You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/dyn/discoveryengine_v1.projects.locations.collections.dataStores.conversations.html
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -403,7 +403,7 @@ <h3>Method Details</h3>
403
403
],
404
404
},
405
405
"content": { # Unstructured data linked to this document. # The unstructured data linked to this document. Content can only be set and must be set if this document is under a `CONTENT_REQUIRED` data store.
406
-
"mimeType": "A String", # The MIME type of the content. Supported types: * `application/pdf` (PDF, only native PDFs are supported for now) * `text/html` (HTML) * `text/plain` (TXT) * `text/xml` (XML) * `application/json` (JSON) * `application/vnd.openxmlformats-officedocument.wordprocessingml.document` (DOCX) * `application/vnd.openxmlformats-officedocument.presentationml.presentation` (PPTX) * `application/vnd.openxmlformats-officedocument.spreadsheetml.sheet` (XLSX) * `application/vnd.ms-excel.sheet.macroenabled.12` (XLSM) The following types are supported only if layout parser is enabled in the data store: * `image/bmp` (BMP) * `image/gif` (GIF) * `image/jpeg` (JPEG) * `image/png` (PNG) * `image/tiff` (TIFF) See https://www.iana.org/assignments/media-types/media-types.xhtml.
406
+
"mimeType": "A String", # The MIME type of the content. Supported types: * `application/pdf` (PDF, only native PDFs are supported for now) * `text/html` (HTML) * `text/plain` (TXT) * `application/xml` or `text/xml` (XML) * `application/json` (JSON) * `application/vnd.openxmlformats-officedocument.wordprocessingml.document` (DOCX) * `application/vnd.openxmlformats-officedocument.presentationml.presentation` (PPTX) * `application/vnd.openxmlformats-officedocument.spreadsheetml.sheet` (XLSX) * `application/vnd.ms-excel.sheet.macroenabled.12` (XLSM) The following types are supported only if layout parser is enabled in the data store: * `image/bmp` (BMP) * `image/gif` (GIF) * `image/jpeg` (JPEG) * `image/png` (PNG) * `image/tiff` (TIFF) See https://www.iana.org/assignments/media-types/media-types.xhtml.
407
407
"rawBytes": "A String", # The content represented as a stream of bytes. The maximum length is 1,000,000 bytes (1 MB / ~0.95 MiB). Note: As with all `bytes` fields, this field is represented as pure binary in Protocol Buffers and base64-encoded string in JSON. For example, `abc123!?$*&()'-=@~` should be represented as `YWJjMTIzIT8kKiYoKSctPUB+` in JSON. See https://developers.google.com/protocol-buffers/docs/proto3#json.
408
408
"uri": "A String", # The URI of the content. Only Cloud Storage URIs (e.g. `gs://bucket-name/path/to/file`) are supported. The maximum file size is 2.5 MB for text-based formats, 200 MB for other formats.
Copy file name to clipboardExpand all lines: docs/dyn/discoveryengine_v1.projects.locations.collections.dataStores.html
+90Lines changed: 90 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -260,6 +260,15 @@ <h3>Method Details</h3>
260
260
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
261
261
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
262
262
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
263
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
264
+
"A String",
265
+
],
266
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
267
+
"A String",
268
+
],
269
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
270
+
"A String",
271
+
],
263
272
},
264
273
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
265
274
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
@@ -276,6 +285,15 @@ <h3>Method Details</h3>
276
285
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
277
286
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
278
287
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
288
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
289
+
"A String",
290
+
],
291
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
292
+
"A String",
293
+
],
294
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
295
+
"A String",
296
+
],
279
297
},
280
298
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
281
299
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
@@ -444,6 +462,15 @@ <h3>Method Details</h3>
444
462
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
445
463
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
446
464
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
465
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
466
+
"A String",
467
+
],
468
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
469
+
"A String",
470
+
],
471
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
472
+
"A String",
473
+
],
447
474
},
448
475
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
449
476
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
@@ -460,6 +487,15 @@ <h3>Method Details</h3>
460
487
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
461
488
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
462
489
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
490
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
491
+
"A String",
492
+
],
493
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
494
+
"A String",
495
+
],
496
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
497
+
"A String",
498
+
],
463
499
},
464
500
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
465
501
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
@@ -584,6 +620,15 @@ <h3>Method Details</h3>
584
620
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
585
621
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
586
622
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
623
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
624
+
"A String",
625
+
],
626
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
627
+
"A String",
628
+
],
629
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
630
+
"A String",
631
+
],
587
632
},
588
633
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
589
634
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
@@ -600,6 +645,15 @@ <h3>Method Details</h3>
600
645
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
601
646
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
602
647
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
648
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
649
+
"A String",
650
+
],
651
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
652
+
"A String",
653
+
],
654
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
655
+
"A String",
656
+
],
603
657
},
604
658
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
605
659
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
@@ -712,6 +766,15 @@ <h3>Method Details</h3>
712
766
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
713
767
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
714
768
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
769
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
770
+
"A String",
771
+
],
772
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
773
+
"A String",
774
+
],
775
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
776
+
"A String",
777
+
],
715
778
},
716
779
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
717
780
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
@@ -728,6 +791,15 @@ <h3>Method Details</h3>
728
791
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
729
792
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
730
793
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
794
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
795
+
"A String",
796
+
],
797
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
798
+
"A String",
799
+
],
800
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
801
+
"A String",
802
+
],
731
803
},
732
804
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
733
805
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
@@ -822,6 +894,15 @@ <h3>Method Details</h3>
822
894
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
823
895
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
824
896
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
897
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
898
+
"A String",
899
+
],
900
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
901
+
"A String",
902
+
],
903
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
904
+
"A String",
905
+
],
825
906
},
826
907
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
827
908
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
@@ -838,6 +919,15 @@ <h3>Method Details</h3>
838
919
"layoutParsingConfig": { # The layout parsing configurations for documents. # Configurations applied to layout parser.
839
920
"enableImageAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the image during parsing.
840
921
"enableTableAnnotation": True or False, # Optional. If true, the LLM based annotation is added to the table during parsing.
922
+
"excludeHtmlClasses": [ # Optional. List of HTML classes to exclude from the parsed content.
923
+
"A String",
924
+
],
925
+
"excludeHtmlElements": [ # Optional. List of HTML elements to exclude from the parsed content.
926
+
"A String",
927
+
],
928
+
"excludeHtmlIds": [ # Optional. List of HTML ids to exclude from the parsed content.
929
+
"A String",
930
+
],
841
931
},
842
932
"ocrParsingConfig": { # The OCR parsing configurations for documents. # Configurations applied to OCR parser. Currently it only applies to PDFs.
843
933
"enhancedDocumentElements": [ # [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to `layout_parsing_config`.
0 commit comments