Update working_yolo_pipeline.py

working_yolo_pipeline.py

@@ -91,6 +91,52 @@ def sanitize_text(text: Optional[str]) -> str:
 
 
 
+# def get_latex_from_base64(base64_string: str) -> str:
+#     """
+#     Decodes a Base64 image string and uses the pre-initialized TrOCR/ORT model
+#     to recognize the formula. It cleans the output by removing spaces and
+#     crucially, replacing double backslashes with single backslashes for correct LaTeX.
+#     """
+#     if ort_model is None or processor is None:
+#         return "[MODEL_ERROR: Model not initialized]"
+
+#     try:
+#         # 1. Decode Base64 to Image
+#         image_data = base64.b64decode(base64_string)
+#         # We must ensure the image is RGB format for the model input
+#         image = Image.open(io.BytesIO(image_data)).convert('RGB')
+        
+#         # 2. Preprocess the image
+#         pixel_values = processor(images=image, return_tensors="pt").pixel_values
+        
+#         # 3. Text Generation (OCR)
+#         generated_ids = ort_model.generate(pixel_values)
+#         raw_generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
+        
+#         if not raw_generated_text:
+#             return "[OCR_WARNING: No formula found]"
+            
+#         latex_string = raw_generated_text[0]
+        
+#         # --- 4. Post-processing and Cleanup ---
+        
+#         # A. Remove all spaces/line breaks
+#         cleaned_latex = re.sub(r'\s+', '', latex_string)
+        
+#         # B. CRITICAL FIX: Replace double backslashes with single backslashes.
+      
+#         return cleaned_latex
+
+
+#     except Exception as e:
+#         # Catch any unexpected errors
+#         print(f"  ❌ TR-OCR Recognition failed: {e}")
+#         return f"[TR_OCR_ERROR: Recognition failed: {e}]"
+
+
+
+
+
 def get_latex_from_base64(base64_string: str) -> str:
     """
     Decodes a Base64 image string and uses the pre-initialized TrOCR/ORT model
@@ -123,7 +169,10 @@ def get_latex_from_base64(base64_string: str) -> str:
         # A. Remove all spaces/line breaks
         cleaned_latex = re.sub(r'\s+', '', latex_string)
         
-        # B. CRITICAL FIX: Replace double backslashes with single backslashes.
+        # B. CRITICAL FIX: Replace double backslashes (\\) with single backslashes (\).
+        # This corrects model output that already over-escaped the LaTeX commands.
+        # Python literal: '\\\\' is replaced with '\\'.
+        cleaned_latex = cleaned_latex.replace('\\\\', '\\')
       
         return cleaned_latex
 
@@ -136,9 +185,6 @@ def get_latex_from_base64(base64_string: str) -> str:
 
 
 
-
-
-
 # ============================================================================
 # --- CONFIGURATION AND CONSTANTS ---
 # ============================================================================