Update space

app.py

@@ -1,64 +1,454 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+import requests
+import math
+import inspect
+import pandas as pd
+import datetime
+from dotenv import load_dotenv
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+from langchain.tools import tool, get_all_tools
+from typing import TypedDict, Annotated
+from langgraph.graph.message import add_messages
+from langchain_core.messages import AnyMessage, HumanMessage, AIMessage
+from langgraph.prebuilt import ToolNode
+from langgraph.graph import START, StateGraph, END
+from langgraph.prebuilt import tools_condition
+from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
 
+## # Load environment variables from .env file
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Load the environment variables
+load_dotenv()
+HF_ACCESS_KEY = os.environ.get("HF_ACCESS_KEY")
+WEATHER_API_KEY = os.environ.get("WEATHER_API_KEY")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+########## ----- DEFINING TOOLS -----##########
 
-    messages.append({"role": "user", "content": message})
+# --- TOOL 1: Web Search Tool (DuckDuckGo) ---
+@tool
+def search_tool(query: str) -> str:
+    """Answer general knowledge or current events queries using DuckDuckGo."""
+    url = f"https://api.duckduckgo.com/?q={query}&format=json&no_html=1"
+    try:
+        resp = requests.get(url, timeout=20)
+        resp.raise_for_status()
+        data = resp.json()
+        for key in ["AbstractText", "Answer", "Definition"]:
+            if data.get(key):
+                return data[key].split(".")[0]
+        return "no_answer"
+    except Exception:
+        return "error"
 
-    response = ""
+# when you use the @tool decorator from langchain.tools, the tool.name and tool.description are automatically extracted from your function
+# tool.name is set to the function name (e.g., `search_tool`), and 
+# tool.description is set to the docstring of the function  (the triple-quoted string right under def ...) (e.g., "Answer general knowledge or current events queries using DuckDuckGo.").
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+# --- TOOL 2: Weather Tool (OpenWeatherMap) ---
+@tool
+def get_weather(city: str) -> str:
+    """Get current temperature in Celsius for a city."""
+    import os
+    api_key = os.environ.get("WEATHER_API_KEY")
+    url = f"https://api.openweathermap.org/data/2.5/weather?q={city}&appid={WEATHER_API_KEY}&units=metric"
+    try:
+        resp = requests.get(url, timeout=20)
+        resp.raise_for_status()
+        data = resp.json()
+        return str(round(data["main"]["temp"]))
+    except Exception:
+        return "error"
 
-        response += token
-        yield response
+# --- TOOL 3: Calculator Tool ---
+@tool
+def calculator(expression: str) -> str:
+    """Evaluate math expressions."""
+    try:
+        allowed = "0123456789+-*/(). "
+        if not all(c in allowed for c in expression):
+            return "error"
+        result = eval(expression, {"__builtins__": None}, {})
+        return str(result)
+    except Exception:
+        return "error"
+    
+# --- TOOL 4: Unit Conversion Tool ---
+@tool
+def convert_units(args: str) -> str:
+    """
+    Convert between metric and imperial units (length, mass, temperature).
+    Input format: '<value> <from_unit> to <to_unit>', e.g. '10 meters to feet'
+    """
+    try:
+        parts = args.lower().split()
+        value = float(parts[0])
+        from_unit = parts[1]
+        to_unit = parts[3]
+        conversions = {
+            ("meters", "feet"): lambda v: v * 3.28084,
+            ("feet", "meters"): lambda v: v / 3.28084,
+            ("kg", "lb"): lambda v: v * 2.20462,
+            ("lb", "kg"): lambda v: v / 2.20462,
+            ("celsius", "fahrenheit"): lambda v: v * 9/5 + 32,
+            ("fahrenheit", "celsius"): lambda v: (v - 32) * 5/9,
+        }
+        func = conversions.get((from_unit, to_unit))
+        if func:
+            return str(round(func(value), 2))
+        return "error"
+    except Exception:
+        return "error"
 
+# --- TOOL 5: Date & Time Tool ---
+@tool
+def get_time(_: str = "") -> str:
+    """Get current UTC time as HH:MM."""
+    return datetime.datetime.utc().strftime("%H:%M")
 
+@tool
+def get_date(_: str = "") -> str:
+    """Get current date as YYYY-MM-DD."""
+    return datetime.datetime.utc().strftime("%Y-%m-%d")
+
+# --- TOOL 6: Wikipedia Summary Tool ---
+@tool
+def wikipedia_summary(query: str) -> str:
+    """Get a short summary of a topic from Wikipedia."""
+    url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{query.replace(' ', '_')}"
+    try:
+        resp = requests.get(url, timeout=20)
+        resp.raise_for_status()
+        data = resp.json()
+        return data.get("extract", "no_answer").split(".")[0]
+    except Exception:
+        return "error"
+
+# --- TOOL 7: Dictionary Tool ---
+@tool
+def dictionary_lookup(word: str) -> str:
+    """Get the definition of an English word."""
+    url = f"https://api.dictionaryapi.dev/api/v2/entries/en/{word}"
+    try:
+        resp = requests.get(url, timeout=20)
+        resp.raise_for_status()
+        data = resp.json()
+        return data[0]["meanings"][0]["definitions"][0]["definition"]
+    except Exception:
+        return "error"
+    
+# --- TOOL 8: Currency Conversion Tool ---
+@tool
+def currency_convert(args: str) -> str:
+    """
+    Convert an amount from one currency to another.
+    Input format: '<amount> <from_currency> to <to_currency>', e.g. '100 USD to EUR'
+    """
+    try:
+        parts = args.upper().split()
+        amount = float(parts[0])
+        from_currency = parts[1]
+        to_currency = parts[3]
+        url = f"https://api.exchangerate.host/convert?from={from_currency}&to={to_currency}&amount={amount}"
+        resp = requests.get(url, timeout=20)
+        resp.raise_for_status()
+        data = resp.json()
+        return str(round(data["result"], 2))
+    except Exception:
+        return "error"
+
+##-- Tool Discovery ---
+# Use @tool for each function.
+# Use get_all_tools() to auto-discover all decorated tools.
+tools_list = get_all_tools()
+
+tool_descriptions = "\n".join(f"- {tool.name}: {tool.description}" for tool in tools_list)
+
+
+## --
+# --- System Prompt for the Agent ---
+system_prompt = f"""
+You are an intelligent assistant with access to the following tools:
+
+{tool_descriptions}
+
+For every question, always follow this process (your internal thinking/execution process):
+
+1. Thought: Reflect step by step on what the user is asking and what information or calculation is needed. Decide if you need to use a tool or can answer directly.
+2. Action: If a tool is needed, specify which tool to use and with what input. If not, state "No action needed".
+3. Observation: If you used a tool, report the tool's output here. If not, write "N/A".
+4. Answer: Give the final answer as a single value (number, string, or comma-separated list), with no extra explanation or units unless requested.
+
+Your Final Answer should be just [Answer] and should not include any additional text or explanation. Final Answer should be a single value (number, string, or comma-separated list).
+
+Examples:
+
+Q: What is 7 * (3 + 2)?
+Thought: The user is asking for a math calculation. I should use the calculator tool.
+Action: calculator("7 * (3 + 2)")
+Observation: 35
+Answer: 35
+
+Your Output (Final Answer) for this question should be: '35'.
+
+Q: What’s the weather in Tokyo?
+Thought: The user wants the current temperature in Tokyo. I should use the get_weather tool.
+Action: get_weather("Tokyo")
+Observation: 22
+Answer: 22
+
+Your Output (Final Answer) for this question should be: '22'.
+
+Q: What is the capital of France?
+Thought: The user is asking for a factual answer. I can answer directly.
+Action: No action needed
+Observation: N/A
+Answer: Paris
+
+Your Output (Final Answer) for this question should be: 'Paris'.
+
+Q: Convert 10 meters to feet.
+Thought: The user wants to convert units. I should use the convert_units tool.
+Action: convert_units("10 meters to feet")
+Observation: 32.81
+Answer: 32.81
+
+Your Output (Final Answer) for this question should be: '32.81'.
+
+Instructions:
+- Always follow the Thought → Action → Observation → Answer for your internal reasoning and execution before giving final answer.
+- Use a tool only if necessary, and don't use multiple tools in a call. Don't use a tool if you can answer directly without hallucination. 
+- Always return your final answer as a single value, with no extra explanation.
+- Be concise and accurate.
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+
+## --- Initialize Hugging Face Model ---
+# Generate the chat interface, including the tools
+llm = HuggingFaceEndpoint(
+    repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
+    huggingfacehub_api_token=HF_ACCESS_KEY,
+    system_prompt=system_prompt,
 )
+# chat = ChatHuggingFace(llm=llm, verbose=True)
+# tools = [search_tool, fetch_weather]
+# chat_with_tools = chat.bind_tools(tools)
+
+
+##
+# --- LANGGRAPH AGENT SETUP ---
+
+# Define the state for the graph
+class AgentState(dict):
+    pass
 
+# Define the main node (agent logic)
+def agent_node(state: AgentState) -> AgentState:
+    question = state["question"]
+    # The LLM will decide which tool to use based on the prompt and tools
+    # response = chat_with_tools.invoke(question) # use this if using ChatHuggingFace with binding option to tools
+    response = llm.invoke(question, tools=tools_list)
+    return AgentState({"question": question, "answer": response})
+
+# Build the graph
+graph = StateGraph(AgentState)
+graph.add_node("agent", agent_node)
+# graph.add_node("tools", ToolNode(tools)) #use this when using ChatHuggingFace with binding option to tools
+# graph.add_edge(START, "agent") #alternatively use the below with set_entry_point
+graph.set_entry_point("agent")
+graph.add_edge("agent", END)
+my_agent = graph.compile()
+
+# Or try simply with Graph instead of StateGraph
+# from langgraph.graph import Graph
+# graph = Graph(llm=llm, tools=tools_list)
+# def agent(question: str) -> str:
+#     return graph.run(question)
+
+## --- AGENT CALL FUNCTION ---
+def agent(question: str) -> str:
+    state = AgentState({"question": question})
+    result = my_agent.invoke(state)
+    return result["answer"]
+
+
+
+## --
+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__":
-    demo.launch()
+    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

@@ -1 +1,8 @@
-huggingface_hub==0.25.2
+gradio
+requests
+math
+langchain
+langgraph
+langchainhub
+huggingface-hub
+langchain-huggingface