second update to app.py along with updates to requirements and packages

app.py

@@ -1,7 +1,13 @@
 from fastapi import FastAPI, UploadFile, File, HTTPException
-from fastapi.middleware.cors import CORSMiddleware # Important for frontend
+from fastapi.middleware.cors import CORSMiddleware
 import uuid
 import logging
+import io
+
+# NEW: Import parsing libraries
+import fitz  # PyMuPDF
+from PIL import Image
+import pytesseract
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -9,11 +15,10 @@ logger = logging.getLogger(__name__)
 
 app = FastAPI()
 
-# --- IMPORTANT: CORS Middleware ---
-# This allows your Netlify frontend to talk to this backend.
+# CORS Middleware
 app.add_middleware(
     CORSMiddleware,
-    allow_origins=["*"],  # Or specify your Netlify URL for production
+    allow_origins=["*"],
     allow_credentials=True,
     allow_methods=["*"],
     allow_headers=["*"],
@@ -23,39 +28,73 @@ app.add_middleware(
 SESSION_DATA = {}
 logger.info("Session store initialized.")
 
-@app.get("/")
-def read_root():
-    return {"message": "Universal Data AI is running!"}
+# --- NEW: Parsing Functions ---
+
+def parse_pdf(content: bytes) -> str:
+    """Extracts text from a PDF file's bytes."""
+    try:
+        doc = fitz.open(stream=content, filetype="pdf")
+        text = ""
+        for page in doc:
+            text += page.get_text()
+        logger.info(f"Successfully parsed PDF, extracted {len(text)} characters.")
+        return text
+    except Exception as e:
+        logger.error(f"PDF parsing failed: {e}")
+        return ""
+
+def parse_image(content: bytes) -> str:
+    """Extracts text from an image file's bytes using OCR."""
+    try:
+        image = Image.open(io.BytesIO(content))
+        text = pytesseract.image_to_string(image)
+        logger.info(f"Successfully parsed image, extracted {len(text)} characters.")
+        return text
+    except Exception as e:
+        logger.error(f"Image parsing failed: {e}")
+        return ""
+
+# --- MODIFIED: The /upload Endpoint ---
 
 @app.post("/upload")
 async def upload_file(file: UploadFile = File(...)):
     """
-    Accepts a file, creates a session, and stores the file content in memory.
+    Accepts a file, detects its type, parses it, and stores the extracted text.
     """
     session_id = str(uuid.uuid4())
-    logger.info(f"New upload received. Creating session_id: {session_id}")
+    logger.info(f"New upload '{file.filename}'. Creating session_id: {session_id}")
+    
+    content = await file.read()
+    extracted_text = ""
+    
+    # Simple dispatcher based on file's content type
+    if file.content_type == "application/pdf":
+        extracted_text = parse_pdf(content)
+    elif file.content_type and file.content_type.startswith("image/"):
+        extracted_text = parse_image(content)
+    elif file.content_type == "text/plain":
+        extracted_text = content.decode("utf-8")
+    else:
+        raise HTTPException(status_code=400, detail=f"Unsupported file type: {file.content_type}")
 
-    try:
-        # For now, we'll just store the content and filename.
-        # Later, this is where you'll call your parsing functions.
-        content = await file.read()
-        SESSION_DATA[session_id] = {
-            "filename": file.filename,
-            "content_type": file.content_type,
-            "data": content  # In a real app, you'd parse this
-        }
-        logger.info(f"File '{file.filename}' stored for session {session_id}")
-        return {"session_id": session_id, "filename": file.filename}
-    except Exception as e:
-        logger.error(f"Error processing file for session {session_id}: {e}")
-        raise HTTPException(status_code=500, detail="Error processing file.")
+    if not extracted_text:
+        raise HTTPException(status_code=400, detail="Could not extract any text from the file.")
 
-@app.get("/session/{session_id}")
-def get_session_data(session_id: str):
-    """
-    Retrieves the data stored for a given session.
-    """
+    # Store the EXTRACTED TEXT, not the raw file content
+    SESSION_DATA[session_id] = {
+        "filename": file.filename,
+        "text": extracted_text
+    }
+    
+    return {
+        "session_id": session_id,
+        "filename": file.filename,
+        "chars_extracted": len(extracted_text)
+    }
+
+# This endpoint is useful for debugging
+@app.get("/session/{session_id}/text")
+def get_session_text(session_id: str):
     if session_id not in SESSION_DATA:
         raise HTTPException(status_code=404, detail="Session not found.")
-    # Return metadata, not the raw data, for privacy
-    return {"filename": SESSION_DATA[session_id].get("filename")}
+    return {"text": SESSION_DATA[session_id].get("text", "")}

requirements.txt

@@ -1,3 +1,7 @@
 fastapi
 uvicorn[standard]
-python-multipart
+python-multipart
+
+PyMuPDF
+Pillow
+pytesseract