Update app.py

app.py

@@ -1,69 +1,95 @@
-from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
+from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, load_tool, tool
 import datetime
 import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
-
 from Gradio_UI import GradioUI
 
-# Below is an example of a tool that does nothing. Amaze us with your creativity !
-@tool
-def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
-    #Keep this format for the description / args / args description but feel free to modify the tool
-    """A tool that does nothing yet 
-    Args:
-        arg1: the first argument
-        arg2: the second argument
-    """
-    return "What magic will you build ?"
-
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
-    """A tool that fetches the current local time in a specified timezone.
+    """Get current time in specified timezone.
     Args:
-        timezone: A string representing a valid timezone (e.g., 'America/New_York').
+        timezone: Valid timezone (e.g., 'America/New_York')
     """
     try:
-        # Create timezone object
         tz = pytz.timezone(timezone)
-        # Get current time in that timezone
         local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
-        return f"The current local time in {timezone} is: {local_time}"
+        return f"Current time in {timezone}: {local_time}"
     except Exception as e:
-        return f"Error fetching time for timezone '{timezone}': {str(e)}"
-
+        return f"Error: {str(e)}"
 
+# Performance optimizations
 final_answer = FinalAnswerTool()
 
-# If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
-# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
-
+# Try alternative model endpoint if main is overloaded
 model = HfApiModel(
-max_tokens=2096,
-temperature=0.5,
-model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
-custom_role_conversions=None,
+    max_tokens=1024,  # Reduced from 2096 to limit output length
+    temperature=0.3,  # Reduced from 0.5 for more focused responses
+    model_id='Qwen/Qwen2.5-Coder-32B-Instruct',
+    custom_role_conversions=None,
 )
 
+# Fallback model configuration
+fallback_model = HfApiModel(
+    max_tokens=1024,
+    temperature=0.3,
+    model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud',
+    custom_role_conversions=None,
+)
 
-# Import tool from Hub
-image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
+# Load image generation tool (only if needed)
+# image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
 
-with open("prompts.yaml", 'r') as stream:
-    prompt_templates = yaml.safe_load(stream)
+# Optimized prompt templates
+optimized_prompts = {
+    "system": """You are a helpful coding assistant. Be concise and direct.
+    Focus on the specific task. Avoid unnecessary explanations unless requested.""",
+    "user": """Task: {task}
+    
+    Available tools: {tools}
     
+    Provide a clear, step-by-step solution."""
+}
+
+# Try to load custom prompts, fallback to optimized ones
+try:
+    with open("prompts.yaml", 'r') as stream:
+        prompt_templates = yaml.safe_load(stream)
+        # Add length limits to existing prompts
+        if 'system' in prompt_templates:
+            prompt_templates['system'] = prompt_templates['system'][:500]  # Limit system prompt
+except FileNotFoundError:
+    prompt_templates = optimized_prompts
+
+# Create agent with performance optimizations
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
-    max_steps=6,
-    verbosity_level=1,
+    tools=[final_answer, get_current_time_in_timezone],
+    max_steps=3,  # Reduced from 6 to limit processing time
+    verbosity_level=0,  # Reduced from 1 to minimize output
     grammar=None,
-    planning_interval=None,
-    name=None,
-    description=None,
+    planning_interval=2,  # Add planning interval for better step management
+    name="OptimizedAgent",
+    description="Fast, efficient coding assistant",
     prompt_templates=prompt_templates
 )
 
+# Add error handling and timeout
+def launch_with_optimizations():
+    try:
+        # Try main model first
+        GradioUI(agent).launch(
+            share=False,  # Disable sharing for better performance
+            server_name="127.0.0.1",
+            server_port=7860,
+            max_threads=4  # Limit concurrent threads
+        )
+    except Exception as e:
+        print(f"Main model failed: {e}")
+        print("Switching to fallback model...")
+        agent.model = fallback_model
+        GradioUI(agent).launch()
 
-GradioUI(agent).launch()
+if __name__ == "__main__":
+    launch_with_optimizations()