Added gemini agent

agent_gemini.py

@@ -0,0 +1,193 @@
+import logging
+import os
+
+import tempfile
+
+from langchain.agents import AgentExecutor, create_tool_calling_agent
+from langchain_google_community import GoogleSearchResults
+from langchain_google_community import GoogleSearchAPIWrapper
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.tools import Tool
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_experimental.utilities import PythonREPL
+
+from tools_audio import transcribe_audio
+
+from tools_doc import (
+    analyze_csv_file,
+    analyze_excel_file,
+    download_file_from_url,
+    extract_text_from_image,
+    read_file,
+)
+from tools_video import (
+    review_youtube_video,
+    use_vision_model,
+    transcribe_youtube,
+    video_frames_to_images,
+)
+
+from tools_browser import website_scrape, web_search
+
+from answers import create_final_answer_graph, validate_answer
+
+logger = logging.getLogger(__name__)
+
+
+class BasicAgent:
+    def __init__(self):
+        try:
+            logger.info("Initializing BasicAgent")
+
+            # Create the prompt template
+            prompt = ChatPromptTemplate.from_messages(
+                [
+                    (
+                        "system",
+                        """You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+                """,
+                    ),
+                    ("placeholder", "{chat_history}"),
+                    ("human", "{input}"),
+                    ("placeholder", "{agent_scratchpad}"),
+                ]
+            )
+            logger.info("Created prompt template")
+
+            # Initialize Gemini model
+            logger.info("Creating Gemini model...")
+            llm = ChatGoogleGenerativeAI(
+                model="models/gemini-2.5-pro-preview-03-25",
+                google_api_key=os.getenv("GEMINI_KEY"),
+                temperature=0.2,
+            )
+            logger.info("Created Gemini model successfully")
+
+            # Define available tools
+            tools = [
+                # GoogleSearchResults(
+                #     api_wrapper=GoogleSearchAPIWrapper(
+                #         google_api_key=os.getenv("GOOGLE_SEARCH_API_KEY"),
+                #         google_cse_id=os.getenv("GOOGLE_CSE_ID"),
+                #         k=5,  # Number of results to return
+                #     )
+                # ),
+                web_search,
+                analyze_csv_file,
+                analyze_excel_file,
+                download_file_from_url,
+                extract_text_from_image,
+                read_file,
+                review_youtube_video,
+                transcribe_audio,
+                transcribe_youtube,
+                use_vision_model,
+                video_frames_to_images,
+                website_scrape,
+                Tool(
+                    name="python_repl",
+                    description="A Python shell. Use this to execute python commands. Input # should be a valid python command. If you want to see the output of a value, # you should print it out with `print(...)`.",
+                    func=PythonREPL().run,
+                ),
+            ]
+            logger.info("Tools: %s", tools)
+
+            # Create the agent
+            agent = create_tool_calling_agent(llm, tools, prompt)
+            logger.info("Created tool calling agent")
+
+            # Create the agent executor
+            self.agent_executor = AgentExecutor(
+                agent=agent,
+                tools=tools,
+                return_intermediate_steps=True,
+                verbose=True,
+            )
+            logger.info("Created agent executor")
+
+            # Create the graph
+            self.validation_graph = create_final_answer_graph()
+
+        except Exception as e:
+            logger.error("Error initializing agent: %s", e, exc_info=True)
+            raise
+
+    def __call__(self, question: str, task_id: str) -> str:
+        """Execute the agent with the given question and optional file.
+        Args:
+            question (str): The question to answer
+            task_id (str): The task ID to fetch the file
+        """
+        max_retries = 3
+        attempt = 0
+
+        # Create a temporary directory that will be automatically cleaned up
+        with tempfile.TemporaryDirectory() as temp_dir:
+            while attempt < max_retries:
+                default_api_url = os.getenv("DEFAULT_API_URL")
+                file_url = f"{default_api_url}/files/{task_id}"
+
+                try:
+                    # Download file to temporary directory
+                    file = download_file_from_url.invoke(
+                        {
+                            "url": file_url,
+                            "directory": temp_dir,
+                        }
+                    )
+                except Exception as e:
+                    logger.error(f"Error downloading file: {e}")
+                    file = None
+
+                try:
+                    attempt += 1
+                    logger.info(f"Attempt {attempt} of {max_retries}")
+
+                    # Prepare input with file information
+                    if file and file.get("type") != "error":
+                        input_data = {
+                            "input": question
+                            + f" [File: type={file.get('type', 'None')}, path={file.get('path', 'None')}]",
+                        }
+                    else:
+                        input_data = {
+                            "input": question,
+                        }
+
+                    # Run the agent to get the answer
+                    result = self.agent_executor.invoke(input_data)
+                    answer = result.get("output", "")
+
+                    logger.info(f"Attempt {attempt} result: {result}")
+
+                    # Run validation
+                    validation_result = validate_answer(
+                        self.validation_graph,
+                        answer,
+                        [result.get("intermediate_steps", [])],
+                    )
+
+                    valid_answer = validation_result.get("valid_answer", False)
+                    final_answer = validation_result.get("final_answer", "")
+
+                    if valid_answer:
+                        logger.info(f"Valid answer found on attempt {attempt}")
+                        return final_answer
+
+                    logger.warning(
+                        f"Validation failed on attempt {attempt}: {final_answer}"
+                    )
+                    if attempt >= max_retries:
+                        raise Exception(
+                            f"Failed to get valid answer after {max_retries} attempts. Last error: {final_answer}"
+                        )
+
+                except Exception as e:
+                    logger.error(
+                        f"Error in attempt {attempt}: {e}", exc_info=True
+                    )
+                    if attempt >= max_retries:
+                        raise Exception(
+                            f"Failed after {max_retries} attempts. Last error: {str(e)}"
+                        )
+                    continue

app.py

@@ -1,24 +1,30 @@
+import concurrent.futures
+import logging
 import os
+import sys
+import traceback
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
-from agent import BasicAgent
+import requests
+from dotenv import load_dotenv
+
+from agent_gemini import BasicAgent
+
+# Load environment variables from .env file
+load_dotenv()
+
+
+# Configure logging
+logging.basicConfig(
+    level=logging.DEBUG,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    handlers=[logging.StreamHandler(sys.stdout)],
+)
+logger = logging.getLogger(__name__)
 
 # (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 ------
-# 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):
@@ -26,146 +32,249 @@ 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
+    try:
+        # --- Determine HF Space Runtime URL and Repo URL ---
+        space_id = os.getenv(
+            "SPACE_ID"
+        )  # Get the SPACE_ID for sending link to the code
 
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+        if profile:
+            username = f"{profile.username}"
+            logger.info(f"User logged in: {username}")
+        else:
+            logger.warning("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:
-        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)
-    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
-    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
+        api_url = os.getenv("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:
+            logger.info("Instantiating agent...")
+            agent = BasicAgent()
+            logger.info("Agent instantiated successfully")
+        except Exception as e:
+            logger.error(f"Error instantiating agent: {e}", exc_info=True)
+            return (
+                f"Error initializing agent: {str(e)}\n{traceback.format_exc()}",
+                None,
+            )
+
+        # 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"
+        logger.info(f"Agent code: {agent_code}")
+
+        # 2. Fetch Questions
+        logger.info(f"Fetching questions from: {questions_url}")
         try:
-            submitted_answer = agent(question_text)
-            answers_payload.append(
-                {"task_id": task_id, "submitted_answer": submitted_answer}
+            response = requests.get(questions_url, timeout=15)
+            response.raise_for_status()
+            questions_data = response.json()
+            if not questions_data:
+                logger.warning("Fetched questions list is empty.")
+                return (
+                    "Fetched questions list is empty or invalid format.",
+                    None,
+                )
+            logger.info(f"Fetched {len(questions_data)} questions.")
+        except requests.exceptions.RequestException as e:
+            logger.error(f"Error fetching questions: {e}", exc_info=True)
+            return f"Error fetching questions: {str(e)}", None
+        except requests.exceptions.JSONDecodeError as e:
+            logger.error(
+                f"Error decoding JSON response from questions endpoint: {e}",
+                exc_info=True,
             )
-            results_log.append(
-                {
-                    "Task ID": task_id,
-                    "Question": question_text,
-                    "Submitted Answer": submitted_answer,
-                }
+            logger.error(f"Response text: {response.text[:500]}")
+            return (
+                f"Error decoding server response for questions: {str(e)}",
+                None,
             )
         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}",
-                }
+            logger.error(
+                f"An unexpected error occurred fetching questions: {e}",
+                exc_info=True,
+            )
+            return (
+                f"An unexpected error occurred fetching questions: {str(e)}",
+                None,
             )
 
-    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
-        )
+        # 3. Run your Agent
+        results_log = []
+        answers_payload = []
+        logger.info(f"Running agent on {len(questions_data)} questions...")
 
-    # 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()
-        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.')}"
+        # Limit the number of questions to process to avoid timeouts
+        max_questions = 20  # Process only 20 questions at a time
+
+        tasks_to_process = [
+            # "99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3",
+            # "1f975693-876d-457b-a649-393859e79bf3",
+            # "840bfca7-4f7b-481a-8794-c560c340185d",
+            # "7bd855d8-463d-4ed5-93ca-5fe35145f733",
+        ]
+
+        # questions_to_process = questions_data[:max_questions]
+
+        if tasks_to_process:
+            questions_to_process = [
+                x
+                for x in questions_data
+                if x.get("task_id") in tasks_to_process
+            ]
+        else:
+            questions_to_process = questions_data[:max_questions]
+
+        logger.info(
+            f"Processing {len(questions_to_process)} out of {len(questions_data)} questions"
         )
-        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}."
+
+        for item in questions_to_process:
+            task_id = item.get("task_id")
+            question_text = item.get("question")
+            if not task_id or question_text is None:
+                logger.warning(
+                    f"Skipping item with missing task_id or question: {item}"
+                )
+                continue
+            try:
+                logger.info(f"Processing task {task_id}: {question_text}")
+
+                # Use concurrent.futures for thread-safe timeout
+                with concurrent.futures.ThreadPoolExecutor() as executor:
+                    try:
+                        future = executor.submit(agent, question_text, task_id)
+                        try:
+                            submitted_answer = future.result(
+                                timeout=180
+                            )  # 60 second timeout
+                            logger.info(
+                                f"Answer for task {task_id}: {submitted_answer}"
+                            )
+
+                            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 concurrent.futures.TimeoutError:
+                            logger.error(f"Timeout processing task {task_id}")
+                            results_log.append(
+                                {
+                                    "Task ID": task_id,
+                                    "Question": question_text,
+                                    "Submitted Answer": "TIMEOUT ERROR: Question processing timed out after 60 seconds",
+                                }
+                            )
+                    finally:
+                        # Clean up temporary directory after processing
+                        try:
+                            import shutil
+
+                            # shutil.rmtree(temp_dir) ## TBD
+                            logger.info(
+                                f"Cleaned up temporary directory for task {task_id}"
+                            )
+                        except Exception as e:
+                            logger.error(
+                                f"Error cleaning up temporary directory for task {task_id}: {e}"
+                            )
+            except Exception as e:
+                logger.error(
+                    f"Error running agent on task {task_id}: {e}",
+                    exc_info=True,
+                )
+                results_log.append(
+                    {
+                        "Task ID": task_id,
+                        "Question": question_text,
+                        "Submitted Answer": f"AGENT ERROR: {str(e)}",
+                    }
+                )
+
+        if not answers_payload:
+            logger.warning("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}'..."
+        logger.info(status_update)
+
+        # 5. Submit
+        logger.info(
+            f"Submitting {len(answers_payload)} answers to: {submit_url}"
         )
         try:
-            error_json = e.response.json()
-            error_detail += (
-                f" Detail: {error_json.get('detail', e.response.text)}"
+            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.')}"
+            )
+            logger.info("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}."
             )
-        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
+            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}"
+            logger.error(status_message, exc_info=True)
+            results_df = pd.DataFrame(results_log)
+            return status_message, results_df
+        except requests.exceptions.Timeout:
+            status_message = "Submission Failed: The request timed out."
+            logger.error(status_message, exc_info=True)
+            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}"
+            logger.error(status_message, exc_info=True)
+            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}"
+            )
+            logger.error(status_message, exc_info=True)
+            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
+        logger.error(
+            f"Unhandled exception in run_and_submit_all: {e}", exc_info=True
+        )
+        return f"Critical error: {str(e)}\n{traceback.format_exc()}", None
 
 
 # --- Build Gradio Interface using Blocks ---
@@ -174,11 +283,9 @@ 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).