Update app.py

app.py

@@ -4,9 +4,17 @@ from pdf2image import convert_from_bytes
 from PIL import Image
 import pytesseract
 import io
+from concurrent.futures import ThreadPoolExecutor
 
 app = FastAPI()
 
+# एक page को OCR में डालने वाली function
+def ocr_page(image):
+    try:
+        return pytesseract.image_to_string(image, lang="hin+eng")
+    except Exception as e:
+        return f"⚠️ Error: {str(e)}"
+
 @app.post("/ocr")
 async def extract_text(file: UploadFile = File(...)):
     filename = file.filename.lower()
@@ -24,18 +32,21 @@ async def extract_text(file: UploadFile = File(...)):
     try:
         if filename.endswith(".pdf"):
             images = convert_from_bytes(contents)
-            for page in images:
-                text = pytesseract.image_to_string(page, lang="hin+eng")
-                extracted_text += text + "\n\n"
+
+            # ✅ सभी pages को parallel OCR में भेजते हैं
+            with ThreadPoolExecutor() as executor:
+                results = executor.map(ocr_page, images)
+
+            extracted_text = "\n\n".join(results)
+
         else:
             image = Image.open(io.BytesIO(contents))
-            text = pytesseract.image_to_string(image, lang="hin+eng")
-            extracted_text = text
+            extracted_text = pytesseract.image_to_string(image, lang="hin+eng")
 
         return {"text": extracted_text.strip() or "⚠️ No text found."}
-    
+
     except Exception as e:
         return JSONResponse(
             content={"error": "🚫 Failed to process file", "details": str(e)},
             status_code=500
-        )
+        )