diff --git a/docs/dyn/discoveryengine_v1alpha.projects.locations.collections.dataStores.html b/docs/dyn/discoveryengine_v1alpha.projects.locations.collections.dataStores.html
index 84c5eaf3adb..e870a7b55ae 100644
--- a/docs/dyn/discoveryengine_v1alpha.projects.locations.collections.dataStores.html
+++ b/docs/dyn/discoveryengine_v1alpha.projects.locations.collections.dataStores.html
@@ -321,14 +321,40 @@ Method Details
An object of the form:
{ # A singleton resource of DataStore. It's empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.
- "name": "A String", # Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
- "ocrConfig": { # The OCR options for parsing documents. # The OCR config. Currently it only applies to PDFs.
+ "defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ "name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
+ "ocrConfig": { # The OCR options for parsing documents. # [DEPRECATED] This field is deprecated. To specify OCR parsing config, please specify `ocr_parsing_config` in `default_parsing_config` field The OCR config. Currently it only applies to PDFs.
"enabled": True or False, # Required. If OCR is enabled or not. OCR must be enabled for other OcrConfig options to apply. We will only perform OCR on the first 80 pages of the PDF files.
"enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
+ "parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.
+ "a_key": { # Related configurations applied to a specific type of document parser.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ },
}
@@ -499,19 +525,45 @@ Method Details
Updates the DocumentProcessingConfig. DocumentProcessingConfig is a singleon resource of DataStore. It's empty when DataStore is created. The first call to this method will set up DocumentProcessingConfig.
Args:
- name: string, Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`. (required)
+ name: string, The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`. (required)
body: object, The request body.
The object takes the form of:
{ # A singleton resource of DataStore. It's empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.
- "name": "A String", # Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
- "ocrConfig": { # The OCR options for parsing documents. # The OCR config. Currently it only applies to PDFs.
+ "defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ "name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
+ "ocrConfig": { # The OCR options for parsing documents. # [DEPRECATED] This field is deprecated. To specify OCR parsing config, please specify `ocr_parsing_config` in `default_parsing_config` field The OCR config. Currently it only applies to PDFs.
"enabled": True or False, # Required. If OCR is enabled or not. OCR must be enabled for other OcrConfig options to apply. We will only perform OCR on the first 80 pages of the PDF files.
"enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
+ "parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.
+ "a_key": { # Related configurations applied to a specific type of document parser.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ },
}
updateMask: string, Indicates which fields in the provided DocumentProcessingConfig to update. The following are the only supported fields: * DocumentProcessingConfig.ocr_config If not set, all supported fields are updated.
@@ -524,14 +576,40 @@ Method Details
An object of the form:
{ # A singleton resource of DataStore. It's empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.
- "name": "A String", # Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
- "ocrConfig": { # The OCR options for parsing documents. # The OCR config. Currently it only applies to PDFs.
+ "defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ "name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
+ "ocrConfig": { # The OCR options for parsing documents. # [DEPRECATED] This field is deprecated. To specify OCR parsing config, please specify `ocr_parsing_config` in `default_parsing_config` field The OCR config. Currently it only applies to PDFs.
"enabled": True or False, # Required. If OCR is enabled or not. OCR must be enabled for other OcrConfig options to apply. We will only perform OCR on the first 80 pages of the PDF files.
"enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
+ "parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.
+ "a_key": { # Related configurations applied to a specific type of document parser.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ },
}
diff --git a/docs/dyn/discoveryengine_v1alpha.projects.locations.dataStores.html b/docs/dyn/discoveryengine_v1alpha.projects.locations.dataStores.html
index 541218fed3f..33b0b6dc1bc 100644
--- a/docs/dyn/discoveryengine_v1alpha.projects.locations.dataStores.html
+++ b/docs/dyn/discoveryengine_v1alpha.projects.locations.dataStores.html
@@ -318,14 +318,40 @@ Method Details
An object of the form:
{ # A singleton resource of DataStore. It's empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.
- "name": "A String", # Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
- "ocrConfig": { # The OCR options for parsing documents. # The OCR config. Currently it only applies to PDFs.
+ "defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ "name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
+ "ocrConfig": { # The OCR options for parsing documents. # [DEPRECATED] This field is deprecated. To specify OCR parsing config, please specify `ocr_parsing_config` in `default_parsing_config` field The OCR config. Currently it only applies to PDFs.
"enabled": True or False, # Required. If OCR is enabled or not. OCR must be enabled for other OcrConfig options to apply. We will only perform OCR on the first 80 pages of the PDF files.
"enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
+ "parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.
+ "a_key": { # Related configurations applied to a specific type of document parser.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ },
}
@@ -445,19 +471,45 @@ Method Details
Updates the DocumentProcessingConfig. DocumentProcessingConfig is a singleon resource of DataStore. It's empty when DataStore is created. The first call to this method will set up DocumentProcessingConfig.
Args:
- name: string, Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`. (required)
+ name: string, The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`. (required)
body: object, The request body.
The object takes the form of:
{ # A singleton resource of DataStore. It's empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.
- "name": "A String", # Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
- "ocrConfig": { # The OCR options for parsing documents. # The OCR config. Currently it only applies to PDFs.
+ "defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ "name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
+ "ocrConfig": { # The OCR options for parsing documents. # [DEPRECATED] This field is deprecated. To specify OCR parsing config, please specify `ocr_parsing_config` in `default_parsing_config` field The OCR config. Currently it only applies to PDFs.
"enabled": True or False, # Required. If OCR is enabled or not. OCR must be enabled for other OcrConfig options to apply. We will only perform OCR on the first 80 pages of the PDF files.
"enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
+ "parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.
+ "a_key": { # Related configurations applied to a specific type of document parser.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ },
}
updateMask: string, Indicates which fields in the provided DocumentProcessingConfig to update. The following are the only supported fields: * DocumentProcessingConfig.ocr_config If not set, all supported fields are updated.
@@ -470,14 +522,40 @@ Method Details
An object of the form:
{ # A singleton resource of DataStore. It's empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.
- "name": "A String", # Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
- "ocrConfig": { # The OCR options for parsing documents. # The OCR config. Currently it only applies to PDFs.
+ "defaultParsingConfig": { # Related configurations applied to a specific type of document parser. # Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ "name": "A String", # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
+ "ocrConfig": { # The OCR options for parsing documents. # [DEPRECATED] This field is deprecated. To specify OCR parsing config, please specify `ocr_parsing_config` in `default_parsing_config` field The OCR config. Currently it only applies to PDFs.
"enabled": True or False, # Required. If OCR is enabled or not. OCR must be enabled for other OcrConfig options to apply. We will only perform OCR on the first 80 pages of the PDF files.
"enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
"A String",
],
"useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
},
+ "parsingConfigOverrides": { # Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.
+ "a_key": { # Related configurations applied to a specific type of document parser.
+ "digitalParsingConfig": { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+ },
+ "layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+ },
+ "ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+ "enhancedDocumentElements": [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+ "A String",
+ ],
+ "useNativeText": True or False, # If true, will use native text instead of OCR text on pages containing native text.
+ },
+ },
+ },
}
diff --git a/googleapiclient/discovery_cache/documents/discoveryengine.v1alpha.json b/googleapiclient/discovery_cache/documents/discoveryengine.v1alpha.json
index a52cb44957e..e38e257b392 100644
--- a/googleapiclient/discovery_cache/documents/discoveryengine.v1alpha.json
+++ b/googleapiclient/discovery_cache/documents/discoveryengine.v1alpha.json
@@ -629,7 +629,7 @@
],
"parameters": {
"name": {
-"description": "Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.",
+"description": "The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/collections/[^/]+/dataStores/[^/]+/documentProcessingConfig$",
"required": true,
@@ -3134,7 +3134,7 @@
],
"parameters": {
"name": {
-"description": "Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.",
+"description": "The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/dataStores/[^/]+/documentProcessingConfig$",
"required": true,
@@ -4596,7 +4596,7 @@
}
}
},
-"revision": "20240123",
+"revision": "20240131",
"rootUrl": "https://discoveryengine.googleapis.com/",
"schemas": {
"GoogleApiHttpBody": {
@@ -6203,6 +6203,12 @@
},
"type": "object"
},
+"GoogleCloudDiscoveryengineV1alphaDigitalParsingConfig": {
+"description": "The digital parsing configurations for documents.",
+"id": "GoogleCloudDiscoveryengineV1alphaDigitalParsingConfig",
+"properties": {},
+"type": "object"
+},
"GoogleCloudDiscoveryengineV1alphaDisableAdvancedSiteSearchMetadata": {
"description": "Metadata related to the progress of the SiteSearchEngineService.DisableAdvancedSiteSearch operation. This will be returned by the google.longrunning.Operation.metadata field.",
"id": "GoogleCloudDiscoveryengineV1alphaDisableAdvancedSiteSearchMetadata",
@@ -6335,14 +6341,44 @@
"description": "A singleton resource of DataStore. It's empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.",
"id": "GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig",
"properties": {
+"defaultParsingConfig": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig",
+"description": "Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing."
+},
"name": {
-"description": "Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.",
-"readOnly": true,
+"description": "The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.",
"type": "string"
},
"ocrConfig": {
"$ref": "GoogleCloudDiscoveryengineV1alphaOcrConfig",
-"description": "The OCR config. Currently it only applies to PDFs."
+"deprecated": true,
+"description": "[DEPRECATED] This field is deprecated. To specify OCR parsing config, please specify `ocr_parsing_config` in `default_parsing_config` field The OCR config. Currently it only applies to PDFs."
+},
+"parsingConfigOverrides": {
+"additionalProperties": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig"
+},
+"description": "Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.",
+"type": "object"
+}
+},
+"type": "object"
+},
+"GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig": {
+"description": "Related configurations applied to a specific type of document parser.",
+"id": "GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig",
+"properties": {
+"digitalParsingConfig": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaDigitalParsingConfig",
+"description": "Configurations applied to digital parser."
+},
+"layoutParsingConfig": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaLayoutParsingConfig",
+"description": "Configurations applied to layout parser."
+},
+"ocrParsingConfig": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaOcrParsingConfig",
+"description": "Configurations applied to OCR parser. Currently it only applies to PDFs."
}
},
"type": "object"
@@ -7248,6 +7284,12 @@
},
"type": "object"
},
+"GoogleCloudDiscoveryengineV1alphaLayoutParsingConfig": {
+"description": "The layout parsing configurations for documents.",
+"id": "GoogleCloudDiscoveryengineV1alphaLayoutParsingConfig",
+"properties": {},
+"type": "object"
+},
"GoogleCloudDiscoveryengineV1alphaListConversationsResponse": {
"description": "Response for ListConversations method.",
"id": "GoogleCloudDiscoveryengineV1alphaListConversationsResponse",
@@ -7401,6 +7443,7 @@
"type": "object"
},
"GoogleCloudDiscoveryengineV1alphaOcrConfig": {
+"deprecated": true,
"description": "The OCR options for parsing documents.",
"id": "GoogleCloudDiscoveryengineV1alphaOcrConfig",
"properties": {
@@ -7422,6 +7465,24 @@
},
"type": "object"
},
+"GoogleCloudDiscoveryengineV1alphaOcrParsingConfig": {
+"description": "The OCR parsing configurations for documents.",
+"id": "GoogleCloudDiscoveryengineV1alphaOcrParsingConfig",
+"properties": {
+"enhancedDocumentElements": {
+"description": "Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.",
+"items": {
+"type": "string"
+},
+"type": "array"
+},
+"useNativeText": {
+"description": "If true, will use native text instead of OCR text on pages containing native text.",
+"type": "boolean"
+}
+},
+"type": "object"
+},
"GoogleCloudDiscoveryengineV1alphaPageInfo": {
"description": "Detailed page information.",
"id": "GoogleCloudDiscoveryengineV1alphaPageInfo",
diff --git a/googleapiclient/discovery_cache/documents/discoveryengine.v1beta.json b/googleapiclient/discovery_cache/documents/discoveryengine.v1beta.json
index 6256e453021..3969e33d084 100644
--- a/googleapiclient/discovery_cache/documents/discoveryengine.v1beta.json
+++ b/googleapiclient/discovery_cache/documents/discoveryengine.v1beta.json
@@ -4164,7 +4164,7 @@
}
}
},
-"revision": "20240123",
+"revision": "20240131",
"rootUrl": "https://discoveryengine.googleapis.com/",
"schemas": {
"GoogleApiHttpBody": {
@@ -5435,6 +5435,12 @@
},
"type": "object"
},
+"GoogleCloudDiscoveryengineV1alphaDigitalParsingConfig": {
+"description": "The digital parsing configurations for documents.",
+"id": "GoogleCloudDiscoveryengineV1alphaDigitalParsingConfig",
+"properties": {},
+"type": "object"
+},
"GoogleCloudDiscoveryengineV1alphaDisableAdvancedSiteSearchMetadata": {
"description": "Metadata related to the progress of the SiteSearchEngineService.DisableAdvancedSiteSearch operation. This will be returned by the google.longrunning.Operation.metadata field.",
"id": "GoogleCloudDiscoveryengineV1alphaDisableAdvancedSiteSearchMetadata",
@@ -5462,14 +5468,44 @@
"description": "A singleton resource of DataStore. It's empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.",
"id": "GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig",
"properties": {
+"defaultParsingConfig": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig",
+"description": "Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing."
+},
"name": {
-"description": "Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.",
-"readOnly": true,
+"description": "The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.",
"type": "string"
},
"ocrConfig": {
"$ref": "GoogleCloudDiscoveryengineV1alphaOcrConfig",
-"description": "The OCR config. Currently it only applies to PDFs."
+"deprecated": true,
+"description": "[DEPRECATED] This field is deprecated. To specify OCR parsing config, please specify `ocr_parsing_config` in `default_parsing_config` field The OCR config. Currently it only applies to PDFs."
+},
+"parsingConfigOverrides": {
+"additionalProperties": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig"
+},
+"description": "Map from file type to override the default parsing configuration based on the file type. Supported keys: * `pdf`: Override parsing config for PDF files, either digital parsing, ocr parsing or layout parsing is supported. * `html`: Override parsing config for HTML files, only digital parsing and or layout parsing are supported.",
+"type": "object"
+}
+},
+"type": "object"
+},
+"GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig": {
+"description": "Related configurations applied to a specific type of document parser.",
+"id": "GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig",
+"properties": {
+"digitalParsingConfig": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaDigitalParsingConfig",
+"description": "Configurations applied to digital parser."
+},
+"layoutParsingConfig": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaLayoutParsingConfig",
+"description": "Configurations applied to layout parser."
+},
+"ocrParsingConfig": {
+"$ref": "GoogleCloudDiscoveryengineV1alphaOcrParsingConfig",
+"description": "Configurations applied to OCR parser. Currently it only applies to PDFs."
}
},
"type": "object"
@@ -6098,7 +6134,14 @@
},
"type": "object"
},
+"GoogleCloudDiscoveryengineV1alphaLayoutParsingConfig": {
+"description": "The layout parsing configurations for documents.",
+"id": "GoogleCloudDiscoveryengineV1alphaLayoutParsingConfig",
+"properties": {},
+"type": "object"
+},
"GoogleCloudDiscoveryengineV1alphaOcrConfig": {
+"deprecated": true,
"description": "The OCR options for parsing documents.",
"id": "GoogleCloudDiscoveryengineV1alphaOcrConfig",
"properties": {
@@ -6120,6 +6163,24 @@
},
"type": "object"
},
+"GoogleCloudDiscoveryengineV1alphaOcrParsingConfig": {
+"description": "The OCR parsing configurations for documents.",
+"id": "GoogleCloudDiscoveryengineV1alphaOcrParsingConfig",
+"properties": {
+"enhancedDocumentElements": {
+"description": "Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.",
+"items": {
+"type": "string"
+},
+"type": "array"
+},
+"useNativeText": {
+"description": "If true, will use native text instead of OCR text on pages containing native text.",
+"type": "boolean"
+}
+},
+"type": "object"
+},
"GoogleCloudDiscoveryengineV1alphaPurgeDocumentsMetadata": {
"description": "Metadata related to the progress of the PurgeDocuments operation. This will be returned by the google.longrunning.Operation.metadata field.",
"id": "GoogleCloudDiscoveryengineV1alphaPurgeDocumentsMetadata",