updatedd app

app.py

@@ -1,65 +1,213 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 import os
+import json
 
-# Initialize the Inference Client with correct endpoint
-client = InferenceClient(
-    token=os.getenv("HF_TOKEN"),
-    base_url="https://router.huggingface.co"  # Updated endpoint
-)
+# Initialize the Inference Client
+client = InferenceClient(token=os.getenv("HF_TOKEN"))
 
 def chat_with_fara(message, history):
     """
-    Interact with Fara-7B model via updated Hugging Face Inference API
+    Interact with Fara-7B using the correct format for agent tasks
     """
     try:
-        # Build the conversation prompt
-        conversation = ""
+        # Build the prompt in the expected format for Fara-7B
+        # Fara-7B is designed for web automation tasks with specific structure
+        system_prompt = """You are Fara, a web automation agent. You help users with web-based tasks by providing step-by-step guidance for browser automation."""
         
-        # Add conversation history
-        for user_msg, assistant_msg in history:
-            conversation += f"User: {user_msg}\nAssistant: {assistant_msg}\n\n"
+        # Format messages for the model
+        messages = [
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": message}
+        ]
         
-        # Add current message
-        conversation += f"User: {message}\nAssistant:"
+        # Use the conversational endpoint which is more appropriate
+        response = client.conversational(
+            text=message,
+            model="microsoft/Fara-7B",
+            max_length=500,
+            temperature=0.7
+        )
+        
+        # Extract the response
+        if hasattr(response, 'generated_text'):
+            return response.generated_text
+        elif isinstance(response, str):
+            return response
+        else:
+            return str(response)
+            
+    except Exception as e:
+        error_msg = f"❌ Error: {str(e)}"
+        
+        # Provide specific guidance based on common errors
+        if "401" in str(e):
+            error_msg += "\n\n🔐 Authentication failed. Please check:"
+            error_msg += "\n- Your HF_TOKEN is set in Space secrets"
+            error_msg += "\n- You have requested access to microsoft/Fara-7B"
+            error_msg += "\n- Your token has the necessary permissions"
+        elif "404" in str(e):
+            error_msg += "\n\n🔍 Model not found. The model might be:"
+            error_msg += "\n- Private and requiring access request"
+            error_msg += "\n- Temporarily unavailable"
+        elif "403" in str(e):
+            error_msg += "\n\n🚫 Access forbidden. You need to:"
+            error_msg += "\n- Visit https://huggingface.co/microsoft/Fara-7B"
+            error_msg += "\n- Click 'Access repository' to request access"
+            error_msg += "\n- Wait for approval from Microsoft"
+        
+        return error_msg
+
+# Alternative: Use text generation with proper formatting
+def chat_with_fara_text_generation(message, history):
+    """
+    Alternative approach using text generation with proper prompt formatting
+    """
+    try:
+        # Format prompt for agent tasks
+        prompt = f"""<|system|>
+You are Fara, a web automation agent designed to help users with web-based tasks.
+
+When responding:
+1. Break down complex web tasks into steps
+2. Suggest specific actions that could be automated
+3. Identify potential challenges in web automation
+4. Provide practical guidance for browser automation
+
+<|user|>
+{message}
+<|assistant|>
+"""
         
-        # Call the inference API
         response = client.text_generation(
-            prompt=conversation,
+            prompt=prompt,
             model="microsoft/Fara-7B",
             max_new_tokens=500,
             temperature=0.7,
             do_sample=True
         )
         
+        # Clean the response
+        if "<|assistant|>" in response:
+            response = response.split("<|assistant|>")[-1].strip()
+        
         return response
         
     except Exception as e:
-        return f"❌ API Error: {str(e)}"
+        return f"❌ Text generation error: {str(e)}"
+
+# Fallback function for when Fara-7B is not accessible
+def fallback_chat(message, history):
+    """
+    Fallback when Fara-7B is not accessible
+    """
+    fallback_responses = {
+        "web automation": "For web automation tasks like the NSW grants search, you would typically:\n\n1. Navigate to https://www.nsw.gov.au/grants-and-funding\n2. Use search functionality to filter for 'healthcare' grants\n3. Extract the list of available funding opportunities\n4. Provide summaries with eligibility criteria and deadlines",
+        
+        "general": "I'd be happy to help with web automation tasks! For tasks like finding grants on government websites, the process involves:\n- Website navigation\n- Search and filtering\n- Data extraction\n- Result organization"
+    }
+    
+    # Simple keyword-based fallback
+    message_lower = message.lower()
+    if any(keyword in message_lower for keyword in ['grant', 'funding', 'nsw', 'healthcare']):
+        return fallback_responses["web automation"]
+    else:
+        return fallback_responses["general"]
+
+def smart_chat_handler(message, history):
+    """
+    Smart handler that tries multiple approaches
+    """
+    # First try the conversational API
+    try:
+        response = chat_with_fara(message, history)
+        if "Error" not in response and "error" not in response.lower():
+            return response
+    except:
+        pass
+    
+    # Then try text generation
+    try:
+        response = chat_with_fara_text_generation(message, history)
+        if "Error" not in response and "error" not in response.lower():
+            return response
+    except:
+        pass
+    
+    # Finally use fallback
+    return fallback_chat(message, history)
 
 # Create the Gradio interface
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🤖 Fara-7B Chat Interface")
+    gr.Markdown(
+        """
+        # 🤖 Fara-7B Web Automation Assistant
+        
+        **Microsoft's specialized agent for web automation tasks**
+        
+        This interface connects to the Fara-7B model designed for:
+        - Web navigation and automation
+        - Task planning for browser actions
+        - Step-by-step guidance for web tasks
+        
+        ⚠️ **Note**: Access to Fara-7B requires permission from Microsoft.
+        """
+    )
     
-    chatbot = gr.Chatbot(height=400)
-    msg = gr.Textbox(
-        label="Your Message",
-        placeholder="Ask me about web automation tasks...",
-        lines=2
+    # Add access information
+    with gr.Accordion("🔐 Access Requirements", open=False):
+        gr.Markdown("""
+        To use Fara-7B, you need:
+        1. **Access Request**: Visit [the model page](https://huggingface.co/microsoft/Fara-7B) and click "Access repository"
+        2. **HF_TOKEN**: Add your Hugging Face token in Space secrets
+        3. **Wait for Approval**: Microsoft needs to approve your access request
+        
+        If you don't have access yet, this demo will show how Fara-7B would respond to web automation tasks.
+        """)
+    
+    chatbot = gr.Chatbot(
+        height=500,
+        label="Web Automation Chat",
+        show_label=True
     )
     
     with gr.Row():
-        send_btn = gr.Button("Send")
-        clear_btn = gr.Button("Clear")
+        msg = gr.Textbox(
+            label="Web Task Description",
+            placeholder="Example: Go to NSW grants website and find healthcare funding...",
+            lines=2,
+            scale=4
+        )
+        send_btn = gr.Button("Execute Task", scale=1, variant="primary")
+    
+    with gr.Row():
+        clear_btn = gr.Button("Clear Chat")
+        method_btn = gr.Button("Check Access Status")
+    
+    output_status = gr.Textbox(label="Status", visible=False)
     
     def respond(message, chat_history):
-        bot_response = chat_with_fara(message, chat_history)
-        chat_history.append((message, bot_response))
+        response = smart_chat_handler(message, chat_history)
+        chat_history.append((message, response))
         return "", chat_history
     
+    def check_access():
+        try:
+            # Simple test to check if model is accessible
+            test_client = InferenceClient(token=os.getenv("HF_TOKEN"))
+            test_response = test_client.model_status("microsoft/Fara-7B")
+            return "✅ Fara-7B is accessible!"
+        except Exception as e:
+            return f"❌ Access issue: {str(e)}"
+    
     msg.submit(respond, [msg, chatbot], [msg, chatbot])
     send_btn.click(respond, [msg, chatbot], [msg, chatbot])
     clear_btn.click(lambda: ([], ""), outputs=[chatbot, msg])
+    method_btn.click(check_access, outputs=output_status)
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=False
+    )