feat: added hints.language_hints field in OcrConfig

Google APIs · copybara-github · commit 236be30123b2 · 2023-03-08T14:07:33.000-08:00
feat: added enable_image_quality_scores field in OcrConfig
feat: added enable_symbol field in OcrConfig

PiperOrigin-RevId: 515136707
diff --git a/google/cloud/documentai/v1beta3/document_io.proto b/google/cloud/documentai/v1beta3/document_io.proto
@@ -104,10 +104,32 @@ message DocumentOutputConfig {
 
 // Config for Document OCR.
 message OcrConfig {
+  // Hints for OCR Engine
+  message Hints {
+    // List of BCP-47 language codes to use for OCR. In most cases, not
+    // specifying it yields the best results since it enables automatic language
+    // detection. For languages based on the Latin alphabet, setting hints is
+    // not needed. In rare cases, when the language of the text in the
+    // image is known, setting a hint will help get better results (although it
+    // will be a significant hindrance if the hint is wrong).
+    repeated string language_hints = 1;
+  }
+
+  // Hints for the OCR model.
+  Hints hints = 2;
+
   // Enables special handling for PDFs with existing text information. Results
   // in better text extraction quality in such PDF inputs.
   bool enable_native_pdf_parsing = 3;
 
+  // Enables intelligent document quality scores after OCR. Can help with
+  // diagnosing why OCR responses are of poor quality for a given input.
+  // Adds additional latency comparable to regular OCR to the process call.
+  bool enable_image_quality_scores = 4;
+
   // A list of advanced OCR options to further fine-tune OCR behavior.
   repeated string advanced_ocr_options = 5;
+
+  // Includes symbol level OCR information if set to true.
+  bool enable_symbol = 6;
 }
