feat: update app.py, add tools.py, and tons of other files

.env.sample

@@ -0,0 +1,7 @@
+LANGFUSE_SECRET_KEY=
+LANGFUSE_PUBLIC_KEY=
+LANGFUSE_HOST=
+GOOGLE_API_KEY=
+TAVILY_API_KEY=
+GROQ_API_KEY=
+MODEL_PROVIDER= # choose from: groq, google, openai

.gitignore

@@ -0,0 +1,5 @@
+__pycache__
+.venv
+_*
+*.bak
+*.tmp

.python-version

@@ -0,0 +1 @@
+3.10

README.md

@@ -1,5 +1,5 @@
 ---
-title: Template Final Assignment
+title: Agent Course - Final assignment
 emoji: 🕵🏻‍♂️
 colorFrom: indigo
 colorTo: indigo
@@ -8,8 +8,9 @@ sdk_version: 5.25.2
 app_file: app.py
 pinned: false
 hf_oauth: true
+python_version: "3.10"
 # 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
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,23 +1,89 @@
 import os
-import gradio as gr
 import requests
-import inspect
+from typing import Literal
+
+import gradio as gr
 import pandas as pd
+from dotenv import load_dotenv
+from langchain_core.messages import HumanMessage, SystemMessage
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_groq import ChatGroq
+from langchain_openai import ChatOpenAI
+from langgraph.graph import MessagesState, START, StateGraph
+from langgraph.prebuilt import ToolNode, tools_condition
+
+from tools import all_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.")
+class MyAgent:
+    def __init__(self, provider: Literal['openai', 'google', 'groq'] = 'groq') -> None:
+        if provider == 'openai':
+            self.llm = ChatOpenAI(model='gpt-4.1-nano', temperature=0)
+        elif provider == 'google':
+            self.llm = ChatGoogleGenerativeAI(model='gemini-2.0-flash', temperature=0)
+        elif provider == 'groq':
+            self.llm = ChatGroq(model='qwen-qwq-32b', temperature=0)
+        else:
+            raise ValueError('Invalid provider. Choose "openai", "google", or "groq".')
+
+        self.tools = all_tools
+        self.llm_with_tools = self.llm.bind_tools(tools=self.tools)
+        self.agent = self.build_graph()
+
+        with open('system_prompt.txt', 'r', encoding='utf-8') as f:
+            self.SYSTEM_PROMPT = f.read()
+
+        if 'LANGFUSE_SECRET_KEY' in os.environ:
+            from langfuse.callback import CallbackHandler
+            self.callbacks = [
+                CallbackHandler(),
+            ]
+
     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
+        messages = [
+            SystemMessage(content=self.SYSTEM_PROMPT),
+            HumanMessage(content=question),
+        ]
+
+        response = self.agent.invoke(
+            input={'messages': messages},
+            config={'callbacks': self.callbacks},
+        )
+
+        response_content = response['messages'][-1].content
+        final_answer = self.extract_final_answer(response_content)
+        return final_answer
+
+    def assistant(self, state: MessagesState):
+        return {
+            'messages': [self.llm_with_tools.invoke(state['messages'])],
+        }
+        
+    def build_graph(self):
+        builder = StateGraph(MessagesState)
+
+        builder.add_node('assistant', self.assistant)
+        builder.add_node('tools', ToolNode(self.tools))
+
+        builder.add_edge(START, 'assistant')
+        builder.add_conditional_edges(
+            'assistant',
+            tools_condition,
+        )
+        builder.add_edge('tools', 'assistant')
+        compiled_graph = builder.compile()
+
+        return compiled_graph
+
+    def extract_final_answer(self, response_content: str) -> str:
+        start_answer_idx = response_content.find("FINAL ANSWER: ")
+        if start_answer_idx == -1:
+            return "Invalid response format. No final answer found."
+        final_answer = response_content[start_answer_idx + len("FINAL ANSWER: "):].strip()
+        return final_answer
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -40,7 +106,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = MyAgent(provider=os.environ.get('MODEL_PROVIDER', 'groq').lower())
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -54,6 +120,9 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
+
+        # questions_data = questions_data[:5]
+
         if not questions_data:
              print("Fetched questions list is empty.")
              return "Fetched questions list is empty or invalid format.", None
@@ -73,12 +142,14 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    for idx, item in enumerate(questions_data):
+        print(f'Running agent on question {idx + 1}/{len(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})
@@ -172,6 +243,7 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
+    load_dotenv()
     print("\n" + "-"*30 + " App Starting " + "-"*30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
@@ -193,4 +265,4 @@ 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)

requirements.txt

@@ -1,2 +1,14 @@
-gradio
-requests
+dotenv==0.9.9
+gradio[oauth]==5.29.0
+langchain-community==0.3.23
+langchain-google-genai==2.1.0
+langchain-groq==0.2.4
+langchain-openai==0.3.16
+langchain-tavily==0.1.6
+langchain-unstructured==0.1.6
+langfuse==2.60.3
+langgraph==0.4.1
+pillow==11.2.1
+pytesseract==0.3.13
+requests==2.32.3
+wikipedia==1.4.0

system_prompt.txt

@@ -0,0 +1,2 @@
+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]. 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 +1,134 @@
+import pytesseract
+from PIL import Image
+from dotenv import load_dotenv
+from langchain.tools import tool
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.tools import TavilySearchResults
+
+
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
+
+@tool
+def add(a: int, b: int) -> int:
+    """Add two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a + b
+
+@tool
+def subtract(a: int, b: int) -> int:
+    """Subtract two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a - b
+
+@tool
+def divide(a: int, b: int) -> float:
+    """Divide two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    try:
+        return a / b
+    except ZeroDivisionError:
+        raise ValueError("Cannot divide by zero.")
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """Get the modulus of two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a % b
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return up to 3 results.
+
+    Args:
+        query: query to search.
+    """
+
+    docs = WikipediaLoader(query, load_max_docs=3).load()
+    results = "wiki_search results:\n\n"
+    results += '\n\n---\n\n'.join([
+        f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+        for doc in docs
+    ])
+    return results
+
+@tool
+def web_search(query: str) -> str:
+    """Search the web for a query and return up to 3 results.
+
+    Args:
+        query: query to search.
+    """
+    docs = TavilySearchResults(max_results=3).invoke(query)
+    results = "web_search results:\n\n"
+    results += '\n\n---\n\n'.join([
+        f'<Document source="{doc["url"]}"/>\n{doc["content"]}\n</Document>'
+        for doc in docs
+    ])
+    return results
+
+@tool
+def extract_text_from_image(image_path: str) -> str:
+    """Extract text from a image.
+
+    Args:
+        image_path: path to the image
+
+    Returns:
+        extracted text from the image
+    """
+    try:
+        image = Image.open(image_path)
+
+        text = pytesseract.image_to_string(image)
+        return f'Extracted text: {text}'
+    except Exception as err:
+        return f'Error extracting text from the image {image_path}: {str(err)}'
+
+all_tools = [
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    wiki_search,
+    web_search,
+    extract_text_from_image,
+]
+
+def main():
+    load_dotenv()
+
+    results = wiki_search('What is Dijkstra algorithm?')
+    print(results)
+    print('-'*80)
+
+    results = web_search('What is TypedDict in python')
+    print(results)
+    print('-'*80)
+
+
+if __name__ == '__main__':
+    main()