feat(discoveryengine): update the api

#### discoveryengine:v1alpha The following keys were deleted: - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig.properties.name.readOnly (Total Keys: 1) The following keys were added: - schemas.GoogleCloudDiscoveryengineV1alphaDigitalParsingConfig (Total Keys: 2) - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig.properties.defaultParsingConfig.$ref (Total Keys: 1) - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig.properties.ocrConfig.deprecated (Total Keys: 1) - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig.properties.parsingConfigOverrides (Total Keys: 2) - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig (Total Keys: 5) - schemas.GoogleCloudDiscoveryengineV1alphaLayoutParsingConfig (Total Keys: 2) - schemas.GoogleCloudDiscoveryengineV1alphaOcrConfig.deprecated (Total Keys: 1) - schemas.GoogleCloudDiscoveryengineV1alphaOcrParsingConfig (Total Keys: 5) #### discoveryengine:v1beta The following keys were deleted: - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig.properties.name.readOnly (Total Keys: 1) The following keys were added: - schemas.GoogleCloudDiscoveryengineV1alphaDigitalParsingConfig (Total Keys: 2) - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig.properties.defaultParsingConfig.$ref (Total Keys: 1) - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig.properties.ocrConfig.deprecated (Total Keys: 1) - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfig.properties.parsingConfigOverrides (Total Keys: 2) - schemas.GoogleCloudDiscoveryengineV1alphaDocumentProcessingConfigParsingConfig (Total Keys: 5) - schemas.GoogleCloudDiscoveryengineV1alphaLayoutParsingConfig (Total Keys: 2) - schemas.GoogleCloudDiscoveryengineV1alphaOcrConfig.deprecated (Total Keys: 1) - schemas.GoogleCloudDiscoveryengineV1alphaOcrParsingConfig (Total Keys: 5)
googleapis · Feb 6, 2024 · 315dbd4 · 315dbd4
1 parent 0d1d764
commit 315dbd4
Show file tree

Hide file tree

Showing 4 changed files with 302 additions and 24 deletions.
diff --git a/docs/dyn/discoveryengine_v1alpha.projects.locations.collections.dataStores.html b/docs/dyn/discoveryengine_v1alpha.projects.locations.collections.dataStores.html
@@ -321,14 +321,40 @@ <h3>Method Details</h3>
   An object of the form:
 
     { # A singleton resource of DataStore. It&#x27;s empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.
-  &quot;name&quot;: &quot;A String&quot;, # Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
-  &quot;ocrConfig&quot;: { # The OCR options for parsing documents. # The OCR config. Currently it only applies to PDFs.
+  &quot;defaultParsingConfig&quot;: { # 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.
+    &quot;digitalParsingConfig&quot;: { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+    },
+    &quot;layoutParsingConfig&quot;: { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+    },
+    &quot;ocrParsingConfig&quot;: { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+      &quot;enhancedDocumentElements&quot;: [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+        &quot;A String&quot;,
+      ],
+      &quot;useNativeText&quot;: True or False, # If true, will use native text instead of OCR text on pages containing native text.
+    },
+  },
+  &quot;name&quot;: &quot;A String&quot;, # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
+  &quot;ocrConfig&quot;: { # 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.
     &quot;enabled&quot;: 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.
     &quot;enhancedDocumentElements&quot;: [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
       &quot;A String&quot;,
     ],
     &quot;useNativeText&quot;: True or False, # If true, will use native text instead of OCR text on pages containing native text.
   },
+  &quot;parsingConfigOverrides&quot;: { # 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.
+    &quot;a_key&quot;: { # Related configurations applied to a specific type of document parser.
+      &quot;digitalParsingConfig&quot;: { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+      },
+      &quot;layoutParsingConfig&quot;: { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+      },
+      &quot;ocrParsingConfig&quot;: { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+        &quot;enhancedDocumentElements&quot;: [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+          &quot;A String&quot;,
+        ],
+        &quot;useNativeText&quot;: True or False, # If true, will use native text instead of OCR text on pages containing native text.
+      },
+    },
+  },
 }</pre>
 </div>
 
@@ -499,19 +525,45 @@ <h3>Method Details</h3>
   <pre>Updates the DocumentProcessingConfig. DocumentProcessingConfig is a singleon resource of DataStore. It&#x27;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&#x27;s empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.
-  &quot;name&quot;: &quot;A String&quot;, # Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
-  &quot;ocrConfig&quot;: { # The OCR options for parsing documents. # The OCR config. Currently it only applies to PDFs.
+  &quot;defaultParsingConfig&quot;: { # 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.
+    &quot;digitalParsingConfig&quot;: { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+    },
+    &quot;layoutParsingConfig&quot;: { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+    },
+    &quot;ocrParsingConfig&quot;: { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+      &quot;enhancedDocumentElements&quot;: [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+        &quot;A String&quot;,
+      ],
+      &quot;useNativeText&quot;: True or False, # If true, will use native text instead of OCR text on pages containing native text.
+    },
+  },
+  &quot;name&quot;: &quot;A String&quot;, # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
+  &quot;ocrConfig&quot;: { # 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.
     &quot;enabled&quot;: 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.
     &quot;enhancedDocumentElements&quot;: [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
       &quot;A String&quot;,
     ],
     &quot;useNativeText&quot;: True or False, # If true, will use native text instead of OCR text on pages containing native text.
   },
+  &quot;parsingConfigOverrides&quot;: { # 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.
+    &quot;a_key&quot;: { # Related configurations applied to a specific type of document parser.
+      &quot;digitalParsingConfig&quot;: { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+      },
+      &quot;layoutParsingConfig&quot;: { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+      },
+      &quot;ocrParsingConfig&quot;: { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+        &quot;enhancedDocumentElements&quot;: [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+          &quot;A String&quot;,
+        ],
+        &quot;useNativeText&quot;: 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 @@ <h3>Method Details</h3>
   An object of the form:
 
     { # A singleton resource of DataStore. It&#x27;s empty when DataStore is created, which defaults to digital parser. The first call to DataStoreService.UpdateDocumentProcessingConfig method will initialize the config.
-  &quot;name&quot;: &quot;A String&quot;, # Output only. The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
-  &quot;ocrConfig&quot;: { # The OCR options for parsing documents. # The OCR config. Currently it only applies to PDFs.
+  &quot;defaultParsingConfig&quot;: { # 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.
+    &quot;digitalParsingConfig&quot;: { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+    },
+    &quot;layoutParsingConfig&quot;: { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+    },
+    &quot;ocrParsingConfig&quot;: { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+      &quot;enhancedDocumentElements&quot;: [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+        &quot;A String&quot;,
+      ],
+      &quot;useNativeText&quot;: True or False, # If true, will use native text instead of OCR text on pages containing native text.
+    },
+  },
+  &quot;name&quot;: &quot;A String&quot;, # The full resource name of the Document Processing Config. Format: `projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig`.
+  &quot;ocrConfig&quot;: { # 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.
     &quot;enabled&quot;: 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.
     &quot;enhancedDocumentElements&quot;: [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
       &quot;A String&quot;,
     ],
     &quot;useNativeText&quot;: True or False, # If true, will use native text instead of OCR text on pages containing native text.
   },
+  &quot;parsingConfigOverrides&quot;: { # 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.
+    &quot;a_key&quot;: { # Related configurations applied to a specific type of document parser.
+      &quot;digitalParsingConfig&quot;: { # The digital parsing configurations for documents. # Configurations applied to digital parser.
+      },
+      &quot;layoutParsingConfig&quot;: { # The layout parsing configurations for documents. # Configurations applied to layout parser.
+      },
+      &quot;ocrParsingConfig&quot;: { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
+        &quot;enhancedDocumentElements&quot;: [ # Apply additional enhanced OCR processing to a list of document elements. Supported values: * `table`: advanced table parsing model.
+          &quot;A String&quot;,
+        ],
+        &quot;useNativeText&quot;: True or False, # If true, will use native text instead of OCR text on pages containing native text.
+      },
+    },
+  },
 }</pre>
 </div>