Update app.py

app.py

@@ -3,7 +3,6 @@ import base64
 import httpx
 import os
 import asyncio
-# Import your backend FastAPI app from your src folder
 from src.main import app as fastapi_backend
 
 # Configuration
@@ -11,49 +10,32 @@ API_URL = "http://0.0.0.0:7860/api/document-analyze"
 API_KEY = os.getenv("API_KEY", "sk_track2_987654321")
 
 async def process_pipeline(file):
-    """
-    Handles the UI logic: 
-    1. Acknowledges the upload immediately.
-    2. Clears previous results.
-    3. Calls the AI backend and displays structured insights.
-    """
-    # 1. Validation - Yield error message if no file
     if file is None:
         yield "### ⚠️ Please upload a file first.", gr.update(visible=True)
-        return  # Stop the generator
+        return 
     
-    # 2. Instant Acknowledgment & Clearing Previous Results
     file_name = os.path.basename(file.name)
     yield f"⏳ **Processing {file_name}...** Analysing content with AI models.", gr.update(visible=True)
     
     try:
-        # 3. Prepare File Data
         ext = file_name.split('.')[-1].lower()
         file_type = "image" if ext in ['jpg', 'jpeg', 'png'] else ext
         
         with open(file.name, "rb") as f:
             encoded_string = base64.b64encode(f.read()).decode('utf-8')
 
-        payload = {
-            "fileName": file_name,
-            "fileType": file_type,
-            "fileBase64": encoded_string
-        }
+        payload = {"fileName": file_name, "fileType": file_type, "fileBase64": encoded_string}
         
-        # 4. Call Backend API
         async with httpx.AsyncClient(timeout=90.0) as client:
             headers = {"x-api-key": API_KEY}
             response = await client.post(API_URL, json=payload, headers=headers)
             res = response.json()
             
             if res.get("status") == "success":
-                # 5. Success Report Formatting
                 report = f"""
 # ✅ Analysis Complete: {res['fileName']}
-
 ### 🤖 AI Summary
 {res['summary']}
-
 ---
 ### 📊 Intelligent Insights
 - **Sentiment:** **{res['sentiment'].upper()}**
@@ -61,56 +43,25 @@ async def process_pipeline(file):
 - **🏢 Organizations:** {', '.join(res['entities']['organizations']) or 'None'}
 - **📅 Dates:** {', '.join(res['entities']['dates']) or 'None'}
 - **💰 Financials/KPIs:** {', '.join(res['entities']['amounts']) or 'None'}
-
-*Note: OCR was used for image processing to extract text data.*
 """
                 yield report, gr.update(visible=True)
             else:
                 yield f"### ❌ Backend Error\n{res.get('message')}", gr.update(visible=True)
-
     except Exception as e:
-        yield f"### ❌ System Error\nCould not connect to AI Engine: {str(e)}", gr.update(visible=True)
+        yield f"### ❌ System Error\n{str(e)}", gr.update(visible=True)
 
-# --- UI Layout Design ---
 with gr.Blocks(theme=gr.themes.Soft(primary_hue="indigo"), title="AI IDP Dashboard") as demo:
     gr.Markdown("# 🏢 Intelligent Document Processing (IDP) Dashboard")
-    gr.Markdown("Extract structured intelligence from **PDFs, Word Docs, and Images** using multi-modal AI.")
-    
     with gr.Row():
         with gr.Column(scale=1):
-            file_uploader = gr.File(
-                label="Step 1: Upload Document", 
-                file_types=[".pdf", ".docx", ".jpg", ".png", ".jpeg"]
-            )
-            with gr.Row():
-                submit_btn = gr.Button("🚀 Analyze Document", variant="primary")
-                clear_btn = gr.Button("🗑️ Clear")
-
+            file_uploader = gr.File(label="Upload Document", file_types=[".pdf", ".docx", ".jpg", ".png", ".jpeg"])
+            submit_btn = gr.Button("🚀 Analyze Document", variant="primary")
+            clear_btn = gr.Button("🗑️ Clear")
         with gr.Column(scale=2):
-            output_panel = gr.Markdown(
-                value="*Upload a file and click analyze to see results...*", 
-                elem_id="results-box"
-            )
-
-    # Functionality: Link Button to Pipeline
-    submit_btn.click(
-        fn=process_pipeline, 
-        inputs=file_uploader, 
-        outputs=[output_panel, output_panel],
-        show_progress="full"
-    )
-    
-    # Logic to Clear/Reset the UI
-    def reset_ui():
-        return None, "*Results will appear here...*"
-    
-    clear_btn.click(fn=reset_ui, outputs=[file_uploader, output_panel])
+            output_panel = gr.Markdown(value="*Results will appear here...*")
 
-# --- PRO DEPLOYMENT ---
-# Change the path from "/" to "/docs" or something unique
-# This allows Gradio to own the main "/" URL
-app = gr.mount_gradio_app(fastapi_backend, demo, path="/api-docs")
+    submit_btn.click(fn=process_pipeline, inputs=file_uploader, outputs=[output_panel, output_panel])
+    clear_btn.click(fn=lambda: (None, "*Results will appear here...*"), outputs=[file_uploader, output_panel])
 
-if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+# Mount Gradio onto FastAPI
+app = gr.mount_gradio_app(fastapi_backend, demo, path="/")