Update app.py

app.py

@@ -1,19 +1,71 @@
-import logging
-from fastapi import FastAPI, File, UploadFile, HTTPException
+import uvicorn
+from fastapi import FastAPI, UploadFile, File, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
+from typing import Optional
+import numpy as np
+from PIL import Image
 from paddleocr import PaddleOCR
 from doctr.io import DocumentFile
 from doctr.models import ocr_predictor
-import numpy as np
-from PIL import Image
 import io
+import logging
+
+class OCRAPIApp:
+    def __init__(self):
+        self.app = FastAPI(
+            docs_url="/",
+            title="OCR API",
+            version="1.0",
+        )
+        self.setup_routes()
+        self.paddle_ocr = PaddleOCR(lang='en', use_angle_cls=True)
+        self.doctr_model = ocr_predictor(pretrained=True)
+
+    def ocr_with_paddle(self, img):
+        try:
+            logging.info("Processing image with PaddleOCR...")
+            result = self.paddle_ocr.ocr(img)
+            text_output = ' '.join([line[1][0] for line in result[0]])
+            return text_output
+        except Exception as e:
+            logging.error(f"Error with PaddleOCR: {e}")
+            raise HTTPException(status_code=500, detail="Error processing image")
 
-# Set up logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
+    def ocr_with_doctr(self, file):
+        try:
+            logging.info("Processing PDF with Doctr...")
+            doc = DocumentFile.from_pdf(file)
+            result = self.doctr_model(doc)
+            text_output = ''
+            for page in result.pages:
+                for block in page.blocks:
+                    for line in block.lines:
+                        text_output += ' '.join([word.value for word in line.words]) + "\n"
+            return text_output
+        except Exception as e:
+            logging.error(f"Error with Doctr: {e}")
+            raise HTTPException(status_code=500, detail="Error processing PDF")
 
-app = FastAPI()
+    async def ocr_endpoint(self, file: UploadFile = File(...)):
+        try:
+            file_bytes = await file.read()
+            if file.filename.endswith(".pdf"):
+                text_output = self.ocr_with_doctr(io.BytesIO(file_bytes))
+            else:
+                img = np.array(Image.open(io.BytesIO(file_bytes)))
+                text_output = self.ocr_with_paddle(img)
+            return {"ocr_text": text_output}
+        except Exception as e:
+            logging.error(f"Error processing file: {e}")
+            raise HTTPException(status_code=500, detail="Error processing file")
 
+    def setup_routes(self):
+        self.app.post("/ocr")(self.ocr_endpoint)
+
+# Initialize the app
+app = OCRAPIApp().app
+
+# Add CORS middleware for cross-origin requests
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
@@ -22,59 +74,5 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-# Initialize models once at startup
-ocr_model = ocr_predictor(pretrained=True)
-paddle_ocr = PaddleOCR(lang='en', use_angle_cls=True)
-
-def ocr_with_doctr(file):
-    text_output = ''
-    try:
-        logger.info("Processing PDF with Doctr...")
-        doc = DocumentFile.from_pdf(file)
-        result = ocr_model(doc)
-        for page in result.pages:
-            for block in page.blocks:
-                for line in block.lines:
-                    text_output += " ".join([word.value for word in line.words]) + "\n"
-    except Exception as e:
-        logger.error(f"Error processing PDF: {e}")
-        raise HTTPException(status_code=500, detail=f"Error processing PDF: {e}")
-    return text_output
-
-def ocr_with_paddle(img):
-    finaltext = ''
-    try:
-        logger.info("Processing image with PaddleOCR...")
-        result = paddle_ocr.ocr(img)
-        for i in range(len(result[0])):
-            text = result[0][i][1][0]
-            finaltext += ' ' + text
-    except Exception as e:
-        logger.error(f"Error processing image: {e}")
-        raise HTTPException(status_code=500, detail=f"Error processing image: {e}")
-    return finaltext
-
-@app.post("/ocr/")
-async def perform_ocr(file: UploadFile = File(...)):
-    try:
-        logger.info(f"Received file: {file.filename}")
-        file_bytes = await file.read()
-        
-        if file.filename.endswith('.pdf'):
-            logger.info("Detected PDF file")
-            text_output = ocr_with_doctr(io.BytesIO(file_bytes))
-        else:
-            logger.info("Detected image file")
-            img = np.array(Image.open(io.BytesIO(file_bytes)))
-            text_output = ocr_with_paddle(img)
-        
-        logger.info("OCR completed successfully")
-        return {"ocr_text": text_output}
-
-    except Exception as e:
-        logger.error(f"Internal server error: {e}")
-        raise HTTPException(status_code=500, detail=f"Internal server error: {e}")
-
-@app.get("/test/")
-async def test_call():
-    return {"message": "Hi. I'm running"}
+if __name__ == "__main__":
+    uvicorn.run("your_file_name:app", host="0.0.0.0", port=8000, reload=True)