Update app.py

app.py

@@ -8,6 +8,10 @@ from langgraph.graph.message import add_messages
 from langchain_core.messages import AnyMessage, HumanMessage
 from langgraph.graph import START, StateGraph
 from langchain_google_genai import ChatGoogleGenerativeAI
+from ToolSet import toolset
+from utils.final_answer import extract_final_answer
+from utils.handle_file import handle_attachment
+from assignment_api import get_all_questions, get_one_random_question, submit
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -16,136 +20,285 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 gemini_api_key = os.getenv("GEMINI_API_KEY")
-tivaly_api_key = os.getenv()
-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):
+tivaly_api_key = os.getenv("TAVILY_API_KEY")
+
+llm = ChatGoogleGenerativeAI(
+    model="gemini-2.0-flash",
+    temperature=0,
+    google_api_key = gemini_api_key
+)
+
+llm_with_tools = llm.bind_tools(toolset)
+
+sys_prompt_file = open("sys_prompt.txt")
+sys_prompt = sys_prompt_file.read()
+
+class AgentState(TypedDict):
+    messages: Annotated[list[AnyMessage], add_messages]
+
+def assistant(state: AgentState):
+    return {
+        "messages": [llm_with_tools.invoke([sys_prompt]+state["messages"])],
+    }
+
+builder = StateGraph(AgentState)
+
+builder.add_node("assistant", assistant)
+builder.add_node("tools", ToolNode(available_tools))
+
+builder.add_edge(START, "assistant")
+builder.add_conditional_edges(
+    "assistant",
+    tools_condition
+)
+builder.add_edge("tools","assistant")
+
+gaia_agent = builder.compile()
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Fetches all questions, runs the agent on them, submits all answers,
+    and displays the results. Handles attachments if present.
     """
     # --- 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)
+    
+    # 1. Instantiate Agent (modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = my_agent
     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 (useful 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
-
+    questions_data = get_all_questions()
+    
     # 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
+        
+        # 2.2 Handle attachment if present
+        attachment_info = None
+        if "file_name" in item and item["file_name"]:
+            file_name = item.get("file_name")
+            attachment_info = handle_attachment(task_id, file_name)
+            print(f"Attachment handling result: {attachment_info['status']}")
+        
         try:
-            submitted_answer = agent(question_text)
+            # Prepare messages based on attachment handling
+            messages = [
+                SystemMessage(content=SYSTEM_PROMPT),
+                SystemMessage(content=f"Current task id: {task_id}")
+            ]
+            
+            # If we have an attachment that Claude can process directly
+            if attachment_info and attachment_info["status"] == "success" and attachment_info["handling"] == "direct":
+                # Encode content for direct inclusion
+                encoded_content = base64.b64encode(attachment_info["raw_content"]).decode('utf-8')
+                content_type = attachment_info["content_type"]
+                
+                # Create multimodal message
+                if content_type.startswith('image/'):
+                    multimodal_content = [
+                        {"type": "text", "text": question_text},
+                        {
+                            "type": "image", 
+                            "source": {
+                                "type": "base64", 
+                                "media_type": content_type,
+                                "data": encoded_content
+                            }
+                        }
+                    ]
+                elif content_type == "application/pdf" or "spreadsheet" in content_type or "excel" in content_type or "csv" in content_type:
+                    multimodal_content = [
+                        {"type": "text", "text": question_text},
+                        {
+                            "type": "file", 
+                            "source": {
+                                "type": "base64", 
+                                "media_type": content_type,
+                                "data": encoded_content
+                            },
+                            "name": attachment_info["file_name"]
+                        }
+                    ]
+                
+                messages.append(HumanMessage(content=multimodal_content))
+                
+            # If we have an attachment that needs tool processing
+            elif attachment_info and attachment_info["status"] == "success" and attachment_info["handling"] == "tool":
+                # Add info about the file to the question
+                file_info = (
+                    f"{question_text}\n\n"
+                    f"Note: This task has an attached file that can be accessed at: {attachment_info['file_path']}\n"
+                    f"File type: {attachment_info['content_type']}"
+                )
+                messages.append(HumanMessage(content=file_info))
+                
+            # If no attachment or error with attachment
+            else:
+                messages.append(HumanMessage(content=question_text))
+            
+            # Invoke the agent with the prepared messages
+            agent_answer = agent.invoke({"messages": messages},{"recursion_limit": 50})
+            submitted_answer = extract_final_answer(agent_answer['messages'][-1].content)
             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}"})
-
+            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)
-
+    
     # 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}")
+    return submit(submission_data, results_log)
+
+def run_and_submit_one( profile: gr.OAuthProfile | None):
+    # --- 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
+    
+    # 1. Instantiate Agent ( modify this part to create your agent)
     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}."
-        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
+        agent = my_agent
+    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
+    questions_data = get_one_random_question()
+    print("questions_data:", questions_data)
+    
+    # 2.2 Handle attachment if present
+    attachment_info = None
+    if "file_name" in questions_data and questions_data["file_name"]:
+        task_id = questions_data.get("task_id")
+        file_name = questions_data.get("file_name")
+        attachment_info = handle_attachment(task_id, file_name)
+        print(f"Attachment handling result: {attachment_info['status']}")
+
+    # 3. Run your Agent
+    results_log = []
+    answers_payload = []
+    print(f"Running agent on {len(questions_data)} questions...")
+
+    task_id = questions_data.get("task_id")
+    question_text = questions_data.get("question")
+
+    if not task_id or question_text is None:
+        print(f"Skipping item with missing task_id or question")
+    try:
+            # Prepare messages based on attachment handling
+            messages = [
+                SystemMessage(content=SYSTEM_PROMPT),
+                SystemMessage(content=f"Current task id: {task_id}")
+            ]
+            
+            # If we have an attachment that Claude can process directly
+            if attachment_info and attachment_info["status"] == "success" and attachment_info["handling"] == "direct":
+                # Encode content for direct inclusion
+                encoded_content = base64.b64encode(attachment_info["raw_content"]).decode('utf-8')
+                content_type = attachment_info["content_type"]
+                
+                # Create multimodal message
+                if content_type.startswith('image/'):
+                    multimodal_content = [
+                        {"type": "text", "text": question_text},
+                        {
+                            "type": "image", 
+                            "source": {
+                                "type": "base64", 
+                                "media_type": content_type,
+                                "data": encoded_content
+                            }
+                        }
+                    ]
+                elif content_type == "application/pdf" or "spreadsheet" in content_type or "excel" in content_type or "csv" in content_type:
+                    multimodal_content = [
+                        {"type": "text", "text": question_text},
+                        {
+                            "type": "file", 
+                            "source": {
+                                "type": "base64", 
+                                "media_type": content_type,
+                                "data": encoded_content
+                            },
+                            "name": attachment_info["file_name"]
+                        }
+                    ]
+                
+                messages.append(HumanMessage(content=multimodal_content))
+                
+            # If we have an attachment that needs tool processing
+            elif attachment_info and attachment_info["status"] == "success" and attachment_info["handling"] == "tool":
+                # Add info about the file to the question
+                file_info = (
+                    f"{question_text}\n\n"
+                    f"Note: This task has an attached file that can be accessed at: {attachment_info['file_path']}\n"
+                    f"File type: {attachment_info['content_type']}"
+                )
+                messages.append(HumanMessage(content=file_info))
+                
+            # If no attachment or error with attachment
+            else:
+                messages.append(HumanMessage(content=question_text))
+            
+            # Invoke the agent with the prepared messages
+            agent_answer = agent.invoke({"messages": messages},{"recursion_limit": 50})
+            submitted_answer = extract_final_answer(agent_answer['messages'][-1].content)
+            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:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+            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)
+
+    # 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)
 
+    return submit(submission_data, results_log)
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
@@ -153,11 +306,9 @@ with gr.Blocks() as demo:
     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).
@@ -168,6 +319,7 @@ with gr.Blocks() as demo:
     gr.LoginButton()
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_one_button = gr.Button("Run one question and submit")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
     # Removed max_rows=10 from DataFrame constructor
@@ -177,6 +329,10 @@ with gr.Blocks() as demo:
         fn=run_and_submit_all,
         outputs=[status_output, results_table]
     )
+    run_one_button.click(
+        fn=run_and_submit_one,
+        outputs=[status_output, results_table]
+    )
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)