feat(agent): add agent to answer question

agent.py

@@ -0,0 +1,30 @@
+from langgraph.prebuilt import create_react_agent
+from langchain_openai import ChatOpenAI
+from langchain_core.messages import HumanMessage
+import os
+import dotenv
+from tools import get_tools
+import json
+import pandas as pd
+from tqdm import tqdm
+
+dotenv.load_dotenv()
+
+def post_process_answer(answer: str):
+    if "FINAL ANSWER:" not in answer:
+        raise ValueError("The answer does not contain 'FINAL ANSWER:' keyword")
+    key_answer_start_idx = answer.find("FINAL ANSWER:") + len("FINAL ANSWER:")
+    key_answer = answer[key_answer_start_idx:].strip()
+    return key_answer
+    
+llm = ChatOpenAI(
+    api_key=os.getenv("API_KEY"),
+    model=os.getenv("MODEL")
+)
+
+tools = get_tools()
+
+with open("system_prompt.txt") as f:
+    system_prompt = f.read()
+
+agent = create_react_agent(model=llm, tools=tools, prompt=system_prompt)

app.py

@@ -3,6 +3,11 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from agent import agent
+from langchain_core.messages import HumanMessage
+from dotenv import load_dotenv
+
+load_dotenv()
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -13,11 +18,26 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
+
+    def post_process_answer(answer: str):
+        if "FINAL ANSWER:" not in answer:
+            raise ValueError("The answer does not contain 'FINAL ANSWER:' keyword")
+        key_answer_start_idx = answer.find("FINAL ANSWER:") + len("FINAL ANSWER:")
+        key_answer = answer[key_answer_start_idx:].strip()
+        return key_answer
+    
     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
+        try:
+            result = agent.invoke({"messages": [HumanMessage(content=question)]})
+            answer = result["messages"][-1].content
+            key_answer = self.post_process_answer(answer)
+            print("Question:", question)
+            print("Answer:", key_answer)
+        except Exception as e:
+            print(e)
+            key_answer = str(e)
+        return key_answer
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """

requirements.txt

@@ -1,2 +1,3 @@
 gradio
-requests
+requests
+gradio[oauth]

system_prompt.txt

@@ -0,0 +1,5 @@
+You are a helpful assistant tasked with answering questions using a set of tools. 
+Now, 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.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer.

tools.py

@@ -0,0 +1,215 @@
+import requests
+from langchain.tools import tool
+from duckduckgo_search import DDGS
+from bs4 import BeautifulSoup
+import tempfile
+from typing import Optional
+import os
+from urllib.parse import urlparse
+
+
+@tool("search", return_direct=False)
+def search(query: str) -> str:
+    """Searches the internet using DuckDuckGo
+
+    Args:
+        query (str): Search query
+
+    Returns:
+        str: Search results
+    """
+    with DDGS() as ddgs:
+        results = [r for r in ddgs.text(query, max_results=5)]
+    return results if results else "No results found."
+
+
+@tool("process_content", return_direct=False)
+def process_content(url: str) -> str:
+    """Process content from a webpage
+
+    Args:
+        url (str): URL to get content
+
+    Returns:
+        str: Content in the webpage
+    """
+    response = requests.get(url)
+    soup = BeautifulSoup(response.content, "html.parser")
+    return soup.get_text()
+
+
+@tool("save_file")
+def save_file(content: str, filename: Optional[str] = None) -> str:
+    """
+    Save content to a temporary file and return the path.
+    Useful for processing files from the GAIA API.
+
+    Args:
+        content: The content to save to the file
+        filename: Optional filename, will generate a random name if not provided
+
+    Returns:
+        Path to the saved file
+    """
+    temp_dir = tempfile.gettempdir()
+    if filename is None:
+        temp_file = tempfile.NamedTemporaryFile(delete=False)
+        filepath = temp_file.name
+    else:
+        filepath = os.path.join(temp_dir, filename)
+
+    # Write content to the file
+    with open(filepath, "w") as f:
+        f.write(content)
+
+    return f"File saved to {filepath}. You can read this file to process its contents."
+
+
+@tool("download_file_from_url")
+def download_file_from_url(url: str, filename: Optional[str] = None) -> str:
+    """
+    Download a file from a URL and save it to a temporary location.
+
+    Args:
+        url: The URL to download from
+        filename: Optional filename, will generate one based on URL if not provided
+
+    Returns:
+        Path to the downloaded file
+    """
+    try:
+        # Parse URL to get filename if not provided
+        if not filename:
+            path = urlparse(url).path
+            filename = os.path.basename(path)
+            if not filename:
+                # Generate a random name if we couldn't extract one
+                import uuid
+
+                filename = f"downloaded_{uuid.uuid4().hex[:8]}"
+
+        # Create temporary file
+        temp_dir = tempfile.gettempdir()
+        filepath = os.path.join(temp_dir, filename)
+
+        # Download the file
+        response = requests.get(url, stream=True)
+        response.raise_for_status()
+
+        # Save the file
+        with open(filepath, "wb") as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+
+        return f"File downloaded to {filepath}. You can now process this file."
+    except Exception as e:
+        return f"Error downloading file: {str(e)}"
+
+
+@tool("extract_text_from_image")
+def extract_text_from_image(image_path: str) -> str:
+    """
+    Extract text from an image using pytesseract (if available).
+
+    Args:
+        image_path: Path to the image file
+
+    Returns:
+        Extracted text or error message
+    """
+    try:
+        # Try to import pytesseract
+        import pytesseract
+        from PIL import Image
+
+        # Open the image
+        image = Image.open(image_path)
+
+        # Extract text
+        text = pytesseract.image_to_string(image)
+
+        return f"Extracted text from image:\n\n{text}"
+    except ImportError:
+        return "Error: pytesseract is not installed. Please install it with 'pip install pytesseract' and ensure Tesseract OCR is installed on your system."
+    except Exception as e:
+        return f"Error extracting text from image: {str(e)}"
+
+
+@tool("analyze_csv_file")
+def analyze_csv_file(file_path: str, query: str) -> str:
+    """
+    Analyze a CSV file using pandas and answer a question about it.
+
+    Args:
+        file_path: Path to the CSV file
+        query: Question about the data
+
+    Returns:
+        Analysis result or error message
+    """
+    try:
+        import pandas as pd
+
+        # Read the CSV file
+        df = pd.read_csv(file_path)
+
+        # Run various analyses based on the query
+        result = f"CSV 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 ImportError:
+        return "Error: pandas is not installed. Please install it with 'pip install pandas'."
+    except Exception as e:
+        return f"Error analyzing CSV file: {str(e)}"
+
+
+@tool("analyze_excel_file")
+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: Path to the Excel file
+        query: Question about the data
+
+    Returns:
+        Analysis result or error message
+    """
+    try:
+        import pandas as pd
+
+        # 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 ImportError:
+        return "Error: pandas and openpyxl are not installed. Please install them with 'pip install pandas openpyxl'."
+    except Exception as e:
+        return f"Error analyzing Excel file: {str(e)}"
+
+
+def get_tools():
+    return [
+        search,
+        # process_content,
+        # save_file,
+        # download_file_from_url,
+        # extract_text_from_image,
+        # analyze_csv_file,
+        # analyze_excel_file
+    ]