50% on GAIA benchmark

.gitignore

@@ -0,0 +1,4 @@
+.env
+GAIA_result.txt
+__pycache__/
+venv/

agent.py

@@ -0,0 +1,161 @@
+from smolagents import CodeAgent, LiteLLMModel, DuckDuckGoSearchTool, PythonInterpreterTool, FinalAnswerTool, VisitWebpageTool, tool
+import os
+import wikipediaapi
+from youtubesearchpython import VideosSearch
+from youtube_transcript_api import YouTubeTranscriptApi, NoTranscriptFound, TranscriptsDisabled
+import pandas as pd
+
+wiki_api = wikipediaapi.Wikipedia(
+    language='en',
+    user_agent="MyAgent/1.0 (contact@example.com)"
+)
+
+@tool
+def search_youtube_video(query: str) -> str:
+    """
+    Searches YouTube and returns the title and URL of the top result.
+
+    Args:
+        query (str): The search term to look up on YouTube.
+
+    Returns:
+        str: The title and URL of the top video result.
+
+    """
+    print(f"--- Executing Youtube with query: '{query}' ---")
+    try:
+        search = VideosSearch(query, limit=1)
+        top_result = search.result()['result'][0]
+        video_id = top_result['id']
+        video_title = top_result['title']
+        video_url = f"https://www.youtube.com/watch?v={video_id}"
+        return f"Title: {video_title}\nURL: {video_url}"
+    except IndexError:
+        return "Error: No YouTube videos found for that query."
+    except Exception as e:
+        return f"An unknown error occurred during Youtube: {e}"
+
+@tool
+def get_youtube_transcript(video_url: str) -> str:
+    """
+    Extracts and returns the full transcript of a YouTube video.
+
+    Args:
+        video_url (str): The full URL of the YouTube video.
+
+    Returns:
+        str: The transcript text, or an error message if unavailable.
+    """
+    print(f"--- Executing YouTube Transcript Tool for URL: '{video_url}' ---")
+    try:
+        # Extract video ID from URL
+        if "watch?v=" in video_url:
+            video_id = video_url.split("watch?v=")[1].split("&")[0]
+        elif "youtu.be/" in video_url:
+            video_id = video_url.split("youtu.be/")[1].split("?")[0]
+        else:
+            return "Error: Invalid YouTube URL format."
+            
+        # Fetch the transcript
+        transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
+        
+        # Combine transcript segments into a single block of text
+        full_transcript = " ".join([item['text'] for item in transcript_list])
+        
+        return full_transcript
+    except NoTranscriptFound:
+        return "Error: No transcript could be found for this video."
+    except TranscriptsDisabled:
+        return "Error: Transcripts are disabled for this video."
+    except Exception as e:
+        return f"An unknown error occurred while fetching the transcript: {e}"
+    
+@tool
+def get_wikipedia_summary(query: str) -> str:
+    """
+    Fetches and returns the summary of a Wikipedia article.
+
+    Args:
+        query (str): The title or topic of the Wikipedia article to search.
+
+    Returns:
+        str: The summary text of the article, or an error message if not found.
+    """
+    print(f"--- Executing Wikipedia Tool with query: '{query}' ---")
+    page = wiki_api.page(query)
+    if not page.exists():
+        return f"Error: The Wikipedia page for '{query}' could not be found."
+    return f"Title: {page.title}\n\nSummary:\n{page.summary}"
+
+@tool
+def analyze_excel_file(file_path: str, query: str) -> str:
+    """
+    Analyze an Excel file using pandas and answer a question about it.
+    Args:
+        file_path (str): the path to the Excel file.
+        query (str): Question about the data
+    """
+    try:
+        # Read the Excel file
+        df = pd.read_excel(file_path)
+
+        # Run various analyses based on the query
+        result = (
+            f"Excel file loaded with {len(df)} rows and {len(df.columns)} columns.\n"
+        )
+        result += f"Columns: {', '.join(df.columns)}\n\n"
+
+        # Add summary statistics
+        result += "Summary statistics:\n"
+        result += str(df.describe())
+
+        return result
+
+    except Exception as e:
+        return f"Error analyzing Excel file: {str(e)}"
+
+class BasicAgent:
+    def __init__(self):
+
+
+        model = LiteLLMModel(model_id="gpt-4.1-2025-04-14")
+
+
+        self.agent = CodeAgent(
+            model=model,
+            tools=[DuckDuckGoSearchTool(), 
+                   PythonInterpreterTool(), 
+                   FinalAnswerTool(), 
+                   VisitWebpageTool(),
+                   search_youtube_video,
+                   get_youtube_transcript,
+                   get_wikipedia_summary,
+                   analyze_excel_file],
+            additional_authorized_imports=['numpy','csv','xlrd','openpyxl','pandas','markdownify','requests'],       
+            add_base_tools=False,
+            max_steps=10,
+        )
+
+
+    
+
+    def __call__(self, question: str) -> str:
+
+        custom_prompt = ("""
+                        __CONSTRAINTS__
+                        - DO NOT start with an intro or include an outro.
+                        """)
+    
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        result = self.agent.run(custom_prompt + question)
+
+        print("Raw result:", result)
+
+        if isinstance(result, dict) and "output" in result:
+            final_str = str(result["output"]).strip()
+        elif hasattr(result, "output"):
+            final_str = str(result.output).strip()
+        else:
+            final_str = str(result).strip()
+
+        return final_str

app.py

@@ -3,22 +3,12 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from agent import BasicAgent
 
 # (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):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
@@ -72,6 +62,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 3. Run your Agent
     results_log = []
     answers_payload = []
+    f = open("GAIA_result.txt", "w")
     print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
         task_id = item.get("task_id")
@@ -83,10 +74,19 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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})
+            f.write(f'''
+            ------------------------------------------------------------------------------------------
+            - ID
+            {task_id}
+            - Question
+            {question_text}
+            - 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}"})
-
+    f.close()
     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)

requirements.txt

@@ -1,2 +1,159 @@
-gradio
-requests
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.13
+aiosignal==1.3.2
+aiosqlite==0.21.0
+annotated-types==0.7.0
+anyio==4.9.0
+asttokens==3.0.0
+attrs==25.3.0
+Authlib==1.6.0
+banks==2.1.3
+beautifulsoup4==4.13.4
+certifi==2025.6.15
+cffi==1.17.1
+charset-normalizer==3.4.2
+click==8.2.1
+colorama==0.4.6
+comm==0.2.2
+cryptography==45.0.4
+dataclasses-json==0.6.7
+debugpy==1.8.14
+decorator==5.2.1
+defusedxml==0.7.1
+Deprecated==1.2.18
+dirtyjson==1.0.8
+distro==1.9.0
+duckduckgo_search==8.0.4
+et_xmlfile==2.0.0
+executing==2.2.0
+fastapi==0.115.13
+ffmpy==0.6.0
+filelock==3.18.0
+filetype==1.2.0
+frozenlist==1.7.0
+fsspec==2025.5.1
+gradio==5.34.2
+gradio_client==1.10.3
+greenlet==3.2.3
+griffe==1.7.3
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.1.5
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.33.0
+idna==3.10
+importlib_metadata==8.7.0
+ipykernel==6.29.5
+ipython==9.3.0
+ipython_pygments_lexers==1.1.1
+itsdangerous==2.2.0
+jedi==0.19.2
+Jinja2==3.1.6
+jiter==0.10.0
+joblib==1.5.1
+jsonschema==4.24.0
+jsonschema-specifications==2025.4.1
+jupyter_client==8.6.3
+jupyter_core==5.8.1
+litellm==1.72.9
+llama-cloud==0.1.26
+llama-cloud-services==0.6.34
+llama-index==0.12.44
+llama-index-agent-openai==0.4.11
+llama-index-cli==0.4.3
+llama-index-core==0.12.44
+llama-index-embeddings-openai==0.3.1
+llama-index-indices-managed-llama-cloud==0.7.7
+llama-index-instrumentation==0.2.0
+llama-index-llms-openai==0.4.7
+llama-index-multi-modal-llms-openai==0.5.1
+llama-index-program-openai==0.3.2
+llama-index-question-gen-openai==0.3.1
+llama-index-readers-file==0.4.9
+llama-index-readers-llama-parse==0.4.0
+llama-index-workflows==1.0.1
+llama-parse==0.6.34
+lxml==5.4.0
+markdown-it-py==3.0.0
+markdownify==1.1.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+multidict==6.5.0
+mypy_extensions==1.1.0
+nest-asyncio==1.6.0
+networkx==3.5
+nltk==3.9.1
+numpy==2.3.1
+openai==1.90.0
+openpyxl==3.1.5
+orjson==3.10.18
+packaging==25.0
+pandas==2.2.3
+parso==0.8.4
+pexpect==4.9.0
+pillow==11.2.1
+platformdirs==4.3.8
+primp==0.15.0
+prompt_toolkit==3.0.51
+propcache==0.3.2
+psutil==7.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pycparser==2.22
+pydantic==2.11.7
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.2
+pypdf==5.6.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+pyzmq==27.0.0
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.4
+rich==14.0.0
+rpds-py==0.25.1
+ruff==0.12.0
+safehttpx==0.1.6
+semantic-version==2.10.0
+setuptools==80.9.0
+shellingham==1.5.4
+six==1.17.0
+smolagents==1.18.0
+sniffio==1.3.1
+soupsieve==2.7
+SQLAlchemy==2.0.41
+stack-data==0.6.3
+starlette==0.46.2
+striprtf==0.0.26
+tenacity==9.1.2
+tiktoken==0.9.0
+tokenizers==0.21.1
+tomlkit==0.13.3
+tornado==6.5.1
+tqdm==4.67.1
+traitlets==5.14.3
+typer==0.16.0
+typing-inspect==0.9.0
+typing-inspection==0.4.1
+typing_extensions==4.14.0
+tzdata==2025.2
+urllib3==2.5.0
+uvicorn==0.34.3
+wcwidth==0.2.13
+websockets==15.0.1
+Wikipedia-API==0.8.1
+wrapt==1.17.2
+xlrd==2.0.2
+yarl==1.20.1
+youtube-python==1.0.13
+youtube-search-python==1.6.6
+youtube-transcript-api==1.1.0
+zipp==3.23.0