Update app.py

app.py

@@ -5,15 +5,13 @@ import requests
 from flask import Flask, request, jsonify, send_from_directory
 from werkzeug.utils import secure_filename
 from PyPDF2 import PdfReader, PdfWriter
-from dotenv import load_dotenv
 
-# Load env
-load_dotenv()
+# --- Load env from Hugging Face Secrets ---
 AZURE_ENDPOINT = os.environ.get("AZURE_ENDPOINT")
 AZURE_KEY = os.environ.get("AZURE_KEY")
 
 if not AZURE_ENDPOINT or not AZURE_KEY:
-    raise RuntimeError("Set AZURE_ENDPOINT and AZURE_KEY in .env")
+    raise RuntimeError("Set AZURE_ENDPOINT and AZURE_KEY as environment variables")
 
 AZURE_ENDPOINT = AZURE_ENDPOINT.rstrip("/")
 UPLOAD_DIR = "/tmp/uploads"
@@ -28,27 +26,33 @@ app = Flask(__name__, static_folder="static", static_url_path="/static")
 def allowed_file(filename):
     return "." in filename and filename.rsplit(".", 1)[1].lower() in ALLOWED_EXTENSIONS
 
+
 def read_file_bytes(path):
     with open(path, "rb") as f:
         return f.read()
 
+
 def submit_read_api(file_path):
-    """Submit file to Computer Vision Read API"""
+    """Submit file to Azure Computer Vision OCR Read API"""
     url = f"{AZURE_ENDPOINT}/vision/v3.2/read/analyze"
     headers = {
         "Ocp-Apim-Subscription-Key": AZURE_KEY,
-        "Content-Type": "application/octet-stream"
+        "Content-Type": "application/octet-stream",
     }
     data = read_file_bytes(file_path)
 
     resp = requests.post(url, headers=headers, data=data)
-    resp.raise_for_status()
+    print("➡️ Azure OCR request:", url)
+    print("➡️ Status:", resp.status_code)
+    print("➡️ Headers:", resp.headers)
 
+    resp.raise_for_status()
     op_location = resp.headers.get("Operation-Location")
     if not op_location:
         raise RuntimeError(f"No Operation-Location header. Response: {resp.text}")
     return op_location
 
+
 def poll_read_result(operation_location, timeout=180, interval=2.0):
     """Poll until OCR is finished"""
     headers = {"Ocp-Apim-Subscription-Key": AZURE_KEY}
@@ -59,6 +63,7 @@ def poll_read_result(operation_location, timeout=180, interval=2.0):
         r.raise_for_status()
         j = r.json()
         status = j.get("status", "").lower()
+        print("📡 Polling Azure OCR:", status)
         if status in ("succeeded", "failed"):
             break
         time.sleep(interval)
@@ -72,9 +77,12 @@ def poll_read_result(operation_location, timeout=180, interval=2.0):
         for line in read_result.get("lines", []):
             lines.append(line["text"])
 
+    print(f"✅ Extracted {len(lines)} lines of text")
     return "\n".join(lines)
 
+
 def split_pdf_into_chunks(pdf_path, chunk_size=2):
+    """Split large PDF into smaller chunks for OCR"""
     reader = PdfReader(pdf_path)
     total_pages = len(reader.pages)
     chunk_files = []
@@ -94,6 +102,7 @@ def split_pdf_into_chunks(pdf_path, chunk_size=2):
 def index():
     return send_from_directory("static", "index.html")
 
+
 @app.route("/upload", methods=["POST"])
 def upload():
     if "file" not in request.files:
@@ -121,10 +130,24 @@ def upload():
             op_location = submit_read_api(path)
             extracted_text = poll_read_result(op_location)
     except Exception as e:
+        import traceback
+
+        print("❌ OCR Error:", e)
+        traceback.print_exc()
         return jsonify({"error": "OCR failed", "details": str(e)}), 500
 
     return jsonify({"text": extracted_text})
 
 
+# Health check
+@app.route("/ping-azure")
+def ping_azure():
+    try:
+        r = requests.get(AZURE_ENDPOINT, timeout=5)
+        return {"status": r.status_code}
+    except Exception as e:
+        return {"error": str(e)}
+
+
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=7860, debug=True)