Update app.py from anycoder

app.py

@@ -40,303 +40,4 @@ Act as an agentic assistant, if a user asks for a long task, break it down and d
 
 When you want to commit changes, you will always use the 'git commit' bash command. It will always
 be suffixed with a line telling it was generated by Mistral Vibe with the appropriate co-authoring information.
-The format you will always uses is the following heredoc.
-
-```bash
-git commit -m "<Commit message here>
-
-Generated by Mistral Vibe.
-Co-Authored-By: Mistral Vibe <vibe@mistral.ai>"
-```"""
-
-# Tools configuration
-tools = [
-    {
-        "type": "function",
-        "function": {
-            "name": "add_number",
-            "description": "Add two numbers.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "a": {"type": "string", "description": "The first number."},
-                    "b": {"type": "string", "description": "The second number."},
-                },
-                "required": ["a", "b"],
-            },
-        },
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "multiply_number",
-            "description": "Multiply two numbers.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "a": {"type": "string", "description": "The first number."},
-                    "b": {"type": "string", "description": "The second number."},
-                },
-                "required": ["a", "b"],
-            },
-        },
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "substract_number",
-            "description": "Substract two numbers.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "a": {"type": "string", "description": "The first number."},
-                    "b": {"type": "string", "description": "The second number."},
-                },
-                "required": ["a", "b"],
-            },
-        },
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "write_a_story",
-            "description": "Write a story about science fiction and people with badass laser sabers.",
-            "parameters": {},
-        },
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "terminal",
-            "description": "Perform operations from the terminal.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "command": {
-                        "type": "string",
-                        "description": "The command you wish to launch, e.g `ls`, `rm`, ...",
-                    },
-                    "args": {
-                        "type": "string",
-                        "description": "The arguments to pass to the command.",
-                    },
-                },
-                "required": ["command"],
-            },
-        },
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "python",
-            "description": "Call a Python interpreter with some Python code that will be ran.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "code": {
-                        "type": "string",
-                        "description": "The Python code to run",
-                    },
-                    "result_variable": {
-                        "type": "string",
-                        "description": "Variable containing the result you'd like to retrieve from the execution.",
-                    },
-                },
-                "required": ["code", "result_variable"],
-            },
-        },
-    },
-]
-
-@spaces.GPU(duration=60)  # Use ZeroGPU with 60 second duration
-def chat_function_gpu(message, history):
-    try:
-        # Prepare input messages
-        messages = [
-            {
-                "role": "system",
-                "content": SP,
-            },
-            {
-                "role": "user",
-                "content": [
-                    {
-                        "type": "text",
-                        "text": message,
-                    }
-                ],
-            },
-        ]
-
-        # Tokenize input
-        tokenized = tokenizer.apply_chat_template(
-            conversation=messages,
-            tools=tools,
-            return_tensors="pt",
-            return_dict=True,
-        )
-
-        input_ids = tokenized["input_ids"].to(device="cuda")
-
-        # Generate output with GPU acceleration
-        output = model.generate(
-            input_ids,
-            max_new_tokens=200,
-            do_sample=True,
-            temperature=0.7,
-            top_p=0.9,
-            num_return_sequences=1
-        )[0]
-
-        # Decode and return response
-        decoded_output = tokenizer.decode(output[len(tokenized["input_ids"][0]) :])
-        return decoded_output
-
-    except Exception as e:
-        return f"Error processing your request: {str(e)}"
-
-# Fallback CPU function for when GPU is not available
-def chat_function_cpu(message, history):
-    try:
-        # Prepare input messages
-        messages = [
-            {
-                "role": "system",
-                "content": SP,
-            },
-            {
-                "role": "user",
-                "content": [
-                    {
-                        "type": "text",
-                        "text": message,
-                    }
-                ],
-            },
-        ]
-
-        # Tokenize input with CPU configuration
-        tokenized = tokenizer.apply_chat_template(
-            conversation=messages,
-            tools=tools,
-            return_tensors="pt",
-            return_dict=True,
-        )
-
-        input_ids = tokenized["input_ids"].to(device="cpu")
-
-        # Generate output with CPU-optimized settings
-        output = model.generate(
-            input_ids,
-            max_new_tokens=100,  # Reduced for CPU performance
-            do_sample=True,
-            temperature=0.7,
-            top_p=0.9,
-            num_return_sequences=1
-        )[0]
-
-        # Decode and return response
-        decoded_output = tokenizer.decode(output[len(tokenized["input_ids"][0]) :])
-        return decoded_output
-
-    except Exception as e:
-        return f"Error processing your request: {str(e)}"
-
-# Create custom theme optimized for ZeroGPU
-custom_theme = gr.themes.Soft(
-    primary_hue="blue",
-    secondary_hue="indigo",
-    neutral_hue="slate",
-    font=gr.themes.GoogleFont("Inter"),
-    text_size="lg",
-    spacing_size="lg",
-    radius_size="md"
-).set(
-    button_primary_background_fill="*primary_600",
-    button_primary_background_fill_hover="*primary_700",
-    block_title_text_weight="600",
-)
-
-# Create Gradio interface with ZeroGPU support
-with gr.Blocks() as demo:
-    chatbot = gr.Chatbot(height=600)
-    msg = gr.Textbox(
-        label="Your Message",
-        placeholder="Type your message here...",
-        lines=3
-    )
-
-    # Clear button
-    clear_btn = gr.ClearButton([msg, chatbot])
-
-    # Submit button with loading indicator
-    submit_btn = gr.Button("Send", variant="primary")
-
-    # Status indicator
-    status_text = gr.Markdown("Ready for your input...")
-
-    def update_status(text):
-        return text
-
-    # Event handlers with status updates
-    def handle_submit(message, history):
-        if torch.cuda.is_available():
-            status_text.value = "Processing with ZeroGPU acceleration..."
-            response = chat_function_gpu(message, history)
-        else:
-            status_text.value = "Processing with CPU (ZeroGPU quota may be exhausted)..."
-            response = chat_function_cpu(message, history)
-        status_text.value = "Ready for your input..."
-        return response
-
-    msg.submit(
-        fn=handle_submit,
-        inputs=[msg, chatbot],
-        outputs=[chatbot],
-        api_visibility="public"
-    )
-
-    submit_btn.click(
-        fn=handle_submit,
-        inputs=[msg, chatbot],
-        outputs=[chatbot],
-        api_visibility="public"
-    )
-
-    # Examples with ZeroGPU information
-    gr.Examples(
-        examples=[
-            "Can you implement in Python a method to compute the fibonnaci sequence at the nth element with n a parameter passed to the function?",
-            "What are the available tools I can use?",
-            "Can you write a story about science fiction with laser sabers?"
-        ],
-        inputs=msg,
-        label="Example Prompts (Powered by ZeroGPU when available)"
-    )
-
-# Launch with custom theme and ZeroGPU settings
-demo.launch(
-    theme=custom_theme,
-    footer_links=[
-        {
-            "label": "Built with anycoder",
-            "url": "https://huggingface.co/spaces/akhaliq/anycoder"
-        },
-        {
-            "label": "Mistral AI",
-            "url": "https://mistral.ai"
-        },
-        {
-            "label": "Hugging Face ZeroGPU",
-            "url": "https://huggingface.co/docs/hub/spaces-zerogpu"
-        },
-        {
-            "label": "Hugging Face Spaces",
-            "url": "https://huggingface.co/spaces"
-        }
-    ],
-    share=False,  # Disable share for Spaces deployment
-    max_threads=4,  # Allow more threads for GPU processing
-    show_error=True,
-    enable_queue=True
-)
+The format you will always uses is the following heredoc.