Fix

app.py

@@ -1,200 +1,232 @@
 import os
-import gradio as gr
-import requests
-import inspect
-import pandas as pd
-from agent import build_graph
-
-# (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.")
-        self.graph = build_graph()
-        
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        # Wrap the question in a HumanMessage from langchain_core
-        messages = [HumanMessage(content=question)]
-        messages = self.graph.invoke({"messages": messages})
-        answer = messages['messages'][-1].content
-        return answer[14:]
-
-
-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)
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+# Set protobuf implementation to avoid C++ extension issues
+os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
+
+# Load keys from environment
+hf_token = os.getenv("HUGGINGFACE_INFERENCE_TOKEN")
+serper_api_key = os.getenv("SERPER_API_KEY")
+
+# ---- Imports ----
+from langgraph.graph import START, StateGraph, MessagesState
+from langgraph.prebuilt import tools_condition, ToolNode
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
+from langchain_community.vectorstores import Chroma
+from langchain_core.documents import Document
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_core.tools import tool
+from langchain.tools.retriever import create_retriever_tool
+from langchain.embeddings import HuggingFaceEmbeddings
+import json
+
+# ---- Tools ----
+
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers together."""
+    return a * b
+
+@tool
+def add(a: int, b: int) -> int:
+    """Add two numbers together."""
+    return a + b
+
+@tool
+def subtract(a: int, b: int) -> int:
+    """Subtract the second number from the first."""
+    return a - b
+
+@tool
+def divide(a: int, b: int) -> float:
+    """Divide the first number by the second. Returns float or error if dividing by zero."""
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """Returns the remainder after division of the first number by the second."""
+    return a % b
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for information. Useful for factual questions about people, places, events, etc."""
     try:
-        agent = BasicAgent()
+        search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+        formatted = "\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 search_docs
+            ]
+        )
+        return {"wiki_results": formatted}
     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}")
+        return f"Wikipedia search failed: {str(e)}"
+
+@tool
+def web_search(query: str) -> str:
+    """Search the web for current information. Useful when you need recent or non-Wikipedia information."""
     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
+        search = TavilySearchResults(max_results=3)
+        search_docs = search.invoke(query)
+        formatted = "\n\n---\n\n".join(
+            [
+                f'<Document source="{doc["url"]}"/>\n{doc["content"]}\n</Document>'
+                for doc in search_docs
+            ]
+        )
+        return {"web_results": formatted}
     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}")
+        return f"Web search failed: {str(e)}"
+
+@tool
+def arxiv_search(query: str) -> str:
+    """Search academic papers on ArXiv. Useful for technical or scientific questions."""
     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.')}"
+        search_docs = ArxivLoader(query=query, load_max_docs=2).load()
+        formatted = "\n\n---\n\n".join(
+            [
+                f'<Document source="{doc.metadata["source"]}"/>\n{doc.page_content[:1000]}\n</Document>'
+                for doc in search_docs
+            ]
         )
-        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
+        return {"arxiv_results": formatted}
     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.
-        """
+        return f"ArXiv search failed: {str(e)}"
+
+# ---- Embedding & Vector Store Setup ----
+
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+
+# Load QA pairs
+json_QA = []
+try:
+    with open('metadata.jsonl', 'r') as jsonl_file:
+        for line in jsonl_file:
+            json_QA.append(json.loads(line))
+except Exception as e:
+    print(f"Error loading metadata.jsonl: {e}")
+    json_QA = []
+
+documents = [
+    Document(
+        page_content=f"Question: {sample['Question']}\n\nAnswer: {sample['Final answer']}",
+        metadata={"source": sample["task_id"], "question": sample["Question"], "answer": sample["Final answer"]}
     )
+    for sample in json_QA
+]
+
+try:
+    vector_store = Chroma.from_documents(
+        documents=documents,
+        embedding=embeddings,
+        persist_directory="./chroma_db",
+        collection_name="qa_collection"
+    )
+    vector_store.persist()
+    print(f"Documents inserted: {len(documents)}")
+except Exception as e:
+    print(f"Error creating vector store: {e}")
+    raise
+
+@tool
+def similar_question_search(query: str) -> str:
+    """Search for similar questions that have been answered before. Always check here first before using other tools."""
+    try:
+        matched_docs = vector_store.similarity_search(query, k=3)
+        formatted = "\n\n---\n\n".join(
+            [
+                f'<Question: {doc.metadata["question"]}>\n<Answer: {doc.metadata["answer"]}>\n</Document>'
+                for doc in matched_docs
+            ]
+        )
+        return {"similar_questions": formatted}
+    except Exception as e:
+        return f"Similar question search failed: {str(e)}"
 
-    gr.LoginButton()
+# ---- System Prompt ----
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+system_prompt = """
+You are an expert question-answering assistant. Follow these steps for each question:
 
-    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)
+1. FIRST check for similar questions using the similar_question_search tool
+2. If a similar question exists with a clear answer, use that answer
+3. If not, determine which tools might help answer the question
+4. Use the tools systematically to gather information
+5. Combine information from multiple sources if needed
+6. Format your final answer precisely as:
+FINAL ANSWER: [your answer here]
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+Rules for answers:
+- Numbers: plain digits only (no commas, units, or symbols)
+- Strings: minimal words, no articles, full names
+- Lists: comma-separated with no extra formatting
+- Be concise but accurate
+"""
 
-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)
+sys_msg = SystemMessage(content=system_prompt)
+
+# ---- Tool List ----
+
+tools = [
+    similar_question_search,  # Check this first
+    multiply, add, subtract, divide, modulus,  # Math tools
+    wiki_search, web_search, arxiv_search  # Information tools
+]
+
+# ---- Graph Definition ----
+
+def build_graph():
+    try:
+        # Using a powerful HuggingFace model
+        llm = ChatHuggingFace(
+            llm=HuggingFaceEndpoint(
+                repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1",
+                temperature=0,
+                max_new_tokens=512,
+                huggingfacehub_api_token=hf_token
+            )
+        )
+        
+        llm_with_tools = llm.bind_tools(tools)
+
+        def assistant(state: MessagesState):
+            return {"messages": [llm_with_tools.invoke(state["messages"])]}
+
+        def retriever(state: MessagesState):
+            try:
+                # First try to find similar questions
+                similar = vector_store.similarity_search(state["messages"][-1].content, k=2)
+                if similar:
+                    example_msg = HumanMessage(
+                        content=f"Here are similar questions and their answers:\n\n" +
+                        "\n\n".join([f"Q: {doc.metadata['question']}\nA: {doc.metadata['answer']}" 
+                                   for doc in similar])
+                    )
+                    return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+                return {"messages": [sys_msg] + state["messages"]}
+            except Exception as e:
+                print(f"Retriever error: {e}")
+                return {"messages": [sys_msg] + state["messages"]}
+
+        builder = StateGraph(MessagesState)
+        builder.add_node("retriever", retriever)
+        builder.add_node("assistant", assistant)
+        builder.add_node("tools", ToolNode(tools))
+        
+        builder.add_edge(START, "retriever")
+        builder.add_edge("retriever", "assistant")
+        builder.add_conditional_edges("assistant", tools_condition)
+        builder.add_edge("tools", "assistant")
+
+        return builder.compile()
+    
+    except Exception as e:
+        print(f"Error building graph: {e}")
+        raise

lang.txt

@@ -0,0 +1,412 @@
+Final_Assignment_Template\app.py
+import os
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+from agent import build_graph
+
+# (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.")
+        self.graph = build_graph()
+        
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        # Wrap the question in a HumanMessage from langchain_core
+        messages = [HumanMessage(content=question)]
+        messages = self.graph.invoke({"messages": messages})
+        answer = messages['messages'][-1].content
+        return answer[14:]
+
+
+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]
+    )
+
+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)
+Final_Assignment_Template\agent.py:
+import os
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+# Set protobuf implementation to avoid C++ extension issues
+os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
+
+# Load keys from environment
+groq_api_key = os.getenv("GROQ_API_KEY")
+serper_api_key = os.getenv("SERPER_API_KEY")
+hf_token = os.getenv("HUGGINGFACE_INFERENCE_TOKEN")
+
+# ---- Imports ----
+from langgraph.graph import START, StateGraph, MessagesState
+from langgraph.prebuilt import tools_condition, ToolNode
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_groq import ChatGroq
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
+from langchain_community.vectorstores import Chroma
+from langchain_core.documents import Document
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_core.tools import tool
+from langchain.tools.retriever import create_retriever_tool
+from langchain.vectorstores import Chroma
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.schema import Document
+import json
+
+# ---- Tools ----
+
+@tool
+def multiply(a: int, b: int) -> int:
+    return a * b
+
+@tool
+def add(a: int, b: int) -> int:
+    return a + b
+
+@tool
+def subtract(a: int, b: int) -> int:
+    return a - b
+
+@tool
+def divide(a: int, b: int) -> float:
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+@tool
+def modulus(a: int, b: int) -> int:
+    return a % b
+
+@tool
+def wiki_search(query: str) -> str:
+    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    formatted = "\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 search_docs
+        ]
+    )
+    return {"wiki_results": formatted}
+
+@tool
+def web_search(query: str) -> str:
+    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
+    formatted = "\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 search_docs
+        ]
+    )
+    return {"web_results": formatted}
+
+@tool
+def arvix_search(query: str) -> str:
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in search_docs
+        ]
+    )
+    return {"arvix_results": formatted}
+
+# ---- Embedding & Vector Store Setup ----
+
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+
+json_QA = []
+with open('metadata.jsonl', 'r') as jsonl_file:
+    for line in jsonl_file:
+        json_QA.append(json.loads(line))
+
+documents = [
+    Document(
+        page_content=f"Question : {sample['Question']}\n\nFinal answer : {sample['Final answer']}",
+        metadata={"source": sample["task_id"]}
+    )
+    for sample in json_QA
+]
+
+vector_store = Chroma.from_documents(
+    documents=documents,
+    embedding=embeddings,
+    persist_directory="./chroma_db",
+    collection_name="my_collection"
+)
+vector_store.persist()
+print("Documents inserted:", vector_store._collection.count())
+
+@tool
+def similar_question_search(query: str) -> str:
+    matched_docs = vector_store.similarity_search(query, 3)
+    formatted = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in matched_docs
+        ]
+    )
+    return {"similar_questions": formatted}
+
+# ---- System Prompt ----
+
+system_prompt = """
+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...
+"""
+
+sys_msg = SystemMessage(content=system_prompt)
+
+# ---- Tool List ----
+
+tools = [
+    multiply, add, subtract, divide, modulus,
+    wiki_search, web_search, arvix_search, similar_question_search
+]
+
+# ---- Graph Definition ----
+
+def build_graph(provider: str = "groq"):
+    if provider == "groq":
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0, api_key=groq_api_key)
+    elif provider == "google":
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+    elif provider == "huggingface":
+        llm = ChatHuggingFace(
+            llm=HuggingFaceEndpoint(repo_id="mosaicml/mpt-30b", temperature=0)
+        )
+    else:
+        raise ValueError("Invalid provider: choose 'groq', 'google', or 'huggingface'.")
+
+    llm_with_tools = llm.bind_tools(tools)
+
+    def assistant(state: MessagesState):
+        return {"messages": [llm_with_tools.invoke(state["messages"])]}
+
+    def retriever(state: MessagesState):
+        similar = vector_store.similarity_search(state["messages"][0].content)
+        if similar:
+            example_msg = HumanMessage(content=f"Here is a similar question:\n\n{similar[0].page_content}")
+            return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+        return {"messages": [sys_msg] + state["messages"]}
+
+    builder = StateGraph(MessagesState)
+    builder.add_node("retriever", retriever)
+    builder.add_node("assistant", assistant)
+    builder.add_node("tools", ToolNode(tools))
+    builder.add_edge(START, "retriever")
+    builder.add_edge("retriever", "assistant")
+    builder.add_conditional_edges("assistant", tools_condition)
+    builder.add_edge("tools", "assistant")
+
+    return builder.compile()
+Final_Assignment_Template\metadata.jsonl:
+
+Final_Assignment_Template\requirements.txt:
+gradio
+requests
+langchain
+langchain-community
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-groq
+langchain-tavily
+langchain-chroma
+langgraph
+sentence-transformers
+huggingface_hub
+supabase
+arxiv
+pymupdf
+wikipedia
+pgvector
+python-dotenv
+protobuf==3.20.3
+
+Final_Assignment_Template\system_prompt.txt:
+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.