renew

agent.py

@@ -0,0 +1,214 @@
+"""LangGraph Agent"""
+import os
+from dotenv import load_dotenv
+from langgraph.graph import START, StateGraph, MessagesState
+from langgraph.prebuilt import tools_condition
+from langgraph.prebuilt import 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
+from langchain_community.document_loaders import ArxivLoader
+from langchain_community.vectorstores import SupabaseVectorStore
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_core.tools import tool
+from langchain.tools.retriever import create_retriever_tool
+from supabase.client import Client, create_client
+
+load_dotenv()
+
+@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) -> int:
+    """Divide two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+@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 maximum 2 results.
+    
+    Args:
+        query: The search query."""
+    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    formatted_search_docs = "\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_search_docs}
+
+@tool
+def web_search(query: str) -> str:
+    """Search Tavily for a query and return maximum 3 results.
+    
+    Args:
+        query: The search query."""
+    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
+    formatted_search_docs = "\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_search_docs}
+
+@tool
+def arvix_search(query: str) -> str:
+    """Search Arxiv for a query and return maximum 3 result.
+    
+    Args:
+        query: The search query."""
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\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_search_docs}
+
+
+
+# load the system prompt from the file
+with open("system_prompt.txt", "r", encoding="utf-8") as f:
+    system_prompt = f.read()
+
+# System message
+sys_msg = SystemMessage(content=system_prompt)
+
+# build a retriever
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
+supabase: Client = create_client(
+    os.environ.get("SUPABASE_URL"), 
+    os.environ.get("SUPABASE_SERVICE_KEY"))
+vector_store = SupabaseVectorStore(
+    client=supabase,
+    embedding= embeddings,
+    table_name="documents",
+    query_name="match_documents_langchain",
+)
+create_retriever_tool = create_retriever_tool(
+    retriever=vector_store.as_retriever(),
+    name="Question Search",
+    description="A tool to retrieve similar questions from a vector store.",
+)
+
+
+
+tools = [
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    wiki_search,
+    web_search,
+    arvix_search,
+]
+
+# Build graph function
+def build_graph(provider: str = "groq"):
+    """Build the graph"""
+    # Load environment variables from .env file
+    if provider == "google":
+        # Google Gemini
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+    elif provider == "groq":
+        # Groq https://console.groq.com/docs/models
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
+    elif provider == "huggingface":
+        # TODO: Add huggingface endpoint
+        llm = ChatHuggingFace(
+            llm=HuggingFaceEndpoint(
+                url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
+                temperature=0,
+            ),
+        )
+    else:
+        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
+    # Bind tools to LLM
+    llm_with_tools = llm.bind_tools(tools)
+
+    # Node
+    def assistant(state: MessagesState):
+        """Assistant node"""
+        return {"messages": [llm_with_tools.invoke(state["messages"])]}
+    
+    def retriever(state: MessagesState):
+        """Retriever node"""
+        similar_question = vector_store.similarity_search(state["messages"][0].content)
+        example_msg = HumanMessage(
+            content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
+        )
+        return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+
+    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")
+
+    # Compile graph
+    return builder.compile()
+
+# test
+if __name__ == "__main__":
+    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
+    # Build the graph
+    graph = build_graph(provider="groq")
+    # Run the graph
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()

app.py

@@ -1,58 +1,38 @@
+""" Basic Agent Evaluation Runner"""
 import os
+import inspect
 import gradio as gr
 import requests
 import pandas as pd
-from dotenv import load_dotenv
-from gemini_agent import GeminiAgent
+from langchain_core.messages import HumanMessage
+from agent import build_graph
+
 
-import time
-import requests
 
-# Constants
+# (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:
+    """A langgraph agent."""
     def __init__(self):
-        print("Initializing the BasicAgent")
-        
-        # Get Gemini API key
-        api_key = os.getenv('GOOGLE_API_KEY')
-        if not api_key:
-            raise ValueError("GOOGLE_API_KEY environment variable not set.")
-            
-        # Initialize GeminiAgent
-        self.agent = GeminiAgent(api_key=api_key)
-        print("GeminiAgent initialized successfully")
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
 
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        final_answer = self.agent.run(question)
-        print(f"Agent returning fixed answer: {final_answer}")
-        return final_answer
+        # 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 fetch_questions_with_retry(url: str, retries: int = 5, backoff_factor: float = 1.0):
-    """
-    尝试 GET url，遇到 429 时指数退避重试，直到成功或超过重试次数。
-    """
-    for i in range(retries):
-        try:
-            resp = requests.get(url, timeout=15)
-            resp.raise_for_status()
-            return resp.json()
-        except requests.exceptions.HTTPError as e:
-            if resp.status_code == 429 and i < retries - 1:
-                wait = backoff_factor * (2 ** i)
-                print(f"Received 429, retrying after {wait:.1f}s (attempt {i+1}/{retries})…")
-                time.sleep(wait)
-                continue
-            else:
-                # 其余 HTTPError 或最后一次 429 都抛出
-                raise
-        except Exception:
-            # 网络等其它错误，直接抛
-            raise
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
+
+def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
@@ -82,36 +62,25 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     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
-    
-    questions_url = f"{api_url}/questions"
     print(f"Fetching questions from: {questions_url}")
     try:
-        questions_data = fetch_questions_with_retry(questions_url, retries=5, backoff_factor=1.0)
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
+        questions_data = response.json()
         if not questions_data:
-            return "Fetched questions list is empty or invalid format.", None
+             print("Fetched questions list is empty.")
+             return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
-    except Exception as e:
-        print(f"Error fetching questions after retries: {e}")
+    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 = []

app2.py

@@ -0,0 +1,240 @@
+import os
+import gradio as gr
+import requests
+import pandas as pd
+from dotenv import load_dotenv
+from gemini_agent import GeminiAgent
+
+import time
+import requests
+
+# Constants
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+class BasicAgent:
+    def __init__(self):
+        print("Initializing the BasicAgent")
+        
+        # Get Gemini API key
+        api_key = os.getenv('GOOGLE_API_KEY')
+        if not api_key:
+            raise ValueError("GOOGLE_API_KEY environment variable not set.")
+            
+        # Initialize GeminiAgent
+        self.agent = GeminiAgent(api_key=api_key)
+        print("GeminiAgent initialized successfully")
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        final_answer = self.agent.run(question)
+        print(f"Agent returning fixed answer: {final_answer}")
+        return final_answer
+
+def fetch_questions_with_retry(url: str, retries: int = 5, backoff_factor: float = 1.0):
+    """
+    尝试 GET url，遇到 429 时指数退避重试，直到成功或超过重试次数。
+    """
+    for i in range(retries):
+        try:
+            resp = requests.get(url, timeout=15)
+            resp.raise_for_status()
+            return resp.json()
+        except requests.exceptions.HTTPError as e:
+            if resp.status_code == 429 and i < retries - 1:
+                wait = backoff_factor * (2 ** i)
+                print(f"Received 429, retrying after {wait:.1f}s (attempt {i+1}/{retries})…")
+                time.sleep(wait)
+                continue
+            else:
+                # 其余 HTTPError 或最后一次 429 都抛出
+                raise
+        except Exception:
+            # 网络等其它错误，直接抛
+            raise
+
+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
+    
+    questions_url = f"{api_url}/questions"
+    print(f"Fetching questions from: {questions_url}")
+    try:
+        questions_data = fetch_questions_with_retry(questions_url, retries=5, backoff_factor=1.0)
+        if not questions_data:
+            return "Fetched questions list is empty or invalid format.", None
+        print(f"Fetched {len(questions_data)} questions.")
+    except Exception as e:
+        print(f"Error fetching questions after retries: {e}")
+        return f"Error 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)

requirements copy.txt

@@ -0,0 +1,21 @@
+gradio
+langchain>=0.1.0
+langchain-core>=0.1.0
+langchain-community>=0.0.10
+langchain-google-genai>=0.0.6
+google-generativeai>=0.3.0
+python-dotenv>=1.0.0
+google-api-python-client>=2.108.0
+duckduckgo-search>=4.4
+tiktoken>=0.5.2
+google-cloud-speech>=2.24.0
+requests>=2.31.0
+pydub>=0.25.1
+yt-dlp>=2023.12.30
+smolagents>=0.1.3
+wikipedia>=1.4.0
+Pillow>=10.2.0
+wikipedia-api>=0.6.0
+transformers
+wikipedia
+torch

requirements.txt

@@ -1,21 +1,18 @@
 gradio
-langchain>=0.1.0
-langchain-core>=0.1.0
-langchain-community>=0.0.10
-langchain-google-genai>=0.0.6
-google-generativeai>=0.3.0
-python-dotenv>=1.0.0
-google-api-python-client>=2.108.0
-duckduckgo-search>=4.4
-tiktoken>=0.5.2
-google-cloud-speech>=2.24.0
-requests>=2.31.0
-pydub>=0.25.1
-yt-dlp>=2023.12.30
-smolagents>=0.1.3
-wikipedia>=1.4.0
-Pillow>=10.2.0
-wikipedia-api>=0.6.0
-transformers
+requests
+langchain
+langchain-community
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-groq
+langchain-tavily
+langchain-chroma
+langgraph
+huggingface_hub
+supabase
+arxiv
+pymupdf
 wikipedia
-torch
+pgvector
+python-dotenv

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.