Upload 3 files

app.py

@@ -1,196 +1,219 @@
 import os
-import gradio as gr
+import re
+import json
 import requests
-import inspect
 import pandas as pd
+from pathlib import Path
+from typing import Optional
+from dotenv import load_dotenv
+
+from langgraph.prebuilt import create_react_agent
+from langchain_core.messages import HumanMessage
+from langchain_core.tools import tool
+from langchain_openai import ChatOpenAI
+import inspect
 
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+load_dotenv()
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-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 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
-
-    if profile:
-        username= f"{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)
+
+class OpenRouterLLM(ChatOpenAI):
+    """Custom OpenRouter LLM wrapper for LangGraph"""
+    
+    def __init__(self, model: str = "deepseek/deepseek-v3.1-terminus", **kwargs):
+        api_key = os.getenv("OPENROUTER_API_KEY") or os.getenv("my_key")
+        super().__init__(
+            model=model,
+            openai_api_key=api_key,
+            openai_api_base="https://openrouter.ai/api/v1",
+            **kwargs
+        )
+
+
+# ------------------ TOOLS ------------------
+
+@tool
+def search_web(query: str) -> str:
+    """Search the web using DuckDuckGo for current information."""
     try:
-        agent = BasicAgent()
+        search_url = f"https://api.duckduckgo.com/?q={query}&format=json&no_html=1&skip_disambig=1"
+        response = requests.get(search_url, timeout=10)
+        if response.status_code == 200:
+            data = response.json()
+            results = []
+            if data.get("AbstractText"):
+                results.append(f"Abstract: {data['AbstractText']}")
+            if data.get("RelatedTopics"):
+                for topic in data["RelatedTopics"][:3]:
+                    if isinstance(topic, dict) and topic.get("Text"):
+                        results.append(f"Related: {topic['Text']}")
+            return "\n".join(results) if results else f"No results for '{query}'."
+        return f"Search failed with status code {response.status_code}"
     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}")
+        return f"Search error: {str(e)}"
+
+
+@tool
+def search_wikipedia(query: str) -> str:
+    """Search Wikipedia for factual information."""
     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
+        search_url = "https://en.wikipedia.org/api/rest_v1/page/summary/" + query.replace(" ", "_")
+        response = requests.get(search_url, timeout=10)
+        if response.status_code == 200:
+            data = response.json()
+            extract = data.get("extract", "")
+            return f"Wikipedia: {extract[:500]}..." if extract else f"No extract for '{query}'."
+        return f"Wikipedia search failed for '{query}'"
     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
-    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}")
-            continue
-        try:
-            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})
-        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}"})
-
-    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)
+        return f"Wikipedia search error: {str(e)}"
 
-    # 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}")
+@tool
+def execute_python(code: str) -> str:
+    """Execute Python code and return the result."""
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
-        final_status = (
-            f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            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}."
+        safe_globals = {
+            '__builtins__': {
+                'print': print, 'len': len, 'str': str, 'int': int, 'float': float,
+                'bool': bool, 'list': list, 'dict': dict, 'tuple': tuple, 'set': set,
+                'range': range, 'sum': sum, 'max': max, 'min': min, 'abs': abs,
+                'round': round, 'sorted': sorted, 'enumerate': enumerate, 'zip': zip,
+            },
+            'math': __import__('math'),
+            'json': __import__('json'),
+            'datetime': __import__('datetime'),
+            'random': __import__('random'),
+        }
+        import io, sys
+        old_stdout = sys.stdout
+        sys.stdout = mystdout = io.StringIO()
         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
+            exec(code, safe_globals)
+            output = mystdout.getvalue()
+        finally:
+            sys.stdout = old_stdout
+        return output if output else "Code executed successfully (no output)"
     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"Python execution error: {str(e)}"
+
 
+@tool
+def read_excel_file(file_path: str, sheet_name: Optional[str] = None) -> str:
+    """Read an Excel file and return its contents as a formatted string."""
+    try:
+        file_path_obj = Path(file_path)
+        if not file_path_obj.exists():
+            return f"Error: File not found at {file_path}"
+        if sheet_name and sheet_name.isdigit():
+            sheet_name = int(sheet_name)
+        elif sheet_name is None:
+            sheet_name = 0
+        df = pd.read_excel(file_path, sheet_name=sheet_name)
+        if len(df) > 20:
+            result = f"Excel file with {len(df)} rows and {len(df.columns)} columns:\n\n"
+            result += "First 10 rows:\n" + df.head(10).to_string(index=False)
+            result += f"\n\n... ({len(df) - 20} rows omitted) ...\n\n"
+            result += "Last 10 rows:\n" + df.tail(10).to_string(index=False)
+        else:
+            result = f"Excel file with {len(df)} rows and {len(df.columns)} columns:\n\n"
+            result += df.to_string(index=False)
+        return result
+    except Exception as e:
+        return f"Error reading Excel file: {str(e)}"
 
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic 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.
+@tool
+def read_text_file(file_path: str) -> str:
+    """Read a text file and return its contents."""
+    try:
+        file_path_obj = Path(file_path)
+        if not file_path_obj.exists():
+            return f"Error: File not found at {file_path}"
+        encodings = ['utf-8', 'utf-16', 'iso-8859-1', 'cp1252']
+        for encoding in encodings:
+            try:
+                with open(file_path_obj, 'r', encoding=encoding) as f:
+                    return f"File content ({encoding} encoding):\n\n{f.read()}"
+            except UnicodeDecodeError:
+                continue
+        return "Error: Could not decode file with any standard encoding"
+    except Exception as e:
+        return f"Error reading file: {str(e)}"
+
 
-        ---
-        **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.
-        """
-    )
+# ------------------ GAIA AGENT ------------------
 
-    gr.LoginButton()
+class GaiaAgent:
+    """LangGraph-based agent for GAIA tasks using OpenRouter DeepSeek"""
+    
+    def __init__(self):
+        print("Initializing GaiaAgent with LangGraph and OpenRouter DeepSeek...")
+        self.llm = OpenRouterLLM(
+            model="deepseek/deepseek-v3.1-terminus",
+            temperature=0.1,
+            max_tokens=2000
+        )
+        self.tools = [search_web, search_wikipedia, execute_python, read_excel_file, read_text_file]
+        prompt_modifier = self._get_system_prompt()
+
+        # Detect correct kwarg for your LangGraph version
+        sig = inspect.signature(create_react_agent)
+        accepted = sig.parameters.keys()
+        kwargs = {}
+        if "messages_modifier" in accepted:
+            kwargs["messages_modifier"] = prompt_modifier
+        elif "state_modifier" in accepted:
+            kwargs["state_modifier"] = prompt_modifier
+        elif "prompt" in accepted:
+            kwargs["prompt"] = prompt_modifier
+
+        self.agent = create_react_agent(self.llm, self.tools, **kwargs)
+        print("GaiaAgent initialized successfully!")
+
+    def _get_system_prompt(self) -> str:
+        return """You are an advanced AI agent designed to answer complex questions...
+(keep your original system prompt here)"""
+
+    def __call__(self, task_id: str, question: str) -> str:
+        try:
+            print(f"Processing task {task_id}: {question[:100]}...")
+            messages = [HumanMessage(content=question)]
+            result = self.agent.invoke({"messages": messages})
+            final_message = result["messages"][-1]
+            answer = final_message.content
+            return self._clean_answer(answer)
+        except Exception as e:
+            return f"Agent error: {e}"
+
+    def _clean_answer(self, answer: str) -> str:
+        # same cleaning code as before
+        answer = answer.strip()
+        if "final answer:" in answer.lower():
+            parts = re.split(r'final answer:', answer, flags=re.IGNORECASE)
+            if len(parts) > 1:
+                answer = parts[-1].strip()
+        prefixes = ["The answer is", "Answer:", "Result:", "Solution:",
+                    "Based on", "Therefore", "In conclusion", "So the answer is"]
+        for prefix in prefixes:
+            if answer.lower().startswith(prefix.lower()):
+                answer = answer[len(prefix):].strip()
+                if answer.startswith(':'):
+                    answer = answer[1:].strip()
+                break
+        if len(answer.split()) <= 3:
+            answer = answer.strip('"\'.')
+        return answer
+
+
+# ------------------ ENTRYPOINT ------------------
+
+import gradio as gr
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+agent = GaiaAgent()
 
-    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)
+def run_agent(prompt: str) -> str:
+    return agent("gaia_task", prompt)
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+demo = gr.Interface(fn=run_agent, inputs="text", outputs="text", title="GAIA Agent")
 
 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)
+    demo.launch(server_name="0.0.0.0", server_port=7860)

gaia_api.py

@@ -0,0 +1,207 @@
+from typing import Dict, List, Tuple
+import re
+import tempfile
+from pathlib import Path
+import pandas as pd
+import requests
+from pandas import DataFrame
+
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+QUESTIONS_URL = f"{DEFAULT_API_URL}/questions"
+SUBMIT_URL = f"{DEFAULT_API_URL}/submit"
+FILE_PATH = f"{DEFAULT_API_URL}/files/"
+
+
+# --- Helper Methods ---
+def fetch_all_questions() -> Dict:
+    """Fetches all questions from the specified API endpoint.
+
+    This function retrieves a list of questions from the API, handles potential errors
+    such as network issues, invalid responses, or empty question lists, and returns
+    the questions as a dictionary.
+
+    Returns:
+        Dict: A dictionary containing the questions data retrieved from the API.
+
+    Raises:
+        UserWarning: If there is an error fetching the questions, such as network issues,
+            invalid JSON response, or an empty question list.  The exception message
+            provides details about the specific error encountered.
+    """
+    print(f"Fetching questions from: {QUESTIONS_URL}")
+    response = requests.get(QUESTIONS_URL, timeout=15)
+    try:
+        response.raise_for_status()
+        questions_data = response.json()
+        if not questions_data:
+            print("Fetched questions list is empty.")
+            raise UserWarning("Fetched questions list is empty or invalid format.")
+        print(f"Fetched {len(questions_data)} questions.")
+        return questions_data
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching questions: {e}")
+        raise UserWarning(f"Error fetching questions: {e}")
+    except requests.exceptions.JSONDecodeError as e:
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        raise UserWarning(f"Error decoding server response for questions: {e}")
+    except Exception as e:
+        print(f"An unexpected error occurred fetching questions: {e}")
+        raise UserWarning(f"An unexpected error occurred fetching questions: {e}")
+
+
+def submit_answers(submission_data: dict, results_log: list) -> Tuple[str, DataFrame]:
+    """Submits answers to the scoring API and returns the submission status and results.
+
+    This function sends the provided answers to the scoring API, handles potential errors
+    such as network issues, server errors, or invalid responses, and returns a status
+    message indicating the success or failure of the submission, along with a DataFrame
+    containing the results log.
+
+    Args:
+        submission_data (dict): A dictionary containing the answers to be submitted.
+            Expected to have a structure compatible with the scoring API.
+        results_log (list): A list of dictionaries containing the results log.
+            This log is converted to a Pandas DataFrame and returned.
+
+    Returns:
+        Tuple[str, DataFrame]: A tuple containing:
+            - A status message (str) indicating the submission status and any relevant
+              information or error messages.
+            - A Pandas DataFrame containing the results log.
+
+    """
+    try:
+        response = requests.post(SUBMIT_URL, json=submission_data, timeout=60)
+        response.raise_for_status()
+        result_data = response.json()
+        final_status = (
+            f"Submission Successful!\n"
+            f"User: {result_data.get('username')}\n"
+            f"Overall Score: {result_data.get('score', 'N/A')}% "
+            f"({result_data.get('correct_count', '?')}/"
+            f"{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
+    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
+
+
+def run_agent(gaia_agent, questions_data: List[Dict]) -> Tuple[List[Dict], List[Dict]]:
+    """Runs the agent on a list of questions and returns the results and answers.
+
+    This function iterates through a list of questions, runs the provided agent on each
+    question, and collects the results and answers. It handles potential errors during
+    agent execution and returns the results log and the answers payload.
+
+    Args:
+        gaia_agent: An instance of the GaiaAgent class, which is responsible for
+            generating answers to the questions.
+        questions_data (List[Dict]): A list of dictionaries, where each dictionary
+            represents a question and contains at least the 'task_id' and 'question' keys.
+
+    Returns:
+        Tuple[List[Dict], List[Dict]]: A tuple containing:
+            - A list of dictionaries representing the results log, where each dictionary
+              contains the 'Task ID', 'Question', and 'Submitted Answer'.
+            - A list of dictionaries representing the answers payload, where each dictionary
+              contains the 'task_id' and 'submitted_answer'.
+    """
+    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")
+        question_text = process_file(task_id, question_text)
+        if not task_id or question_text is None:
+            print(f"Skipping invalid item (missing task_id or question): {item}")
+            continue
+        try:
+            submitted_answer = gaia_agent(task_id, question_text)
+            answers_payload.append(
+                {"task_id": task_id, "submitted_answer": submitted_answer}
+            )
+        except Exception as e:
+            print(f"Error running agent on task {task_id}: {e}")
+            submitted_answer = f"AGENT ERROR: {e}"
+
+        results_log.append(
+            {
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": submitted_answer,
+            }
+        )
+    return results_log, answers_payload
+
+
+def process_file(task_id: str, question_text: str) -> str:
+    """
+    Attempt to download a file associated with a task from the API.
+
+    - If the file exists (HTTP 200), it is saved to a temp directory and the local file path is returned.
+    - If no file is found (HTTP 404), returns the original question text.
+    - For all other HTTP errors, the exception is propagated to the caller.
+    """
+    file_url = f"{FILE_PATH}{task_id}"
+
+    try:
+        response = requests.get(file_url, timeout=30)
+        response.raise_for_status()
+    except requests.exceptions.RequestException as exc:
+        print(f"Exception in download_file>> {str(exc)}")
+        return question_text # Unable to get the file
+
+    # Determine filename from 'Content-Disposition' header, fallback to task_id
+    content_disposition = response.headers.get("content-disposition", "")
+    filename = task_id
+    match = re.search(r'filename="([^"]+)"', content_disposition)
+    if match:
+        filename = match.group(1)
+
+    # Save file in a temp directory
+    temp_storage_dir = Path(tempfile.gettempdir()) / "gaia_cached_files"
+    temp_storage_dir.mkdir(parents=True, exist_ok=True)
+
+    file_path = temp_storage_dir / filename
+    file_path.write_bytes(response.content)
+    
+    print(f"Downloaded file for task {task_id}: {filename}")
+    
+    return (
+        f"{question_text}\n\n"
+        f"---\n"
+        f"A file was downloaded for this task and saved locally at:\n"
+        f"{str(file_path)}\n"
+        f"---\n\n"
+    )

requirements.txt

@@ -1,2 +1,11 @@
 gradio
-requests
+gradio[oauth]
+requests
+python-dotenv
+pandas
+openpyxl
+xlrd
+langgraph>=0.2.0
+langchain-core>=0.3.0
+langchain-openai>=0.2.0
+langchain-community>=0.3.0