Update app.py

app.py

@@ -18,6 +18,7 @@ import re
 import json
 from dotenv import load_dotenv
 import uvicorn
+import base64
 
 load_dotenv()
 
@@ -55,7 +56,7 @@ def fetch_file_from_s3_file(file_key):
         response = s3_client.get_object(Bucket=S3_BUCKET_NAME, Key=file_key)
         content_type = response['ContentType']  # Retrieve MIME type
         file_data = response['Body'].read()
-        return io.BytesIO(file_data), content_type  # Return file data as BytesIO
+        return file_data, content_type  # Return file data as BytesIO
     except Exception as e:
         raise Exception(f"Failed to fetch file from S3: {str(e)}")
 
@@ -102,13 +103,13 @@ def ocr_from_s3(api_key: str = Depends(verify_api_key),file_key: str = Query(...
         file_data, content_type = fetch_file_from_s3_file(file_key)
 
         extracted_text = []
-
+        base64Data = base64.b64encode(file_data).decode('utf-8')
         # Determine file type based on MIME type
         if content_type.startswith("image/"):  # Image file
-            image = Image.open(file_data).convert("RGB")  # Use BytesIO stream directly
+            image = Image.open(io.BytesIO(file_data)).convert("RGB")  # Use BytesIO stream directly
             image_np = np.array(image)  # Convert to NumPy array
             result = ocr.ocr(image_np, cls=True)
-
+            base64DataResp = f"data:image/{content_type.lower()};base64,{base64_data}"
             # Extract text from OCR results
             for line in result:
                 for word_info in line:
@@ -116,7 +117,7 @@ def ocr_from_s3(api_key: str = Depends(verify_api_key),file_key: str = Query(...
 
         elif content_type == "application/pdf":  # PDF file
             # Open PDF using PyMuPDF
-            pdf_document = fitz.open(stream=file_data, filetype="pdf")
+            pdf_document = fitz.open(stream=io.BytesIO(file_data), filetype="pdf")
 
             extracted_text = []
 
@@ -138,6 +139,7 @@ def ocr_from_s3(api_key: str = Depends(verify_api_key),file_key: str = Query(...
                         extracted_text.append(word_info[1][0])
 
             pdf_document.close()
+            base64DataResp = f"data:application/pdf;base64,{base64_data}"
         else:
             return {"error": f"Unsupported file type: {content_type}"}
 
@@ -150,6 +152,7 @@ def ocr_from_s3(api_key: str = Depends(verify_api_key),file_key: str = Query(...
         return {
             "file_key": file_key,
             "file_type": content_type,
+            "base64DataResp":base64DataResp,
             "extracted_text": full_text,
             "summary": summary
         }