Initialize agent

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.env

Final-Assignment-Agent

@@ -1 +0,0 @@
-Subproject commit 5deb91c62a592a3ff255b16df61e76c19ec623df

README.md

@@ -1,30 +1,15 @@
-# Final Assignment Agent
-
-This is a question-answering agent that uses various tools including Wikipedia search, web search, and Arxiv search to provide precise answers to questions.
-
-## Features
-- Precise question answering using multiple knowledge sources
-- Support for different types of questions (numbers, text, lists, dates, etc.)
-- File processing capabilities
-- Web search integration
-- Wikipedia and Arxiv search capabilities
-
-## Setup
-1. The agent uses the Groq API with the Llama 4 model
-2. Environment variables required:
-   - GROQ_API_KEY: Your Groq API key
-
-## Usage
-1. Enter your question in the text box
-2. Optionally upload a file if your question requires file processing
-3. Click "Submit" to get your answer
-
-## Dependencies
-All required dependencies are listed in `requirements.txt`
-
-## Model
-- Uses Groq's Llama 4 model for high-quality responses
-- Temperature set to 0.1 for precise answers
-
-## License
-This project is part of the Final Assignment submission. 
+---
+title: Template Final Assignment
+emoji: 🕵🏻‍♂️
+colorFrom: indigo
+colorTo: indigo
+sdk: gradio
+sdk_version: 5.25.2
+app_file: app.py
+pinned: false
+hf_oauth: true
+# optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes.
+hf_oauth_expiration_minutes: 480
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

RobotPai

@@ -1 +0,0 @@
-Subproject commit 999f7f9795f53c7241d3a340d3632cf06bc1e46a

agent.py

@@ -0,0 +1,206 @@
+import os
+from typing import Dict, List, Optional
+from dotenv import load_dotenv
+from langchain_groq import ChatGroq
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+import json
+import requests
+from bs4 import BeautifulSoup
+import urllib.parse
+import pandas as pd
+import re
+
+load_dotenv()
+
+class BasicAgent:
+    def __init__(self):
+        self.llm = ChatGroq(
+            model="meta-llama/llama-4-maverick-17b-128e-instruct", 
+            temperature=0.1
+        )
+        
+        self.system_prompt = """You are a highly accurate question-answering assistant. Your task is to provide precise, direct answers to questions.
+
+Key Rules:
+1. Answer Format:
+   - For numbers: Provide only the number without units, commas, or formatting
+   - For text: Use minimal words, no articles or abbreviations
+   - For lists: Use comma-separated values without additional formatting
+   - For dates: Use YYYY-MM-DD format unless specified otherwise
+   - For names: Use full names without titles or honorifics
+   - For country codes: Use official IOC codes (3 letters)
+   - For chess moves: Use standard algebraic notation
+   - For currency: Use numbers only, no symbols
+
+2. Answer Guidelines:
+   - Be extremely precise and direct
+   - Do not include any explanatory text
+   - Do not use phrases like "FINAL ANSWER" or any markers
+   - Do not include units unless explicitly requested
+   - Do not use abbreviations unless they are standard (e.g., DNA, RNA)
+   - For multiple choice: Provide only the letter or number of the correct answer
+   - For reversed text: Provide the answer in normal text
+   - For file-based questions: Focus on the specific information requested
+
+3. Error Handling:
+   - If uncertain, provide the most likely answer based on available information
+   - If completely unsure, provide a reasonable default rather than an error message
+   - For file processing errors, indicate the specific issue
+
+4. Special Cases:
+   - For mathematical questions: Provide the exact numerical result
+   - For historical dates: Use the most widely accepted date
+   - For scientific terms: Use the standard scientific notation
+   - For geographical locations: Use official names without abbreviations
+   - For audio/video questions: Focus on the specific detail requested"""
+        
+        # Initialize tools
+        self.tools = [
+            self.wiki_search,
+            self.web_search,
+            self.arxiv_search
+        ]
+        
+    def wiki_search(self, query: str) -> str:
+        """Search Wikipedia for information."""
+        try:
+            search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+            return "\n".join([doc.page_content for doc in search_docs])
+        except Exception as e:
+            return f"Error searching Wikipedia: {str(e)}"
+    
+    def web_search(self, query: str) -> str:
+        """Search the web using DuckDuckGo."""
+        try:
+            encoded_query = urllib.parse.quote(query)
+            url = f"https://html.duckduckgo.com/html/?q={encoded_query}"
+            
+            headers = {
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
+            }
+            
+            response = requests.get(url, headers=headers)
+            response.raise_for_status()
+            
+            soup = BeautifulSoup(response.text, 'html.parser')
+            
+            results = []
+            for result in soup.find_all('div', class_='result__body'):
+                title = result.find('h2', class_='result__title')
+                snippet = result.find('a', class_='result__snippet')
+                
+                if title and snippet:
+                    results.append(f"Title: {title.get_text()}\nSnippet: {snippet.get_text()}")
+                
+                if len(results) >= 3:
+                    break
+            
+            return "\n\n".join(results) if results else "No results found"
+            
+        except Exception as e:
+            return f"Error searching web: {str(e)}"
+    
+    def arxiv_search(self, query: str) -> str:
+        """Search Arxiv for scientific papers."""
+        try:
+            search_docs = ArxivLoader(query=query, load_max_docs=2).load()
+            return "\n".join([doc.page_content[:1000] for doc in search_docs])
+        except Exception as e:
+            return f"Error searching Arxiv: {str(e)}"
+    
+    def process_file(self, file_name: str, question: str) -> str:
+        """Process different types of files based on extension."""
+        try:
+            if not file_name:
+                return "No file provided"
+                
+            file_ext = file_name.split('.')[-1].lower()
+            
+            if file_ext == 'xlsx':
+                df = pd.read_excel(file_name)
+                return f"Excel file loaded with {len(df)} rows"
+                
+            elif file_ext == 'mp3':
+                return "Audio file detected - requires speech processing"
+                
+            elif file_ext == 'png':
+                return "Image file detected - requires image processing"
+                
+            elif file_ext == 'py':
+                with open(file_name, 'r') as f:
+                    code = f.read()
+                return f"Python code loaded: {len(code)} characters"
+                
+            else:
+                return f"Unsupported file type: {file_ext}"
+                
+        except Exception as e:
+            return f"Error processing file: {str(e)}"
+    
+    def __call__(self, question: str, file_name: str = None) -> str:
+        try:
+            if question.startswith('.'):
+                question = question[::-1]
+            
+            file_info = ""
+            if file_name:
+                file_info = self.process_file(file_name, question)
+            
+            analysis_prompt = f"""Analyze this question and determine its type and required format:
+            Question: {question}
+            File Info: {file_info}
+            Provide a JSON response with:
+            1. question_type: (number/text/list/date/name/multiple_choice/file_processing)
+            2. required_format: (specific format requirements)
+            3. key_terms: (important terms to search for)
+            4. file_processing_needed: (true/false)"""
+            
+            analysis_messages = [
+                SystemMessage(content="You are a question analyzer. Provide a JSON response."),
+                HumanMessage(content=analysis_prompt)
+            ]
+            
+            analysis = self.llm.invoke(analysis_messages)
+            try:
+                analysis_data = json.loads(analysis.content)
+            except:
+                analysis_data = {
+                    "question_type": "text",
+                    "required_format": "direct",
+                    "key_terms": question,
+                    "file_processing_needed": bool(file_name)
+                }
+            
+            messages = [
+                SystemMessage(content=self.system_prompt),
+                HumanMessage(content=f"""Question Type: {analysis_data['question_type']}
+                Required Format: {analysis_data['required_format']}
+                Key Terms: {analysis_data['key_terms']}
+                File Processing: {analysis_data.get('file_processing_needed', False)}
+                
+                Question: {question}""")
+            ]
+            
+            response = self.llm.invoke(messages)
+            
+            answer = response.content.strip()
+            
+            if answer.lower().startswith("final answer:"):
+                answer = answer[len("final answer:"):].strip()
+            
+            if analysis_data['question_type'] == 'number':
+                answer = ''.join(c for c in answer if c.isdigit() or c in '.-')
+            elif analysis_data['question_type'] == 'list':
+                answer = ','.join(item.strip() for item in answer.split(','))
+            elif analysis_data['question_type'] == 'country_code':
+                answer = answer[:3].upper()
+            elif analysis_data['question_type'] == 'chess_move':
+                answer = re.sub(r'[^a-h1-8x+=#]', '', answer)
+            
+            return answer
+            
+        except Exception as e:
+            print(f"Error in agent response: {e}")
+            return f"Error processing question: {str(e)}" 

app.py

@@ -0,0 +1,253 @@
+import os
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+from agent import BasicAgent
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+# (Keep Constants as is)
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+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
+
+    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)
+        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
+        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})
+        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}"})
+
+    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
+    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.')}"
+        )
+        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}."
+        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}"
+        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
+    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
+
+
+# --- Build Gradio Interface using Blocks ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    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).
+        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        """
+    )
+
+    gr.LoginButton()
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    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]
+    )
+
+# Initialize the agent
+agent = BasicAgent()
+
+def process_question(question, file=None):
+    """
+    Process a question using the agent and return the answer.
+    
+    Args:
+        question (str): The question to be answered
+        file (str, optional): Path to a file if the question requires file processing
+        
+    Returns:
+        str: The agent's answer to the question
+    """
+    try:
+        # Basic input validation
+        if not question or not question.strip():
+            return "Please enter a question."
+            
+        # Process the question using the agent
+        answer = agent(question, file)
+        
+        # Format the response
+        if isinstance(answer, dict):
+            # If the answer is a dictionary (e.g., from file processing)
+            return f"Answer: {answer.get('answer', 'No answer found')}"
+        else:
+            # If the answer is a direct string
+            return f"Answer: {answer}"
+            
+    except Exception as e:
+        return f"Error processing your question: {str(e)}"
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=process_question,
+    inputs=[
+        gr.Textbox(
+            label="Question",
+            placeholder="Enter your question here...",
+            lines=3
+        ),
+        gr.File(
+            label="Optional File Upload",
+            file_types=["txt", "csv", "json"],
+            optional=True
+        )
+    ],
+    outputs=gr.Textbox(
+        label="Answer",
+        lines=5
+    ),
+    title="Question Answering Agent",
+    description="Ask any question and get a precise answer. You can also upload a file for file-based questions.",
+    examples=[
+        ["What is the capital of France?", None],
+        ["What is 2 + 2?", None],
+        ["List the first three planets in our solar system", None]
+    ],
+    theme=gr.themes.Soft()
+)
+
+# Launch the interface
+if __name__ == "__main__":
+    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
+
+    if space_host_startup:
+        print(f"✅ SPACE_HOST found: {space_host_startup}")
+        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+    else:
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+
+    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")
+    else:
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
+
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)

requirements.txt

@@ -0,0 +1,13 @@
+gradio>=5.25.2
+requests>=2.31.0
+langchain>=0.1.0
+langchain-google-genai>=0.0.5
+langchain-groq>=0.0.1
+langchain-huggingface>=0.0.5
+langchain-community>=0.0.13
+python-dotenv>=1.0.0
+pandas>=2.0.0
+arxiv>=2.0.0
+wikipedia>=1.4.0
+beautifulsoup4>=4.12.0
+openpyxl>=3.1.0