Update app.py

app.py

@@ -1,103 +1,189 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from langchain.agents import AgentExecutor, create_react_agent
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts import PromptTemplate
+from langchain_community.tools import DuckDuckGoSearchRun
+from langchain.tools import Tool
+from langchain_community.tools import PythonREPLTool
+import tempfile
+import base64
+from langchain_core.messages import HumanMessage
+
+# For PDF and Excel handling - these imports will be used in process_file
+try:
+    from langchain_community.document_loaders import PyPDFLoader
+    import openpyxl  # For Excel
+except ImportError:
+    pass  # Assume installed during HF build
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# --- Advanced Agent Definition ---
+# ----- THIS IS WHERE THE ADVANCED LOGIC IS BUILT FOR HIGHER SCORES -----
 class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+    def __init__(self, api_url):
+        print("Advanced BasicAgent initialized with tool support.")
+        openai_api_key = os.getenv("OPENAI_API_KEY")
+        if not openai_api_key:
+            raise ValueError("OPENAI_API_KEY must be set in Hugging Face Space variables for the agent to work.")
+        
+        # Use a strong model like gpt-4o for better reasoning and vision
+        self.llm = ChatOpenAI(temperature=0, model="gpt-4o", api_key=openai_api_key)
+        
+        # Tools for web search, code execution, and file processing
+        self.search_tool = DuckDuckGoSearchRun(name="web_search", description="Search the web for information.")
+        self.python_tool = PythonREPLTool(description="Execute Python code for calculations or data processing. Input should be valid Python code.")
+        
+        # Custom tool for processing files (downloads from API, handles images/PDFs/Excel/text)
+        self.file_tool = Tool(
+            name="process_file",
+            func=self._process_file,
+            description="Download and process a file associated with a task. Input format: 'task_id: <id>, file_name: <name>'"
+        )
+        
+        self.tools = [self.search_tool, self.python_tool, self.file_tool]
+        
+        # React agent prompt template (inspired by GAIA prompting for exact answers)
+        self.prompt_template = PromptTemplate.from_template("""
+You are an expert AI agent solving GAIA benchmark questions. These questions require reasoning, tool use, and sometimes file processing.
+
+Question: {question}
+
+If the question mentions a file or attachment, use the 'process_file' tool with 'task_id: <task_id>, file_name: <file_name>'.
+
+Reason step-by-step using tools as needed. Output ONLY the final answer in the exact format required by the question. No explanations, no extra text.
+
+{agent_scratchpad}
+""")
+        
+        self.agent = create_react_agent(self.llm, self.tools, self.prompt_template)
+        self.executor = AgentExecutor(agent=self.agent, tools=self.tools, verbose=True, handle_parsing_errors=True, max_iterations=10)
+        
+        self.api_url = api_url
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    def _process_file(self, input_str: str) -> str:
+        """Internal function to download and process files."""
+        try:
+            # Parse input
+            parts = dict(part.strip().split(': ', 1) for part in input_str.split(', '))
+            task_id = parts.get('task_id')
+            file_name = parts.get('file_name')
+            if not task_id or not file_name:
+                return "Invalid input for process_file. Need 'task_id' and 'file_name'."
+            
+            # Download file
+            file_url = f"{self.api_url}/files/{task_id}"
+            response = requests.get(file_url, timeout=10)
+            response.raise_for_status()
+            
+            with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(file_name)[1]) as tmp:
+                tmp.write(response.content)
+                file_path = tmp.name
+            
+            ext = os.path.splitext(file_name)[1].lower()
+            
+            if ext in ['.jpg', '.png', '.jpeg', '.gif']:
+                # Use vision to describe image
+                with open(file_path, "rb") as img_file:
+                    base64_image = base64.b64encode(img_file.read()).decode('utf-8')
+                message = HumanMessage(content=[
+                    {"type": "text", "text": "Describe this image in detail, focusing on elements relevant to the question."},
+                    {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}}
+                ])
+                description = self.llm.invoke([message]).content
+                os.unlink(file_path)
+                return description
+            
+            elif ext == '.pdf':
+                loader = PyPDFLoader(file_path)
+                docs = loader.load()
+                text = "\n\n".join(doc.page_content for doc in docs)
+                os.unlink(file_path)
+                return text[:20000]  # Truncate if too long
+            
+            elif ext in ['.xlsx', '.xls']:
+                import pandas as pd
+                df = pd.read_excel(file_path)
+                os.unlink(file_path)
+                return df.to_string()
+            
+            else:
+                # Text file
+                with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
+                    text = f.read()
+                os.unlink(file_path)
+                return text[:20000]
+        
+        except Exception as e:
+            return f"Error processing file: {str(e)}"
+
+    def __call__(self, question: str, task_id: str, file_name: str | None = None) -> str:
+        print(f"Agent processing question (first 50 chars): {question[:50]}... (task_id: {task_id}, file: {file_name})")
+        input_prompt = question
+        if file_name:
+            input_prompt += f"\nThere is an attached file '{file_name}'. Use the 'process_file' tool with 'task_id: {task_id}, file_name: {file_name}' to access it."
+        
+        try:
+            response = self.executor.invoke({"question": input_prompt})
+            answer = response['output'].strip()
+            print(f"Agent returning answer: {answer}")
+            return answer
+        except Exception as e:
+            print(f"Error generating answer: {e}")
+            return "Agent error occurred."
 
+# Update the run_and_submit_all to pass task_id and file_name to agent
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
     if profile:
-        username= f"{profile.username}"
+        username = profile.username
         print(f"User logged in: {username}")
     else:
-        print("User not logged in.")
         return "Please Login to Hugging Face with the button.", None
-
+    
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
-
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    
     try:
-        agent = BasicAgent()
+        agent = BasicAgent(api_url)
     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)
+    
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+    
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
-        if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
-    except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
-
-    # 3. Run your Agent
+        return f"Error fetching questions: {e}", None
+    
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
-        if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
+        file_name = item.get("file_name")  # Assuming the API provides 'file_name'; if not, check item for attachments
+        if not task_id or not question_text:
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text, task_id, file_name)
             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})
         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}"})
-
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+    
     if not answers_payload:
-        print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-
-    # 4. Prepare Submission 
+    
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-    print(status_update)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -109,88 +195,28 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
             f"Message: {result_data.get('message', 'No message received.')}"
         )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
-        try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return final_status, pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
-
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Advanced Agent Evaluation Runner for GAIA (Aiming for 60%+)")
     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.
-
-        ---
-        **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.
+        1. Set OPENAI_API_KEY in Hugging Face Space variables (Settings > Variables).
+        2. Log in to Hugging Face.
+        3. Click 'Run Evaluation & Submit All Answers'.
+        
+        This agent uses GPT-4o with tools for search, code execution, and file processing (images/PDFs/Excel) to achieve higher scores.
         """
     )
-
     gr.LoginButton()
-
     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(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
-        print(f"✅ SPACE_ID found: {space_id_startup}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)