Update app.py

app.py

@@ -1,29 +1,171 @@
-
 import os
-import gradio as gr
 import requests
-import inspect
 import pandas as pd
-from dotenv import load_dotenv
-from agent import build_graph
-from langchain_core.messages import HumanMessage
+import gradio as gr
+import tempfile
+import json
+from pathlib import Path
+from typing import Union, Optional
+from smolagents import LiteLLMModel, DuckDuckGoSearchTool, CodeAgent, WikipediaSearchTool
+from smolagents.tools import Tool
 
-load_dotenv()
 
+# --- Function to Configure Google Credentials (ESSENTIAL) ---
+def setup_google_credentials():
+    """
+    Reads Google Cloud credential JSON content from an environment variable,
+    writes it to a temporary file, and sets the GOOGLE_APPLICATION_CREDENTIALS
+    environment variable to the path of that file.
+
+    This function should be called before any Google Cloud client library
+    (like the one used by LiteLLM for Vertex AI) is initialized.
+
+    Requires the service account key JSON content to be stored in an
+    environment variable named 'GOOGLE_APPLICATION_CREDENTIALS_JSON'.
+    Set this in your Hugging Face Space secrets.
+    """
+    credentials_json_str = os.environ.get("GOOGLE_APPLICATION_CREDENTIALS_JSON")
+    if not credentials_json_str:
+        print("ERROR: 'GOOGLE_APPLICATION_CREDENTIALS_JSON' secret not found in environment variables.")
+        print("       Please ensure you have set this secret in your Hugging Face Space settings.")
+        # Depending on requirements, you might want to raise an error here
+        # raise ValueError("Secret 'GOOGLE_APPLICATION_CREDENTIALS_JSON' not set.")
+        return False # Indicate failure
+
+    try:
+        # Create a secure temporary file to store the credentials
+        # delete=False ensures the file persists until the process exits or it's manually cleaned up.
+        # We need the file path to set the environment variable.
+        with tempfile.NamedTemporaryFile(mode='w', suffix=".json", delete=False, encoding='utf-8') as temp_f:
+            temp_f.write(credentials_json_str)
+            credentials_path = temp_f.name # Get the path to the temporary file
+
+        # Set the environment variable that Google client libraries expect
+        os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = credentials_path
+        print(f"Google Application Credentials successfully set to temporary file: {credentials_path}")
+        return True # Indicate success
+    except json.JSONDecodeError:
+        print("ERROR: Failed to parse the content of 'GOOGLE_APPLICATION_CREDENTIALS_JSON'. Ensure it's valid JSON.")
+        return False
+    except OSError as e:
+        print(f"ERROR: Failed to write credentials to temporary file: {e}")
+        return False
+    except Exception as e:
+        print(f"ERROR: An unexpected error occurred during Google credential setup: {e}")
+        # You might want to re-raise the exception depending on your error handling strategy
+        # raise e
+        return False
+
+# --- Call Credential Setup EARLY ---
+# This needs to run before any code (like BasicAgent initialization) tries to use Google Cloud services.
+print("Attempting to configure Google Cloud credentials...")
+CREDENTIALS_CONFIGURED = setup_google_credentials()
+if not CREDENTIALS_CONFIGURED:
+     print("WARNING: Google Cloud credentials setup failed. Agent initialization might fail.")
+
+
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 
-def run_and_submit_all(profile: gr.OAuthProfile | None):
+### Defining tools ###
+
+class ExcelToTextTool(Tool):
+    """Render an Excel worksheet as Markdown text."""
+
+    name = "excel_to_text"
+    description = (
+        "Read an Excel file and return a Markdown table of the requested sheet. "
+        "Accepts either the sheet name or the zero-based index."
+    )
+
+    inputs = {
+        "excel_path": {
+            "type": "string",
+            "description": "Path to the Excel file (.xlsx / .xls).",
+        },
+        "sheet_name": {
+            "type": "string",
+            "description": (
+                "Worksheet name or zero‑based index *as a string* (optional; default first sheet)."
+            ),
+            "nullable": True,
+        },
+    }
+
+    output_type = "string"
+
+    def forward(
+            self,
+            excel_path: str,
+            sheet_name: Optional[str] = None,
+    ) -> str:
+        """Load *excel_path* and return the sheet as a Markdown table."""
+
+        path = Path(excel_path).expanduser().resolve()
+        if not path.exists():
+            return f"Error: Excel file not found at {path}"
+
+        try:
+            # Interpret sheet identifier
+            sheet: Union[str, int]
+            if sheet_name is None or sheet_name == "":
+                sheet = 0 # first sheet
+            else:
+                # If the user passed a numeric string (e.g. "1"), cast to int
+                sheet = int(sheet_name) if sheet_name.isdigit() else sheet_name
+
+            # Load worksheet
+            df = pd.read_excel(path, sheet_name=sheet)
+
+            # Render to Markdown, fallback to tabulate if needed
+            if hasattr(pd.DataFrame, "to_markdown"):
+                return df.to_markdown(index=False)
+            from tabulate import tabulate
+
+            return tabulate(df, headers="keys", tablefmt="github", showindex=False)
+
+        except Exception as exc:  # broad catch keeps the agent chat‑friendly
+            return f"Error reading Excel file: {exc}"
+
+
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+class BasicAgent:
+    def __init__(self):
+        # Assuming you've set GOOGLE_API_KEY in secrets
+        google_api_key = os.environ.get("GOOGLE_API_KEY")
+        if not google_api_key:
+           raise ValueError("GOOGLE_API_KEY environment variable not set.")
+
+        # Check if the global credential setup was successful
+        if not CREDENTIALS_CONFIGURED:
+             raise ValueError("Google Cloud credentials could not be configured. Check startup logs and HF Secrets (ensure 'GOOGLE_APPLICATION_CREDENTIALS_JSON' is set correctly).")
+        self.agent = CodeAgent(
+            model=LiteLLMModel(model_id="gemini-2.0-flash"),
+            tools=[DuckDuckGoSearchTool(), WikipediaSearchTool(), ExcelToTextTool()],
+            add_base_tools=True,
+            additional_authorized_imports=['pandas','numpy','csv','subprocess']
+        )
+        print("BasicAgent initialized.")
+
+    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 answer: {fixed_answer}")
+        return fixed_answer
+
+def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the LangGraph Agent on them, submits all answers,
+    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
+    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.")
@@ -33,17 +175,15 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        # Use the build_graph function from agent.py
-        agent_graph = build_graph()
-        print("LangGraph agent initialized.")
+        agent = BasicAgent()
     except Exception as e:
-        print(f"Error instantiating agent graph: {e}")
-        return f"Error initializing agent graph: {e}", None
+        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" if space_id else "Agent code link unavailable (SPACE_ID not set)" # Added a check for SPACE_ID
-    print(f"Agent code link: {agent_code}")
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -52,16 +192,16 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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("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
+         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
@@ -70,60 +210,25 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-
-    # Removed the problematic print statement from here
-
     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
-
-        # Moved the print statement inside the loop, after task_id and question_text are assigned
-        print(f"--- Starting processing Task ID: {task_id}, Question: {question_text[:100]}...")
-
         try:
-            # Invoke the LangGraph agent
-            result_state = agent_graph.invoke({"messages": [HumanMessage(content=question_text)]})
-
-            # Extract the final answer from the last message
-            submitted_answer = "Error: Agent did not provide a response."  # Default in case extraction fails
-
-            if result_state and "messages" in result_state and result_state["messages"]:
-                last_message = result_state["messages"][-1]
-                # The final content is typically in the content attribute of the last message
-                if hasattr(last_message, 'content') and last_message.content:
-                    submitted_answer = last_message.content
-                # else: Handle cases where the last message might be a tool message etc.,
-                # for simplicity, we just use the default error message if content is missing.
-
-            # Ensure submitted_answer is a string
-            if not isinstance(submitted_answer, str):
-                submitted_answer = str(submitted_answer)
-
+            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})
-
-            # Moved this print statement inside the loop as well
-            print(f"--- Finished processing Task ID: {task_id}")
-            # Moved this print statement inside the loop as well
-            print(f"--- Extracted answer for Task ID: {task_id}: {submitted_answer[:100]}...")
-
-
         except Exception as e:
-            print(f"Error running agent graph on task {task_id}: {e}")
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-            # Note: If an error occurs, the 'Finished' and 'Extracted answer' prints for this specific task won't happen,
-            # which is reasonable behavior.
+             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.")
-        # Even if no answers, show the log of errors
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission
+    # 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)
@@ -174,15 +279,14 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# LangGraph Agent Evaluation Runner")  # Updated title
+    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
 
-        1.  Please clone this space, then modify the code in `agent.py` and `app.py` to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  **Make sure you have your `DEEPSEEK_API_KEY` set as a Space Secret.**
-        3.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        4.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+        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:**
@@ -196,6 +300,7 @@ 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(
@@ -204,10 +309,10 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
+    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
+    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -215,14 +320,14 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup:  # Print repo URLs if SPACE_ID is found
+    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("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for LangGraph Agent Evaluation...")  # Updated message
-    demo.launch(debug=True, share=False, auth=None)
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)