Release v1

agent.py

@@ -0,0 +1,68 @@
+from typing import Any, Optional
+
+from smolagents import CodeAgent
+
+from utils.logger import get_logger
+
+logger = get_logger(__name__)
+
+
+class Agent:
+    def __init__(
+        self, model: Any, tools: Optional[list] = None, prompt: Optional[str] = None
+    ):
+        logger.info("Initializing Agent")
+
+        self.model = model
+
+        self.tools = tools
+
+        self.imports = [
+            "pandas",
+            "numpy",
+            "os",
+            "requests",
+            "tempfile",
+            "datetime",
+            "json",
+            "time",
+            "re",
+            "openpyxl",
+        ]
+
+        self.agent = CodeAgent(
+            model=self.model,
+            tools=self.tools,
+            add_base_tools=True,
+            additional_authorized_imports=self.imports,
+        )
+
+        self.prompt = prompt or (
+            """
+            You are an advanced AI assistant specialized in solving complex, real-world tasks that require multi-step reasoning, factual accuracy, and use of external tools.
+        
+            Follow these principles:
+            - Be precise and concise. The final answer must strictly match the required format with no extra commentary.
+            - Use tools intelligently. If a question involves external information, structured data, images, or audio, call the appropriate tool to retrieve or process it.
+            - Reason step-by-step. Think through the solution logically and plan your actions carefully before answering.
+            - Validate information. Always verify facts when possible instead of guessing.
+            - Use code if needed. For calculations, parsing, or transformations, generate Python code and execute it.
+
+            IMPORTANT: When giving the final answer, output only the direct required result without any extra text like "Final Answer:" or explanations. YOU MUST RESPOND IN THE EXACT FORMAT AS THE QUESTION.
+
+            QUESTION: {question}
+
+            CONTEXT: {context}
+
+            ANSWER:
+            """
+        )
+
+        logger.info("Agent initialized")
+
+    def __call__(self, question: str, file_path: Optional[str] = None) -> str:
+        answer = self.agent.run(
+            self.prompt.format(question=question, context=file_path)
+        )
+        answer = str(answer).strip("'").strip('"').strip()
+        return answer

app.py

@@ -1,34 +1,43 @@
+import inspect
 import os
+import tempfile
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+import requests
+
+from agent import Agent
+from model import get_model
+from tools import get_tools
 
 # (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):
+
+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
+    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.")
@@ -37,10 +46,13 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
+    files_url = f"{api_url}/files"
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = Agent(
+            model=get_model("OpenAIServerModel", "gpt-4.1-mini"), tools=get_tools()
+        )
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -55,16 +67,16 @@ 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
@@ -80,19 +92,51 @@ def run_and_submit_all( profile: gr.OAuthProfile | 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})
+            file_path = None
+            try:
+                file_response = requests.get(f"{files_url}/{task_id}", timeout=15)
+                if file_response.status_code == 200 and file_response.content:
+                    with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
+                        tmp_file.write(file_response.content)
+                        file_path = tmp_file.name
+                        print(f"Downloaded file for task {task_id} to {file_path}")
+                else:
+                    print(f"No file for task {task_id} or file is empty.")
+            except Exception as e:
+                print(f"Error downloading file for task {task_id}: {e}")
+                file_path = None
+
+            submitted_answer = agent(question_text, file_path)
+            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}
+    # 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)
 
@@ -162,20 +206,19 @@ 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)
+    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)
+    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}")
@@ -183,14 +226,18 @@ 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")
+        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(
+            "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 Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)

model.py

@@ -0,0 +1,53 @@
+import os
+from typing import Any
+
+from smolagents import HfApiModel, InferenceClientModel, LiteLLMModel, OpenAIServerModel
+
+
+def get_huggingface_api_model(model_id: str, **kwargs) -> Any:
+    api_key = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+    if not api_key:
+        raise ValueError("HUGGINGFACEHUB_API_TOKEN is not set")
+
+    return HfApiModel(model_id=model_id, token=api_key, **kwargs)
+
+
+def get_inference_client_model(model_id: str, **kwargs) -> Any:
+    api_key = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+    if not api_key:
+        raise ValueError("HUGGINGFACEHUB_API_TOKEN is not set")
+
+    return InferenceClientModel(model_id=model_id, token=api_key, **kwargs)
+
+
+def get_openai_server_model(model_id: str, **kwargs) -> Any:
+    api_key = os.getenv("OPENAI_API_KEY")
+    if not api_key:
+        raise ValueError("OPENAI_API_KEY is not set")
+
+    api_base = os.getenv("OPENAI_API_BASE")
+    if not api_base:
+        raise ValueError("OPENAI_API_BASE is not set")
+
+    return OpenAIServerModel(
+        model_id=model_id, api_key=api_key, api_base=api_base, **kwargs
+    )
+
+
+def get_lite_llm_model(model_id: str, **kwargs) -> Any:
+    return LiteLLMModel(model_id=model_id, **kwargs)
+
+
+def get_model(model_type: str, model_id: str, **kwargs) -> Any:
+
+    models = {
+        "HfApiModel": get_huggingface_api_model,
+        "InferenceClientModel": get_inference_client_model,
+        "OpenAIServerModel": get_openai_server_model,
+        "LiteLLMModel": get_lite_llm_model,
+    }
+
+    if model_type not in models:
+        raise ValueError(f"Unknown model type: {model_type}")
+
+    return models[model_type](model_id, **kwargs)

requirements.txt

@@ -1,2 +1,12 @@
 gradio
-requests
+numpy
+openpyxl
+pandas
+requests
+smolagents
+smolagents[audio]
+smolagents[openai]
+smolagents[transformers]
+transformers
+wikipedia-api
+youtube-transcript-api

tools.py

@@ -0,0 +1,35 @@
+from smolagents import (
+    DuckDuckGoSearchTool,
+    PythonInterpreterTool,
+    SpeechToTextTool,
+    Tool,
+    VisitWebpageTool,
+    WikipediaSearchTool,
+)
+from youtube_transcript_api import YouTubeTranscriptApi
+
+
+class YouTubeTranscriptionTool(Tool):
+    name = "youtube_transcription"
+    description = "Fetches the transcript of a YouTube video given its URL"
+    inputs = {
+        "video_url": {"type": "string", "description": "YouTube video URL"},
+    }
+    output_type = "string"
+
+    def forward(self, video_url: str) -> str:
+        video_id = video_url.strip().split("v=")[-1]
+        transcript = YouTubeTranscriptApi.get_transcript(video_id)
+        return " ".join([entry["text"] for entry in transcript])
+
+
+def get_tools():
+    tools = [
+        DuckDuckGoSearchTool(),
+        PythonInterpreterTool(),
+        WikipediaSearchTool(),
+        VisitWebpageTool(),
+        SpeechToTextTool(),
+        YouTubeTranscriptionTool(),
+    ]
+    return tools

utils/logger.py

@@ -0,0 +1,20 @@
+import logging
+
+
+def get_logger(name: str = __name__) -> logging.Logger:
+    """
+    Create and configure a logger.
+
+    Args:
+        name (str, optional): Name of the logger. Defaults to the module name.
+
+    Returns:
+        logging.Logger: Configured logger instance.
+    """
+    logging.basicConfig(
+        format="%(asctime)s:%(module)s:%(funcName)s:%(levelname)s: %(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S",
+    )
+    logger = logging.getLogger(name)
+    logger.setLevel(logging.INFO)
+    return logger