added new code logic

app.py

@@ -3,7 +3,12 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
-from smolagents import CodeAgent, OpenAIServerModel, DuckDuckGoSearchTool, WikipediaSearchTool, HfApiModel
+from smolagents import CodeAgent, OpenAIServerModel, DuckDuckGoSearchTool, WikipediaSearchTool, HfApiModel, GoogleSearchTool
+from dotenv import find_dotenv, load_dotenv
+from  tools import WikipediaSearch, ExcelReader, download_files, get_images, FileReader, AudioTransciber, YouTubeTranscipt, YouTubeVideoUnderstanding
+from pathlib import Path
+from PIL import Image
+
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
@@ -12,18 +17,21 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        # model = OpenAIServerModel(model_id="gpt-4o",
-        #                          api_key=os.getenv("OPENAI_API_KEY"))
-        model=HfApiModel(api_key=os.getenv('HUGGING_FACE_API_KEY'))
-        # Initialize the DuckDuckGo search tool
-        search_tool = DuckDuckGoSearchTool()
-        wiki_search = WikipediaSearchTool()
-        
+        load_dotenv(find_dotenv())
+        os.environ["SERPER_API_KEY"] = os.getenv('SERPER_API_KEY')
+        model = OpenAIServerModel(model_id="gpt-4o",
+                                 api_key=os.getenv("OPEN_AI_KEY"))
+        #model=HfApiModel(api_key=os.getenv('HUGGING_FACE_API_KEY'))
         # Instantiate the agent
         self.agent = CodeAgent(
-                    tools=[search_tool, wiki_search],
+                    tools=[
+                           GoogleSearchTool(provider="serper"), 
+                           #DuckDuckGoSearchTool(),
+                           WikipediaSearch(), ExcelReader(),  FileReader(), AudioTransciber(), YouTubeTranscipt(),
+                           YouTubeVideoUnderstanding()],
                     model=model,
-                    add_base_tools=True
+                    add_base_tools=True,
+                    additional_authorized_imports=['pandas','numpy', 'io']
         )
         SYSTEM_PROMPT = """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].
@@ -32,9 +40,10 @@ class BasicAgent:
         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.
+        digits in plain text unless specified otherwise. Never include currency symbols in the response.
         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.
+        to be put in the list is a number or a string. For question that contain phrases like `what is the number` or 
+        `what is the highest number` return just the number, e.g., 2.
         """
         self.agent.prompt_templates["system_prompt"] = self.agent.prompt_templates["system_prompt"] + SYSTEM_PROMPT
     def __call__(self, question: str) -> str:
@@ -43,12 +52,12 @@ class BasicAgent:
         print(f"Agent returning answer: {final_answer}")
         return final_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 ---
+    #--- 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:
@@ -57,22 +66,10 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     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)
-    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)
@@ -92,42 +89,62 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", 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
 
     # 3. Run your Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    # added limit for testing
+    #questions_data = [i for i in questions_data if i['task_id'] == 'f918266a-b3e0-4914-865d-4faa564f1aef']
+    images = []
+    #added limit for testing
     for item in questions_data:
         task_id = item.get("task_id")
-        question_text = item.get("question")
+        question_text = item.get("question") + 'You can use wikipedia.'
+        file_name = item.get('file_name')
+        if file_name:
+            file_path = download_files(task_id, file_name)
+            file_format = file_name.split('.')[-1]
+            question_text = question_text + f"This question has an associated file at path: {file_path}. The file is in the {file_format} format"
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
+            print(images)
             submitted_answer = agent(question_text)
+            print(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 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)
+        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
+    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 = (
             f"Submission Successful!\n"
             f"User: {result_data.get('username')}\n"
             f"Overall Score: {result_data.get('score', 'N/A')}% "
@@ -218,4 +235,7 @@ if __name__ == "__main__":
     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)
+
+if __name__ == "__main__":
+    run_and_submit_all()

requirements.txt

@@ -2,4 +2,7 @@ gradio
 requests
 smolagents
 smolagents[openai]
-wikipedia-api
+openpyxl
+Wikipedia-API
+llama-index-readers-youtube_transcript
+google-genai

tools.py

@@ -0,0 +1,156 @@
+from smolagents import Tool
+import wikipedia
+from bs4 import BeautifulSoup
+import io 
+import pandas as pd
+import requests 
+from tabulate import tabulate
+import os
+import tempfile
+from pathlib import Path
+from PIL import Image
+from io import BytesIO
+from dotenv import find_dotenv, load_dotenv
+from openai import OpenAI
+from llama_index.readers.youtube_transcript import YoutubeTranscriptReader
+from google import genai
+from google.genai import types
+
+class WikipediaSearch(Tool):
+    name = "wikipedia_search"
+    description = "Fetches wikipedia pages."
+    inputs = {
+        "query": {
+            "type": "string",
+            "description": "Query to be searched on wikipedia"
+        }
+        }
+    output_type = "string"
+
+    def forward(self, query:str)->str:
+        res = wikipedia.page(query)
+        bs = BeautifulSoup(res.html(), 'html.parser')
+        text_only = bs.get_text()
+        return text_only
+
+class ExcelReader(Tool):
+    name = 'excel_processor'
+    description = "excel reading tool, processed files of .xlsx and .xls format."
+    inputs = {
+
+        "file_path": {
+            "type": "string",
+            "description": "path to the excel file"
+        }
+        }
+    output_type = "string"
+    
+    def forward(self, file_path:str)->str:
+        df = pd.read_excel(file_path)
+        txt_excel = tabulate(df, headers="keys", tablefmt="github", showindex=False)
+        return txt_excel
+    
+class FileReader(Tool):
+    name = 'file_reader'
+    description = "reads saved files"
+    inputs = {
+
+        "file_path": {
+            "type": "string",
+            "description": "path to the file"
+        }
+        }
+    output_type = "string"
+    
+    def forward(self, file_path:str)->str:
+        with open(file_path, "r") as file:
+            content = file.read()
+        return content
+    
+def download_files(task_id, file_name):
+    url = f'https://agents-course-unit4-scoring.hf.space/files/{task_id}'
+    response = requests.get(url, timeout=15)
+    tmp_dir = Path(tempfile.gettempdir()) / "project_files"
+    tmp_dir.mkdir(exist_ok=True)
+    filepath = os.path.join(tmp_dir, file_name)
+    with open(filepath, "wb") as f:
+        f.write(response.content)
+
+    return filepath
+
+def get_images(file_format, file_path):
+    if file_format in ['png', 'jpeg', 'jpg']:
+        images  = [Image.open(file_path).convert("RGB")]
+    else:
+        images = []
+
+    return images
+
+class AudioTransciber(Tool):
+    name = 'audio_transcriber'
+    description = "transcribes audio files"
+    inputs = {
+
+        "file_path": {
+            "type": "string",
+            "description": "path to the file"
+        }
+        }
+    output_type = "string"
+    
+    def forward(self, file_path:str)->str:
+        audio = open(file_path, 'rb')
+        client = OpenAI(api_key=os.getenv("OPEN_AI_KEY"))
+        transcript = client.audio.transcriptions.create(model='whisper-1',
+                                         file=audio)
+        return transcript
+    
+class YouTubeTranscipt(Tool):
+    name = 'youtube_transcript'
+    description = "a tool that returns a transcript for a youtube video. Youtube videos come from urls containing www.youtube.com"
+    inputs = {
+
+        "url": {
+            "type": "string",
+            "description": "url to the youtube video, has 'www.youtube.com' in it."
+        }
+        }
+    output_type = "string"
+    
+    def forward(self, url:str)->str:
+        loader = YoutubeTranscriptReader()
+        documents = loader.load_data(ytlinks=[url])
+        transcript = documents[0].text
+        return transcript
+    
+class YouTubeVideoUnderstanding(Tool):
+    name = 'youtube_video_understanding'
+    description = "a tool that processes summarizes what is happenening in a youtube video. Youtube videos come from urls containing www.youtube.com"
+    inputs = {
+        "url": {
+            "type": "string",
+            "description": "url to the youtube video, has 'www.youtube.com' in it."
+        },
+        "prompt": {
+            "type": "string",
+            "description": "user prompt about the video content"
+
+        }
+        }
+    output_type = "string"
+  
+    def forward(self, url:str, prompt:str)->str:
+        load_dotenv(find_dotenv())
+        client = genai.Client(api_key=os.getenv("GEMINI_API_KEY"))
+        response = client.models.generate_content(
+         model='models/gemini-2.5-flash-preview-04-17',
+            contents=types.Content(
+                parts=[
+                    types.Part(
+                        file_data=types.FileData(file_uri=url)
+                    ),
+                    types.Part(text=prompt)
+                ]
+            )
+        )
+        return response.text