Update app.py

app.py

@@ -2,35 +2,281 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
-from smolagents import CodeAgent, DuckDuckGoSearchTool, OpenAIServerModel,HfApiModel
-# (Keep Constants as is)
+from smolagents import CodeAgent, DuckDuckGoSearchTool, OpenAIServerModel, Tool, PythonInterpreterTool
+
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# Custom file reading tool
+class FileReadTool(Tool):
+    name = "file_reader"
+    description = """
+    This tool reads the content of text files.
+    It's useful for processing plain text files (.txt, .csv, .json, etc).
+    """
+    inputs = {
+        "file_path": {
+            "type": "string",
+            "description": "The path to the file to read",
+        }
+    }
+    output_type = "string"
+    
+    def forward(self, file_path: str) -> str:
+        """
+        Reads the content of the given file.
+        """
+        try:
+            # Check if the file exists
+            if not os.path.exists(file_path):
+                return f"Error: File not found at {file_path}"
+                
+            # Read the file
+            with open(file_path, 'r', encoding='utf-8') as file:
+                content = file.read()
+                
+            # If the content is too long, truncate it
+            if len(content) > 10000:
+                content = content[:10000] + "...\n[Text truncated due to length]"
+                
+            return content or "File is empty."
+            
+        except Exception as e:
+            return f"Error reading file: {str(e)}"
+
+class PDFReaderTool(Tool):
+    name = "pdf_reader"
+    description = """
+    This tool extracts text content from PDF files.
+    It's useful for reading research papers, reports, or other document types.
+    """
+    inputs = {
+        "pdf_path": {
+            "type": "string",
+            "description": "The path to the PDF file to read",
+        }
+    }
+    output_type = "string"
+    
+    def forward(self, pdf_path: str) -> str:
+        """
+        Extracts text from the given PDF file.
+        """
+        try:
+            # Check if the file exists
+            if not os.path.exists(pdf_path):
+                return f"Error: PDF file not found at {pdf_path}"
+                
+            import PyPDF2
+            
+            # Open the PDF file
+            with open(pdf_path, 'rb') as file:
+                # Create a PDF reader object
+                pdf_reader = PyPDF2.PdfReader(file)
+                
+                # Get the number of pages
+                num_pages = len(pdf_reader.pages)
+                
+                # Extract text from all pages
+                text = ""
+                for page_num in range(num_pages):
+                    page = pdf_reader.pages[page_num]
+                    text += page.extract_text() + "\n\n"
+                
+                # If the text is too long, truncate it
+                if len(text) > 10000:
+                    text = text[:10000] + "...\n[Text truncated due to length]"
+                
+                return text or "No text could be extracted from the PDF."
+                
+        except Exception as e:
+            return f"Error reading PDF: {str(e)}"
+
+class ExcelReaderTool(Tool):
+    name = "excel_reader"
+    description = """
+    This tool reads and processes Excel files (.xlsx, .xls).
+    It can extract data, calculate statistics, and perform data analysis on spreadsheets.
+    """
+    inputs = {
+        "excel_path": {
+            "type": "string",
+            "description": "The path to the Excel file to read",
+        },
+        "sheet_name": {
+            "type": "string",
+            "description": "The name of the sheet to read (optional, defaults to first sheet)",
+            "nullable": True
+        }
+    }
+    output_type = "string"
+    
+    def forward(self, excel_path: str, sheet_name: str = None) -> str:
+        """
+        Reads and processes the given Excel file.
+        """
+        try:
+            # Check if the file exists
+            if not os.path.exists(excel_path):
+                return f"Error: Excel file not found at {excel_path}"
+                
+            import pandas as pd
+            
+            # Read the Excel file
+            if sheet_name:
+                df = pd.read_excel(excel_path, sheet_name=sheet_name)
+            else:
+                df = pd.read_excel(excel_path)
+                
+            # Get basic info about the data
+            info = {
+                "shape": df.shape,
+                "columns": list(df.columns),
+                "dtypes": df.dtypes.to_dict(),
+                "head": df.head(5).to_dict()
+            }
+            
+            # Return formatted info
+            result = f"Excel file: {excel_path}\n"
+            result += f"Shape: {info['shape'][0]} rows × {info['shape'][1]} columns\n\n"
+            result += "Columns:\n"
+            for col in info['columns']:
+                result += f"- {col} ({info['dtypes'].get(col)})\n"
+            
+            result += "\nPreview (first 5 rows):\n"
+            result += df.head(5).to_string()
+            
+            return result
+            
+        except Exception as e:
+            return f"Error reading Excel file: {str(e)}"
+
+class ImageAnalysisTool(Tool):
+    name = "image_analysis"
+    description = """
+    This tool analyzes an image and extracts relevant information from it.
+    It can describe image content, extract text from images, identify objects, etc.
+    """
+    inputs = {
+        "image_path": {
+            "type": "string",
+            "description": "The path to the image file to analyze",
+        }
+    }
+    output_type = "string"
+    
+    def forward(self, image_path: str) -> str:
+        """
+        Analyzes the given image and returns relevant information using OpenAI's ChatGPT API.
+        """
+        try:
+            # Check if the file exists
+            if not os.path.exists(image_path):
+                return f"Error: Image file not found at {image_path}"
+                
+            import requests
+            import base64
+            import json
+            from PIL import Image
+            
+            # Load the image
+            with open(image_path, "rb") as image_file:
+                image_bytes = image_file.read()
+                
+            # Convert to base64 for OpenAI API
+            encoded_image = base64.b64encode(image_bytes).decode('utf-8')
+            
+            # Get API key from environment
+            api_key = os.getenv('OPENAI_API_KEY', '')
+            if not api_key:
+                return "OpenAI API key not configured. Please add the OPENAI_API_KEY to your environment variables."
+            
+            # Prepare the API request for ChatGPT with vision capabilities
+            api_url = "https://api.openai.com/v1/chat/completions"
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {api_key}"
+            }
+            
+            payload = {
+                "model": "gpt-4o-mini-2024-07-18",  # Vision-capable model
+                "messages": [
+                    {
+                        "role": "user",
+                        "content": [
+                            {
+                                "type": "text",
+                                "text": "Analyze this image in detail. Describe what you see, including main subjects, activities, background elements, colors, and any text visible in the image. If there's text in the image, please extract it."
+                            },
+                            {
+                                "type": "image_url",
+                                "image_url": {
+                                    "url": f"data:image/jpeg;base64,{encoded_image}"
+                                }
+                            }
+                        ]
+                    }
+                ],
+                "max_tokens": 500
+            }
+            
+            response = requests.post(
+                api_url,
+                headers=headers,
+                json=payload
+            )
+            
+            if response.status_code != 200:
+                return f"Error: OpenAI API returned status code {response.status_code}. Details: {response.text}"
+                
+            result = response.json()
+            
+            # Extract the response content
+            if "choices" in result and len(result["choices"]) > 0:
+                analysis = result["choices"][0]["message"]["content"]
+                return f"Image analysis result: {analysis}"
+            else:
+                return f"Error: Unexpected response format from OpenAI API: {result}"
+                
+        except Exception as e:
+            return f"Error analyzing image: {str(e)}"
 
 # --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
         # Initialize the model
-        #model = HfApiModel()
-        model = HfApiModel(model_id="Qwen/Qwen2.5-Coder-32B-Instruct",api_key=os.environ['HF_TOKEN'])
-        # model = OpenAIServerModel(model_id="openai/gpt-4o",api_key=os.environ["API_KEY"],api_base="https://models.github.ai/inference")
-        # Initialize the search tool
-        search_tool = DuckDuckGoSearchTool()
+        model = OpenAIServerModel(model_id="openai/gpt-4o-mini",api_key=os.environ["API_KEY"],api_base="https://models.github.ai/inference")
+        
+        # Initialize tools
+        self.tools = [
+            DuckDuckGoSearchTool(),  # Built-in web search tool
+            FileReadTool(),          # Custom file reader
+            PDFReaderTool(),         # PDF reader
+            ExcelReaderTool(),       # Excel reader
+            ImageAnalysisTool(),     # Image analysis
+                   # Code execution
+        ]
+        
         # Initialize Agent
         self.agent = CodeAgent(
-            model = model,
-            tools=[search_tool]
+            model=model,
+            tools=self.tools,
+            add_base_tools=True  # Add basic tools like math
         )
+        
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer =self.agent.run(question)
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        try:
+            answer = self.agent.run(question)
+            print(f"Agent returned answer (first 50 chars): {answer[:50]}...")
+            return answer
+        except Exception as e:
+            error_msg = f"Error running agent: {str(e)}"
+            print(error_msg)
+            return f"I encountered an issue while processing your question: {str(e)}"
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
@@ -39,7 +285,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -49,13 +295,14 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
     try:
         agent = BasicAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+    
+    # In the case of an app running as a Hugging Face space, this link points toward your codebase
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
@@ -91,9 +338,11 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
+            print(f"Processing task {task_id}: {question_text[:50]}...")
             submitted_answer = agent(question_text)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            print(f"Completed task {task_id}")
         except Exception as e:
              print(f"Error running agent on task {task_id}: {e}")
              results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
@@ -153,17 +402,18 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Advanced Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+
+        1. Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+
         ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        **Note:**
+        Once you click on the "submit" button, it may take quite some time as the agent processes all the questions.
+        The agent is using SmolaAgents with multiple tools including web search, file processing, and code execution.
         """
     )
 
@@ -172,7 +422,6 @@ with gr.Blocks() as demo:
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -201,5 +450,5 @@ if __name__ == "__main__":
 
     print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("Launching Gradio Interface for Advanced Agent Evaluation...")
     demo.launch(debug=True, share=False)