Update app.py

Adds a single tool that describes a plant image if provided

app.py

@@ -1,3 +1,14 @@
+"""
+This app.py consitutes an application where users can pose queries to
+an agent about plants.
+
+The user can provide pictures and text about plants and expect the agent to answer
+their questions about said plant.
+
+Useful tools: 
+1. DuckDuckGoSearchTool -- get internet search results about plant
+2. 
+"""
 from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
 import datetime
 import requests
@@ -7,33 +18,44 @@ 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 ?"
+
+vl_model = InferenceClient(model='Qwen/Qwen3-VL-4B-Thinking')
 
 @tool
-def get_current_time_in_timezone(timezone: str) -> str:
-    """A tool that fetches the current local time in a specified timezone.
-    Args:
-        timezone: A string representing a valid timezone (e.g., 'America/New_York').
+def describe_plant_image(user_query: str, image_url: str) -> str:
+    """
+    Describe a plant image and answer the user's query.
+    Only to be used if and only if a user provides an image_url or if
+    prior chat messages have retrieved image_url(s).
     """
-    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}"
-    except Exception as e:
-        return f"Error fetching time for timezone '{timezone}': {str(e)}"
+    system_prompt = (
+        "You are an LLM assistant that analyzes plant images and:\n"
+        "1. Identifies the plant if possible\n"
+        "2. Describes key visible characteristics\n"
+        "3. Answers the user's question clearly and concisely"
+    )
 
+    response = vl_model.chat.completions.create(
+        messages=[
+            {
+                "role": "system",
+                "content": system_prompt,
+            },
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": user_query},
+                    {
+                        "type": "image_url",
+                        "image_url": {"url": image_url},
+                    },
+                ],
+            },
+        ]
+    )
 
+    return response.choices[0].message.content
+    
 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:
@@ -55,7 +77,7 @@ with open("prompts.yaml", 'r') as stream:
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
+    tools=[DuckDuckGoSearchTool, describe_plant_image, final_answer], ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,
     grammar=None,