String** | Description of the sub-document including document type and any identifying information such as person name | [optional]
|
|
9
|
+
**file_bytes** | **String** | The extracted sub-document as PDF file bytes | [optional]
|
|
10
|
+
|
|
11
|
+
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
=begin
|
|
2
2
|
#Document AI API
|
|
3
3
|
|
|
4
|
-
#
|
|
4
|
+
#Extract structured data including named fields, tables, barcodes, classifications, and summaries from common document formats, scanned documents, and photos of documents using AI. Also supports handwriting and low quality photos and scans, as well as digital document input. Supports a wide range of languages, and is able to analyze and infer semantic structure from the visual layout for documents.
|
|
5
5
|
|
|
6
6
|
OpenAPI spec version: v1
|
|
7
|
-
|
|
7
|
+
Contact: support@cloudmersive.com
|
|
8
8
|
Generated by: https://github.com/swagger-api/swagger-codegen.git
|
|
9
9
|
Swagger Codegen version: 2.4.14
|
|
10
10
|
|
|
@@ -19,8 +19,58 @@ module CloudmersiveDocumentaiApiClient
|
|
|
19
19
|
def initialize(api_client = ApiClient.default)
|
|
20
20
|
@api_client = api_client
|
|
21
21
|
end
|
|
22
|
+
# Answer Questions about a Document in a structured way using Advanced AI
|
|
23
|
+
# Answer boolean (yes/no), multiple-choice and free-response questions about the contents of a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.
|
|
24
|
+
# @param [Hash] opts the optional parameters
|
|
25
|
+
# @option opts [DocumentQuestionsRequest] :body Input request, including document and questions
|
|
26
|
+
# @return [DocumentQuestionAnswersResult]
|
|
27
|
+
def answer_questions(opts = {})
|
|
28
|
+
data, _status_code, _headers = answer_questions_with_http_info(opts)
|
|
29
|
+
data
|
|
30
|
+
end
|
|
31
|
+
|
|
32
|
+
# Answer Questions about a Document in a structured way using Advanced AI
|
|
33
|
+
# Answer boolean (yes/no), multiple-choice and free-response questions about the contents of a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.
|
|
34
|
+
# @param [Hash] opts the optional parameters
|
|
35
|
+
# @option opts [DocumentQuestionsRequest] :body Input request, including document and questions
|
|
36
|
+
# @return [Array<(DocumentQuestionAnswersResult, Fixnum, Hash)>] DocumentQuestionAnswersResult data, response status code and response headers
|
|
37
|
+
def answer_questions_with_http_info(opts = {})
|
|
38
|
+
if @api_client.config.debugging
|
|
39
|
+
@api_client.config.logger.debug 'Calling API: AnalyzeApi.answer_questions ...'
|
|
40
|
+
end
|
|
41
|
+
# resource path
|
|
42
|
+
local_var_path = '/document-ai/document/analyze/answer-questions'
|
|
43
|
+
|
|
44
|
+
# query parameters
|
|
45
|
+
query_params = {}
|
|
46
|
+
|
|
47
|
+
# header parameters
|
|
48
|
+
header_params = {}
|
|
49
|
+
# HTTP header 'Accept' (if needed)
|
|
50
|
+
header_params['Accept'] = @api_client.select_header_accept(['text/plain', 'application/json', 'text/json'])
|
|
51
|
+
# HTTP header 'Content-Type'
|
|
52
|
+
header_params['Content-Type'] = @api_client.select_header_content_type(['application/json', 'text/json', 'application/*+json'])
|
|
53
|
+
|
|
54
|
+
# form parameters
|
|
55
|
+
form_params = {}
|
|
56
|
+
|
|
57
|
+
# http body (model)
|
|
58
|
+
post_body = @api_client.object_to_http_body(opts[:'body'])
|
|
59
|
+
auth_names = ['Apikey']
|
|
60
|
+
data, status_code, headers = @api_client.call_api(:POST, local_var_path,
|
|
61
|
+
:header_params => header_params,
|
|
62
|
+
:query_params => query_params,
|
|
63
|
+
:form_params => form_params,
|
|
64
|
+
:body => post_body,
|
|
65
|
+
:auth_names => auth_names,
|
|
66
|
+
:return_type => 'DocumentQuestionAnswersResult')
|
|
67
|
+
if @api_client.config.debugging
|
|
68
|
+
@api_client.config.logger.debug "API called: AnalyzeApi#answer_questions\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
|
69
|
+
end
|
|
70
|
+
return data, status_code, headers
|
|
71
|
+
end
|
|
22
72
|
# Enforce Policies to a Document to allow or block it using Advanced AI
|
|
23
|
-
# Enforce Policies to a Document to allow or block it using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
73
|
+
# Enforce Policies to a Document to allow or block it using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.
|
|
24
74
|
# @param [Hash] opts the optional parameters
|
|
25
75
|
# @option opts [DocumentPolicyRequest] :body Input request, including document and policy rules
|
|
26
76
|
# @return [DocumentPolicyResult]
|
|
@@ -30,7 +80,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
30
80
|
end
|
|
31
81
|
|
|
32
82
|
# Enforce Policies to a Document to allow or block it using Advanced AI
|
|
33
|
-
# Enforce Policies to a Document to allow or block it using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
83
|
+
# Enforce Policies to a Document to allow or block it using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.
|
|
34
84
|
# @param [Hash] opts the optional parameters
|
|
35
85
|
# @option opts [DocumentPolicyRequest] :body Input request, including document and policy rules
|
|
36
86
|
# @return [Array<(DocumentPolicyResult, Fixnum, Hash)>] DocumentPolicyResult data, response status code and response headers
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
=begin
|
|
2
2
|
#Document AI API
|
|
3
3
|
|
|
4
|
-
#
|
|
4
|
+
#Extract structured data including named fields, tables, barcodes, classifications, and summaries from common document formats, scanned documents, and photos of documents using AI. Also supports handwriting and low quality photos and scans, as well as digital document input. Supports a wide range of languages, and is able to analyze and infer semantic structure from the visual layout for documents.
|
|
5
5
|
|
|
6
6
|
OpenAPI spec version: v1
|
|
7
|
-
|
|
7
|
+
Contact: support@cloudmersive.com
|
|
8
8
|
Generated by: https://github.com/swagger-api/swagger-codegen.git
|
|
9
9
|
Swagger Codegen version: 2.4.14
|
|
10
10
|
|
|
@@ -20,9 +20,10 @@ module CloudmersiveDocumentaiApiClient
|
|
|
20
20
|
@api_client = api_client
|
|
21
21
|
end
|
|
22
22
|
# Extract All Fields and Tables of Data from a Document using AI
|
|
23
|
-
# Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
23
|
+
# Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
24
24
|
# @param [Hash] opts the optional parameters
|
|
25
25
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
26
|
+
# @option opts [String] :preprocessing Optional: Set the level of image pre-processing to enhance accuracy. Possible values are 'Auto' (default), 'Paged', and 'Compatability'. Use 'Paged' to treat each page as a separate document for extraction (requires Advanced recognitionMode). Default is Auto.
|
|
26
27
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
27
28
|
# @return [ExtractFieldsAndTablesResponse]
|
|
28
29
|
def extract_all_fields_and_tables(opts = {})
|
|
@@ -31,9 +32,10 @@ module CloudmersiveDocumentaiApiClient
|
|
|
31
32
|
end
|
|
32
33
|
|
|
33
34
|
# Extract All Fields and Tables of Data from a Document using AI
|
|
34
|
-
# Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
35
|
+
# Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
35
36
|
# @param [Hash] opts the optional parameters
|
|
36
37
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
38
|
+
# @option opts [String] :preprocessing Optional: Set the level of image pre-processing to enhance accuracy. Possible values are 'Auto' (default), 'Paged', and 'Compatability'. Use 'Paged' to treat each page as a separate document for extraction (requires Advanced recognitionMode). Default is Auto.
|
|
37
39
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
38
40
|
# @return [Array<(ExtractFieldsAndTablesResponse, Fixnum, Hash)>] ExtractFieldsAndTablesResponse data, response status code and response headers
|
|
39
41
|
def extract_all_fields_and_tables_with_http_info(opts = {})
|
|
@@ -53,6 +55,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
53
55
|
# HTTP header 'Content-Type'
|
|
54
56
|
header_params['Content-Type'] = @api_client.select_header_content_type(['multipart/form-data'])
|
|
55
57
|
header_params[:'recognitionMode'] = opts[:'recognition_mode'] if !opts[:'recognition_mode'].nil?
|
|
58
|
+
header_params[:'preprocessing'] = opts[:'preprocessing'] if !opts[:'preprocessing'].nil?
|
|
56
59
|
|
|
57
60
|
# form parameters
|
|
58
61
|
form_params = {}
|
|
@@ -74,7 +77,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
74
77
|
return data, status_code, headers
|
|
75
78
|
end
|
|
76
79
|
# Extract Barcodes of from a Document using AI
|
|
77
|
-
# Extract all barcodes from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
80
|
+
# Extract all barcodes from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG, HEIC and WEBP. Consumes 100 API calls per page.
|
|
78
81
|
# @param [Hash] opts the optional parameters
|
|
79
82
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
80
83
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
@@ -85,7 +88,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
85
88
|
end
|
|
86
89
|
|
|
87
90
|
# Extract Barcodes of from a Document using AI
|
|
88
|
-
# Extract all barcodes from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
91
|
+
# Extract all barcodes from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG, HEIC and WEBP. Consumes 100 API calls per page.
|
|
89
92
|
# @param [Hash] opts the optional parameters
|
|
90
93
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
91
94
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
@@ -128,7 +131,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
128
131
|
return data, status_code, headers
|
|
129
132
|
end
|
|
130
133
|
# Extract Classification or Category from a Document using AI
|
|
131
|
-
# Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
134
|
+
# Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
132
135
|
# @param [Hash] opts the optional parameters
|
|
133
136
|
# @option opts [String] :categories Desired classification to extract
|
|
134
137
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
@@ -140,7 +143,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
140
143
|
end
|
|
141
144
|
|
|
142
145
|
# Extract Classification or Category from a Document using AI
|
|
143
|
-
# Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
146
|
+
# Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
144
147
|
# @param [Hash] opts the optional parameters
|
|
145
148
|
# @option opts [String] :categories Desired classification to extract
|
|
146
149
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
@@ -185,7 +188,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
185
188
|
return data, status_code, headers
|
|
186
189
|
end
|
|
187
190
|
# Extract Classification or Category from a Document using Advanced AI
|
|
188
|
-
# Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and
|
|
191
|
+
# Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
189
192
|
# @param [Hash] opts the optional parameters
|
|
190
193
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
191
194
|
# @option opts [AdvancedExtractClassificationRequest] :body Input request to perform the classification on
|
|
@@ -196,7 +199,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
196
199
|
end
|
|
197
200
|
|
|
198
201
|
# Extract Classification or Category from a Document using Advanced AI
|
|
199
|
-
# Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and
|
|
202
|
+
# Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
200
203
|
# @param [Hash] opts the optional parameters
|
|
201
204
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
202
205
|
# @option opts [AdvancedExtractClassificationRequest] :body Input request to perform the classification on
|
|
@@ -238,7 +241,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
238
241
|
return data, status_code, headers
|
|
239
242
|
end
|
|
240
243
|
# Extract Field Values from a Document using AI
|
|
241
|
-
# Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
244
|
+
# Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
242
245
|
# @param [Hash] opts the optional parameters
|
|
243
246
|
# @option opts [String] :field_names Desired fields to extract, comma separated
|
|
244
247
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
@@ -250,7 +253,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
250
253
|
end
|
|
251
254
|
|
|
252
255
|
# Extract Field Values from a Document using AI
|
|
253
|
-
# Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
256
|
+
# Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
254
257
|
# @param [Hash] opts the optional parameters
|
|
255
258
|
# @option opts [String] :field_names Desired fields to extract, comma separated
|
|
256
259
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
@@ -295,22 +298,22 @@ module CloudmersiveDocumentaiApiClient
|
|
|
295
298
|
return data, status_code, headers
|
|
296
299
|
end
|
|
297
300
|
# Extract Field Values from a Document using Advanced AI
|
|
298
|
-
# Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and
|
|
301
|
+
# Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
299
302
|
# @param [Hash] opts the optional parameters
|
|
300
303
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
301
304
|
# @option opts [AdvancedExtractFieldsRequest] :body Input request, including document file as byte array, and information on which fields to extract
|
|
302
|
-
# @return [
|
|
305
|
+
# @return [ExtractFieldsAdvancedResponse]
|
|
303
306
|
def extract_fields_advanced(opts = {})
|
|
304
307
|
data, _status_code, _headers = extract_fields_advanced_with_http_info(opts)
|
|
305
308
|
data
|
|
306
309
|
end
|
|
307
310
|
|
|
308
311
|
# Extract Field Values from a Document using Advanced AI
|
|
309
|
-
# Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and
|
|
312
|
+
# Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
310
313
|
# @param [Hash] opts the optional parameters
|
|
311
314
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
312
315
|
# @option opts [AdvancedExtractFieldsRequest] :body Input request, including document file as byte array, and information on which fields to extract
|
|
313
|
-
# @return [Array<(
|
|
316
|
+
# @return [Array<(ExtractFieldsAdvancedResponse, Fixnum, Hash)>] ExtractFieldsAdvancedResponse data, response status code and response headers
|
|
314
317
|
def extract_fields_advanced_with_http_info(opts = {})
|
|
315
318
|
if @api_client.config.debugging
|
|
316
319
|
@api_client.config.logger.debug 'Calling API: ExtractApi.extract_fields_advanced ...'
|
|
@@ -341,16 +344,71 @@ module CloudmersiveDocumentaiApiClient
|
|
|
341
344
|
:form_params => form_params,
|
|
342
345
|
:body => post_body,
|
|
343
346
|
:auth_names => auth_names,
|
|
344
|
-
:return_type => '
|
|
347
|
+
:return_type => 'ExtractFieldsAdvancedResponse')
|
|
345
348
|
if @api_client.config.debugging
|
|
346
349
|
@api_client.config.logger.debug "API called: ExtractApi#extract_fields_advanced\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
|
347
350
|
end
|
|
348
351
|
return data, status_code, headers
|
|
349
352
|
end
|
|
353
|
+
# Intelligently Split a Combined Document into Sub-Documents using AI
|
|
354
|
+
# Analyzes a document containing multiple sub-documents (such as a scanned batch of ID cards, forms, or mixed documents) and intelligently splits it into separate sub-documents. Uses AI to detect document boundaries based on visual content, headers, names, and document types. Returns the page ranges and PDF bytes for each identified sub-document. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
355
|
+
# @param [Hash] opts the optional parameters
|
|
356
|
+
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
357
|
+
# @option opts [File] :input_file Input document containing multiple sub-documents to split
|
|
358
|
+
# @return [SplitDocumentResponse]
|
|
359
|
+
def extract_split(opts = {})
|
|
360
|
+
data, _status_code, _headers = extract_split_with_http_info(opts)
|
|
361
|
+
data
|
|
362
|
+
end
|
|
363
|
+
|
|
364
|
+
# Intelligently Split a Combined Document into Sub-Documents using AI
|
|
365
|
+
# Analyzes a document containing multiple sub-documents (such as a scanned batch of ID cards, forms, or mixed documents) and intelligently splits it into separate sub-documents. Uses AI to detect document boundaries based on visual content, headers, names, and document types. Returns the page ranges and PDF bytes for each identified sub-document. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
366
|
+
# @param [Hash] opts the optional parameters
|
|
367
|
+
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
368
|
+
# @option opts [File] :input_file Input document containing multiple sub-documents to split
|
|
369
|
+
# @return [Array<(SplitDocumentResponse, Fixnum, Hash)>] SplitDocumentResponse data, response status code and response headers
|
|
370
|
+
def extract_split_with_http_info(opts = {})
|
|
371
|
+
if @api_client.config.debugging
|
|
372
|
+
@api_client.config.logger.debug 'Calling API: ExtractApi.extract_split ...'
|
|
373
|
+
end
|
|
374
|
+
# resource path
|
|
375
|
+
local_var_path = '/document-ai/document/extract/split'
|
|
376
|
+
|
|
377
|
+
# query parameters
|
|
378
|
+
query_params = {}
|
|
379
|
+
|
|
380
|
+
# header parameters
|
|
381
|
+
header_params = {}
|
|
382
|
+
# HTTP header 'Accept' (if needed)
|
|
383
|
+
header_params['Accept'] = @api_client.select_header_accept(['text/plain', 'application/json', 'text/json'])
|
|
384
|
+
# HTTP header 'Content-Type'
|
|
385
|
+
header_params['Content-Type'] = @api_client.select_header_content_type(['multipart/form-data'])
|
|
386
|
+
header_params[:'recognitionMode'] = opts[:'recognition_mode'] if !opts[:'recognition_mode'].nil?
|
|
387
|
+
|
|
388
|
+
# form parameters
|
|
389
|
+
form_params = {}
|
|
390
|
+
form_params['InputFile'] = opts[:'input_file'] if !opts[:'input_file'].nil?
|
|
391
|
+
|
|
392
|
+
# http body (model)
|
|
393
|
+
post_body = nil
|
|
394
|
+
auth_names = ['Apikey']
|
|
395
|
+
data, status_code, headers = @api_client.call_api(:POST, local_var_path,
|
|
396
|
+
:header_params => header_params,
|
|
397
|
+
:query_params => query_params,
|
|
398
|
+
:form_params => form_params,
|
|
399
|
+
:body => post_body,
|
|
400
|
+
:auth_names => auth_names,
|
|
401
|
+
:return_type => 'SplitDocumentResponse')
|
|
402
|
+
if @api_client.config.debugging
|
|
403
|
+
@api_client.config.logger.debug "API called: ExtractApi#extract_split\nData: #{data.inspect}\nStatus code: #{status_code}\nHeaders: #{headers}"
|
|
404
|
+
end
|
|
405
|
+
return data, status_code, headers
|
|
406
|
+
end
|
|
350
407
|
# Extract Summary from a Document using AI
|
|
351
|
-
# Creates a 1 paragraph summary of the input document using Artificial Intelligence. Input document formats supported include DOCX, PDF, PNG and
|
|
408
|
+
# Creates a 1 paragraph summary of the input document using Artificial Intelligence. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
352
409
|
# @param [Hash] opts the optional parameters
|
|
353
410
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
411
|
+
# @option opts [String] :language Optional; Three-letter language code (ISO 639) for the summary. Default is ENG. Possible language codes are: AAR,ABK,ACE,ACH,ADA,ADY,AFA,AFH,AFR,AIN,AKA,AKK,ALB,ALE,ALG,ALT,AMH,ANG,ANP,APA,ARA,ARC,ARG,ARM,ARN,ARP,ART,ARW,ASM,AST,ATH,AUS,AVA,AVE,AWA,AYM,AZE,BAD,BAI,BAK,BAL,BAM,BAN,BAQ,BAS,BAT,BEJ,BEL,BEM,BEN,BER,BHO,BIH,BIK,BIN,BIS,BLA,BNT,BOD,BOS,BRA,BRE,BTK,BUA,BUG,BUL,BUR,BYN,CAD,CAI,CAR,CAT,CAU,CEB,CEL,CES,CHA,CHB,CHE,CHG,CHI,CHK,CHM,CHN,CHO,CHP,CHR,CHU,CHV,CHY,CMC,CNR,COP,COR,COS,CPE,CPF,CPP,CRE,CRH,CRP,CSB,CUS,CYM,CZE,DAK,DAN,DAR,DAY,DEL,DEN,DEU,DGR,DIN,DIV,DOI,DRA,DSB,DUA,DUM,DUT,DYU,DZO,EFI,EGY,EKA,ELL,ELX,ENG,ENM,EPO,EST,EUS,EWE,EWO,FAN,FAO,FAS,FAT,FIJ,FIL,FIN,FIU,FON,FRA,FRE,FRM,FRO,FRR,FRS,FRY,FUL,FUR,GAA,GAY,GBA,GEM,GEO,GER,GEZ,GIL,GLA,GLE,GLG,GLV,GMH,GOH,GON,GOR,GOT,GRB,GRC,GRE,GRN,GSW,GUJ,GWI,HAI,HAT,HAU,HAW,HEB,HER,HIL,HIM,HIN,HIT,HMN,HMO,HRV,HSB,HUN,HUP,HYE,IBA,IBO,ICE,IDO,III,IJO,IKU,ILE,ILO,INA,INC,IND,INE,INH,IPK,IRA,IRO,ISL,ITA,JAV,JBO,JPN,JPR,JRB,KAA,KAB,KAC,KAL,KAM,KAN,KAR,KAS,KAT,KAU,KAW,KAZ,KBD,KHA,KHI,KHM,KHO,KIK,KIN,KIR,KMB,KOK,KOM,KON,KOR,KOS,KPE,KRC,KRL,KRO,KRU,KUA,KUM,KUR,KUT,LAD,LAH,LAM,LAO,LAT,LAV,LEZ,LIM,LIN,LIT,LOL,LOZ,LTZ,LUA,LUB,LUG,LUI,LUN,LUO,LUS,MAC,MAD,MAG,MAH,MAI,MAK,MAL,MAN,MAO,MAP,MAR,MAS,MAY,MDF,MDR,MEN,MGA,MIC,MIN,MIS,MKD,MKH,MLG,MLT,MNC,MNI,MNO,MOH,MON,MOS,MRI,MSA,MUL,MUN,MUS,MWL,MWR,MYA,MYN,MYV,NAH,NAI,NAP,NAU,NAV,NBL,NDE,NDO,NDS,NEP,NEW,NIA,NIC,NIU,NLD,NNO,NOB,NOG,NON,NOR,NQO,NSO,NUB,NWC,NYA,NYM,NYN,NYO,NZI,OCI,OJI,ORI,ORM,OSA,OSS,OTA,OTO,PAA,PAG,PAL,PAM,PAN,PAP,PAU,PEO,PER,PHI,PHN,PLI,POL,PON,POR,PRA,PRO,PUS,QUE,RAJ,RAP,RAR,ROA,ROH,ROM,RON,RUM,RUN,RUP,RUS,SAD,SAG,SAH,SAI,SAL,SAM,SAN,SAS,SAT,SCN,SCO,SEL,SEM,SGA,SGN,SHN,SID,SIN,SIO,SIT,SLA,SLK,SLO,SLV,SMA,SME,SMI,SMJ,SMN,SMO,SMS,SNA,SND,SNK,SOG,SOM,SON,SOT,SPA,SQI,SRD,SRN,SRP,SRR,SSA,SSW,SUK,SUN,SUS,SUX,SWA,SWE,SYC,SYR,TAH,TAI,TAM,TAT,TEL,TEM,TER,TET,TGK,TGL,THA,TIB,TIG,TIR,TIV,TKL,TLH,TLI,TMH,TOG,TON,TPI,TSI,TSN,TSO,TUK,TUM,TUP,TUR,TUT,TVL,TWI,TYV,UDM,UGA,UIG,UKR,UMB,UND,URD,UZB,VAI,VEN,VIE,VOL,VOT,WAK,WAL,WAR,WAS,WEL,WEN,WLN,WOL,XAL,XHO,YAO,YAP,YID,YOR,YPK,ZAP,ZBL,ZEN,ZGH,ZHA,ZHO,ZND,ZUL,ZUN,ZXX,ZZA.
|
|
354
412
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
355
413
|
# @return [SummarizeDocumentResponse]
|
|
356
414
|
def extract_summary(opts = {})
|
|
@@ -359,9 +417,10 @@ module CloudmersiveDocumentaiApiClient
|
|
|
359
417
|
end
|
|
360
418
|
|
|
361
419
|
# Extract Summary from a Document using AI
|
|
362
|
-
# Creates a 1 paragraph summary of the input document using Artificial Intelligence. Input document formats supported include DOCX, PDF, PNG and
|
|
420
|
+
# Creates a 1 paragraph summary of the input document using Artificial Intelligence. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumes 100 API calls per page.
|
|
363
421
|
# @param [Hash] opts the optional parameters
|
|
364
422
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
423
|
+
# @option opts [String] :language Optional; Three-letter language code (ISO 639) for the summary. Default is ENG. Possible language codes are: AAR,ABK,ACE,ACH,ADA,ADY,AFA,AFH,AFR,AIN,AKA,AKK,ALB,ALE,ALG,ALT,AMH,ANG,ANP,APA,ARA,ARC,ARG,ARM,ARN,ARP,ART,ARW,ASM,AST,ATH,AUS,AVA,AVE,AWA,AYM,AZE,BAD,BAI,BAK,BAL,BAM,BAN,BAQ,BAS,BAT,BEJ,BEL,BEM,BEN,BER,BHO,BIH,BIK,BIN,BIS,BLA,BNT,BOD,BOS,BRA,BRE,BTK,BUA,BUG,BUL,BUR,BYN,CAD,CAI,CAR,CAT,CAU,CEB,CEL,CES,CHA,CHB,CHE,CHG,CHI,CHK,CHM,CHN,CHO,CHP,CHR,CHU,CHV,CHY,CMC,CNR,COP,COR,COS,CPE,CPF,CPP,CRE,CRH,CRP,CSB,CUS,CYM,CZE,DAK,DAN,DAR,DAY,DEL,DEN,DEU,DGR,DIN,DIV,DOI,DRA,DSB,DUA,DUM,DUT,DYU,DZO,EFI,EGY,EKA,ELL,ELX,ENG,ENM,EPO,EST,EUS,EWE,EWO,FAN,FAO,FAS,FAT,FIJ,FIL,FIN,FIU,FON,FRA,FRE,FRM,FRO,FRR,FRS,FRY,FUL,FUR,GAA,GAY,GBA,GEM,GEO,GER,GEZ,GIL,GLA,GLE,GLG,GLV,GMH,GOH,GON,GOR,GOT,GRB,GRC,GRE,GRN,GSW,GUJ,GWI,HAI,HAT,HAU,HAW,HEB,HER,HIL,HIM,HIN,HIT,HMN,HMO,HRV,HSB,HUN,HUP,HYE,IBA,IBO,ICE,IDO,III,IJO,IKU,ILE,ILO,INA,INC,IND,INE,INH,IPK,IRA,IRO,ISL,ITA,JAV,JBO,JPN,JPR,JRB,KAA,KAB,KAC,KAL,KAM,KAN,KAR,KAS,KAT,KAU,KAW,KAZ,KBD,KHA,KHI,KHM,KHO,KIK,KIN,KIR,KMB,KOK,KOM,KON,KOR,KOS,KPE,KRC,KRL,KRO,KRU,KUA,KUM,KUR,KUT,LAD,LAH,LAM,LAO,LAT,LAV,LEZ,LIM,LIN,LIT,LOL,LOZ,LTZ,LUA,LUB,LUG,LUI,LUN,LUO,LUS,MAC,MAD,MAG,MAH,MAI,MAK,MAL,MAN,MAO,MAP,MAR,MAS,MAY,MDF,MDR,MEN,MGA,MIC,MIN,MIS,MKD,MKH,MLG,MLT,MNC,MNI,MNO,MOH,MON,MOS,MRI,MSA,MUL,MUN,MUS,MWL,MWR,MYA,MYN,MYV,NAH,NAI,NAP,NAU,NAV,NBL,NDE,NDO,NDS,NEP,NEW,NIA,NIC,NIU,NLD,NNO,NOB,NOG,NON,NOR,NQO,NSO,NUB,NWC,NYA,NYM,NYN,NYO,NZI,OCI,OJI,ORI,ORM,OSA,OSS,OTA,OTO,PAA,PAG,PAL,PAM,PAN,PAP,PAU,PEO,PER,PHI,PHN,PLI,POL,PON,POR,PRA,PRO,PUS,QUE,RAJ,RAP,RAR,ROA,ROH,ROM,RON,RUM,RUN,RUP,RUS,SAD,SAG,SAH,SAI,SAL,SAM,SAN,SAS,SAT,SCN,SCO,SEL,SEM,SGA,SGN,SHN,SID,SIN,SIO,SIT,SLA,SLK,SLO,SLV,SMA,SME,SMI,SMJ,SMN,SMO,SMS,SNA,SND,SNK,SOG,SOM,SON,SOT,SPA,SQI,SRD,SRN,SRP,SRR,SSA,SSW,SUK,SUN,SUS,SUX,SWA,SWE,SYC,SYR,TAH,TAI,TAM,TAT,TEL,TEM,TER,TET,TGK,TGL,THA,TIB,TIG,TIR,TIV,TKL,TLH,TLI,TMH,TOG,TON,TPI,TSI,TSN,TSO,TUK,TUM,TUP,TUR,TUT,TVL,TWI,TYV,UDM,UGA,UIG,UKR,UMB,UND,URD,UZB,VAI,VEN,VIE,VOL,VOT,WAK,WAL,WAR,WAS,WEL,WEN,WLN,WOL,XAL,XHO,YAO,YAP,YID,YOR,YPK,ZAP,ZBL,ZEN,ZGH,ZHA,ZHO,ZND,ZUL,ZUN,ZXX,ZZA.
|
|
365
424
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
366
425
|
# @return [Array<(SummarizeDocumentResponse, Fixnum, Hash)>] SummarizeDocumentResponse data, response status code and response headers
|
|
367
426
|
def extract_summary_with_http_info(opts = {})
|
|
@@ -381,6 +440,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
381
440
|
# HTTP header 'Content-Type'
|
|
382
441
|
header_params['Content-Type'] = @api_client.select_header_content_type(['multipart/form-data'])
|
|
383
442
|
header_params[:'recognitionMode'] = opts[:'recognition_mode'] if !opts[:'recognition_mode'].nil?
|
|
443
|
+
header_params[:'language'] = opts[:'language'] if !opts[:'language'].nil?
|
|
384
444
|
|
|
385
445
|
# form parameters
|
|
386
446
|
form_params = {}
|
|
@@ -402,7 +462,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
402
462
|
return data, status_code, headers
|
|
403
463
|
end
|
|
404
464
|
# Extract Tables of Data from a Document using AI
|
|
405
|
-
# Extract Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
465
|
+
# Extract Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumeds 100 API calls per page.
|
|
406
466
|
# @param [Hash] opts the optional parameters
|
|
407
467
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
408
468
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
@@ -413,7 +473,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
413
473
|
end
|
|
414
474
|
|
|
415
475
|
# Extract Tables of Data from a Document using AI
|
|
416
|
-
# Extract Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
476
|
+
# Extract Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Consumeds 100 API calls per page.
|
|
417
477
|
# @param [Hash] opts the optional parameters
|
|
418
478
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
419
479
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
@@ -456,9 +516,9 @@ module CloudmersiveDocumentaiApiClient
|
|
|
456
516
|
return data, status_code, headers
|
|
457
517
|
end
|
|
458
518
|
# Extract Text from a Document using AI
|
|
459
|
-
# Extract raw text from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
519
|
+
# Extract raw text from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Supports a wide range of languages. Consumes 100 API calls per page.
|
|
460
520
|
# @param [Hash] opts the optional parameters
|
|
461
|
-
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
521
|
+
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images. Set to Deterministic to directly extract text from digital documents without using AI.
|
|
462
522
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
463
523
|
# @return [ExtractTextResponse]
|
|
464
524
|
def extract_text(opts = {})
|
|
@@ -467,9 +527,9 @@ module CloudmersiveDocumentaiApiClient
|
|
|
467
527
|
end
|
|
468
528
|
|
|
469
529
|
# Extract Text from a Document using AI
|
|
470
|
-
# Extract raw text from a document using AI. Input document formats supported include DOCX, PDF, PNG and
|
|
530
|
+
# Extract raw text from a document using AI. Input document formats supported include DOCX, PDF, XLSX, PPTX, EML, MSG, JPG, PNG and WEBP. Supports a wide range of languages. Consumes 100 API calls per page.
|
|
471
531
|
# @param [Hash] opts the optional parameters
|
|
472
|
-
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
532
|
+
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images. Set to Deterministic to directly extract text from digital documents without using AI.
|
|
473
533
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
474
534
|
# @return [Array<(ExtractTextResponse, Fixnum, Hash)>] ExtractTextResponse data, response status code and response headers
|
|
475
535
|
def extract_text_with_http_info(opts = {})
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
=begin
|
|
2
2
|
#Document AI API
|
|
3
3
|
|
|
4
|
-
#
|
|
4
|
+
#Extract structured data including named fields, tables, barcodes, classifications, and summaries from common document formats, scanned documents, and photos of documents using AI. Also supports handwriting and low quality photos and scans, as well as digital document input. Supports a wide range of languages, and is able to analyze and infer semantic structure from the visual layout for documents.
|
|
5
5
|
|
|
6
6
|
OpenAPI spec version: v1
|
|
7
|
-
|
|
7
|
+
Contact: support@cloudmersive.com
|
|
8
8
|
Generated by: https://github.com/swagger-api/swagger-codegen.git
|
|
9
9
|
Swagger Codegen version: 2.4.14
|
|
10
10
|
|
|
@@ -20,7 +20,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
20
20
|
@api_client = api_client
|
|
21
21
|
end
|
|
22
22
|
# Extract All Fields and Tables of Data from a Document using AI as a Batch Job
|
|
23
|
-
# Creates an async batch job for processing a large document as an AI batch job. Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
23
|
+
# Creates an async batch job for processing a large document as an AI batch job. Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.
|
|
24
24
|
# @param [Hash] opts the optional parameters
|
|
25
25
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
26
26
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
@@ -31,7 +31,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
31
31
|
end
|
|
32
32
|
|
|
33
33
|
# Extract All Fields and Tables of Data from a Document using AI as a Batch Job
|
|
34
|
-
# Creates an async batch job for processing a large document as an AI batch job. Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
34
|
+
# Creates an async batch job for processing a large document as an AI batch job. Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.
|
|
35
35
|
# @param [Hash] opts the optional parameters
|
|
36
36
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
37
37
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
@@ -74,7 +74,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
74
74
|
return data, status_code, headers
|
|
75
75
|
end
|
|
76
76
|
# Extract Classification or Category from a Document using AI as a Batch Job
|
|
77
|
-
# Creates an async batch job for processing a large document as an AI batch job. Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
77
|
+
# Creates an async batch job for processing a large document as an AI batch job. Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.
|
|
78
78
|
# @param [Hash] opts the optional parameters
|
|
79
79
|
# @option opts [String] :categories Desired classification to extract
|
|
80
80
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
@@ -86,7 +86,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
86
86
|
end
|
|
87
87
|
|
|
88
88
|
# Extract Classification or Category from a Document using AI as a Batch Job
|
|
89
|
-
# Creates an async batch job for processing a large document as an AI batch job. Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
89
|
+
# Creates an async batch job for processing a large document as an AI batch job. Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.
|
|
90
90
|
# @param [Hash] opts the optional parameters
|
|
91
91
|
# @option opts [String] :categories Desired classification to extract
|
|
92
92
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
@@ -131,10 +131,10 @@ module CloudmersiveDocumentaiApiClient
|
|
|
131
131
|
return data, status_code, headers
|
|
132
132
|
end
|
|
133
133
|
# Extract Field Values from a Document using Advanced AI as a Batch Job
|
|
134
|
-
# Creates an async batch job for processing a large document as an AI batch job. Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
134
|
+
# Creates an async batch job for processing a large document as an AI batch job. Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.
|
|
135
135
|
# @param [Hash] opts the optional parameters
|
|
136
136
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
137
|
-
# @option opts [AdvancedExtractFieldsRequest] :body
|
|
137
|
+
# @option opts [AdvancedExtractFieldsRequest] :body Input document and parameters
|
|
138
138
|
# @return [ExtractDocumentBatchJobResult]
|
|
139
139
|
def extract_fields_from_document_advanced_batch_job(opts = {})
|
|
140
140
|
data, _status_code, _headers = extract_fields_from_document_advanced_batch_job_with_http_info(opts)
|
|
@@ -142,10 +142,10 @@ module CloudmersiveDocumentaiApiClient
|
|
|
142
142
|
end
|
|
143
143
|
|
|
144
144
|
# Extract Field Values from a Document using Advanced AI as a Batch Job
|
|
145
|
-
# Creates an async batch job for processing a large document as an AI batch job. Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG.
|
|
145
|
+
# Creates an async batch job for processing a large document as an AI batch job. Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.
|
|
146
146
|
# @param [Hash] opts the optional parameters
|
|
147
147
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
148
|
-
# @option opts [AdvancedExtractFieldsRequest] :body
|
|
148
|
+
# @option opts [AdvancedExtractFieldsRequest] :body Input document and parameters
|
|
149
149
|
# @return [Array<(ExtractDocumentBatchJobResult, Fixnum, Hash)>] ExtractDocumentBatchJobResult data, response status code and response headers
|
|
150
150
|
def extract_fields_from_document_advanced_batch_job_with_http_info(opts = {})
|
|
151
151
|
if @api_client.config.debugging
|
|
@@ -184,7 +184,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
184
184
|
return data, status_code, headers
|
|
185
185
|
end
|
|
186
186
|
# Extract Text from a Document using AI as a Batch Job
|
|
187
|
-
# Creates an async batch job for processing a large document as an AI batch job. Input document formats supported include DOCX, PDF, PNG and JPG. Supports a wide range of languages.
|
|
187
|
+
# Creates an async batch job for processing a large document as an AI batch job. Input document formats supported include DOCX, PDF, PNG and JPG. Supports a wide range of languages. Requires Managed Instance or Private Cloud deployment.
|
|
188
188
|
# @param [Hash] opts the optional parameters
|
|
189
189
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
190
190
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
@@ -195,7 +195,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
195
195
|
end
|
|
196
196
|
|
|
197
197
|
# Extract Text from a Document using AI as a Batch Job
|
|
198
|
-
# Creates an async batch job for processing a large document as an AI batch job. Input document formats supported include DOCX, PDF, PNG and JPG. Supports a wide range of languages.
|
|
198
|
+
# Creates an async batch job for processing a large document as an AI batch job. Input document formats supported include DOCX, PDF, PNG and JPG. Supports a wide range of languages. Requires Managed Instance or Private Cloud deployment.
|
|
199
199
|
# @param [Hash] opts the optional parameters
|
|
200
200
|
# @option opts [String] :recognition_mode Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
|
|
201
201
|
# @option opts [File] :input_file Input document, or photos of a document, to extract data from
|
|
@@ -240,7 +240,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
240
240
|
# Get the status and result of an Extract Document Batch Job
|
|
241
241
|
# Returns the result of the Async Job - possible states can be STARTED or COMPLETED. This API is only available for Cloudmersive Managed Instance and Private Cloud deployments.
|
|
242
242
|
# @param [Hash] opts the optional parameters
|
|
243
|
-
# @option opts [String] :async_job_id
|
|
243
|
+
# @option opts [String] :async_job_id Job ID for the batch job to get the status of
|
|
244
244
|
# @return [ExtractDocumentJobStatusResult]
|
|
245
245
|
def get_async_job_status(opts = {})
|
|
246
246
|
data, _status_code, _headers = get_async_job_status_with_http_info(opts)
|
|
@@ -250,7 +250,7 @@ module CloudmersiveDocumentaiApiClient
|
|
|
250
250
|
# Get the status and result of an Extract Document Batch Job
|
|
251
251
|
# Returns the result of the Async Job - possible states can be STARTED or COMPLETED. This API is only available for Cloudmersive Managed Instance and Private Cloud deployments.
|
|
252
252
|
# @param [Hash] opts the optional parameters
|
|
253
|
-
# @option opts [String] :async_job_id
|
|
253
|
+
# @option opts [String] :async_job_id Job ID for the batch job to get the status of
|
|
254
254
|
# @return [Array<(ExtractDocumentJobStatusResult, Fixnum, Hash)>] ExtractDocumentJobStatusResult data, response status code and response headers
|
|
255
255
|
def get_async_job_status_with_http_info(opts = {})
|
|
256
256
|
if @api_client.config.debugging
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
=begin
|
|
2
2
|
#Document AI API
|
|
3
3
|
|
|
4
|
-
#
|
|
4
|
+
#Extract structured data including named fields, tables, barcodes, classifications, and summaries from common document formats, scanned documents, and photos of documents using AI. Also supports handwriting and low quality photos and scans, as well as digital document input. Supports a wide range of languages, and is able to analyze and infer semantic structure from the visual layout for documents.
|
|
5
5
|
|
|
6
6
|
OpenAPI spec version: v1
|
|
7
|
-
|
|
7
|
+
Contact: support@cloudmersive.com
|
|
8
8
|
Generated by: https://github.com/swagger-api/swagger-codegen.git
|
|
9
9
|
Swagger Codegen version: 2.4.14
|
|
10
10
|
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
=begin
|
|
2
2
|
#Document AI API
|
|
3
3
|
|
|
4
|
-
#
|
|
4
|
+
#Extract structured data including named fields, tables, barcodes, classifications, and summaries from common document formats, scanned documents, and photos of documents using AI. Also supports handwriting and low quality photos and scans, as well as digital document input. Supports a wide range of languages, and is able to analyze and infer semantic structure from the visual layout for documents.
|
|
5
5
|
|
|
6
6
|
OpenAPI spec version: v1
|
|
7
|
-
|
|
7
|
+
Contact: support@cloudmersive.com
|
|
8
8
|
Generated by: https://github.com/swagger-api/swagger-codegen.git
|
|
9
9
|
Swagger Codegen version: 2.4.14
|
|
10
10
|
|