Create app.py

Create the agent

app.py

@@ -1,196 +1,142 @@
-import os
-import gradio as gr
-import requests
-import inspect
-import pandas as pd
-
-# (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.")
-    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
-
-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}")
+from transformers import pipeline
+import operator
+from langgraph.graph import StateGraph, START, END
+from typing import Annotated
+from typing_extensions import TypedDict, Optional
+from langgraph.types import Send
+from pydantic import BaseModel
+
+from langchain_community.utilities import WikipediaAPIWrapper
+from langchain_community.tools import WikipediaQueryRun
+from langchain_experimental.utilities import PythonREPL
+
+llm = pipeline("text-generation", model="distilgpt2")
+
+class SmallerQuestions(BaseModel):
+    questions = list[str]
+
+class Question(BaseModel):
+    question: str
+    nature: str
+    context: str
+    middle_answer: str
+
+class Nature(BaseModel):
+    nature: Literal["research", "computation", "interpretation"]
+
+class SearchableQuestion(BaseModel):
+    question: str
+    key_words: list[str]
+    context: str
+
+class Code(BaseModel):
+    code: str
+
+class OverallState(TypedDict):
+    first_question: str
+    smaller_questions: list[str]
+    middle_answer: Annotated[list, operator.add]
+    answer: str
+
+#Nodes
+
+def BreakQuestion(state: OverallState):
+    prompt = """Task: 
+                Break the following question down into a maximum of 7 smaller questions. 
+                Your response must be a list in which each item corresponds to one smaller question.
+                Question:
+                """ + state["first_question"]
+    response = llm.with_structured_output(SmallerQuestions).invoke(prompt)
+    return {smaller_questions: response.questions}
+
+def DecideNature(state: Question):
+    prompt = """Task:
+                The following question is answearable via one of these three approaches: "computation", "reasearch" or "interpretation".
+                Computation is a question that requires a python interpreter; research is a question that requires a web search in sites like wikipedia; interpretation is a question that needs only reasoning to be answered.
+                Decide which of those is the best approach and return only the string corresponding to the one you choose, and nothing else.
+                Question: 
+                """ + state["question"]
+    response = llm.with_structured_output(Nature).invoke(prompt)
+    return {nature: response.nature}
+
+def KeyWords(state: SearchableQuestion):
+    prompt = """Task:
+                Gather the key words from the following question to perform a search.
+                Question:
+                """ + state["question"]
+    response = llm.with_structured_output(SearchableQuestion).invoke(prompt)
+    return {key_words: response.key_words}
+    
+def WikiSearch(state: SearchableQuestion):
+    wikipedia_api = WikipediaAPIWrapper(top_k_results=1,doc_content_chars_max=1000)
+    wikipedia = WikipediaQueryRun(api_wrapper=wikipedia_api)
+    result = wikipedia.run({query: state["key_words"]})
+    return {context: result}
+
+def ContextAnswer(state: SearchableQuestion):
+    prompt = """Task:
+                I will give you a context and a question, and I wnat you to answer the question based on the given context and nothing else.
+                Context:
+                """ + state["context"] + "Question: " + state["question"]
+    response = llm.invoke(prompt)
+    return {middle_answer: [response]}
+
+def Computation(state: Question):
+    python_repl = PythonREPL()
+    prompt = """Task:
+                The following question requires a computation to be answered. Create a code that solves the problem.
+                Your response must be only the code that solves the problem and nothing else.
+                Question:
+                """ + state["question"]
+    response = llm.with_structured_output(Code).invoke(prompt)
+    code_result = python_repl.run(response.code)
+    structured_answer = "The result of the following problem is " + code_result + "Problem: " + state["question"]
+    return {middle_answer: [structured_answer]}
+
+def Reasoning(state: Question):
+    prompt = """Task:
+                Answer the following question using your reasoning. Your response must be contain only the answer to the question and nothing else.
+                Question:
+                """ + state["question"])
+    response = llm.invoke(prompt)
+    return {middle_answer: [response]}
+
+def FinalAnswer(state: OverallState):
+    middle_answers = "\n\n".join(state["middle_answer"])
+    prompt = """Task:
+                You will receive a question and some information from which you must be able to solve the question completely.
+                Do your best to keep your response as close to the given information as possible. Your response should contain only the final answer to the question and nothing else.
+                Question:
+                """ + state["question"] + "Context: " + middle_answers
+    response = llm.invoke(prompt)
+    return {answer: response}
+
+#Edges
+
+def Nature(state: Question):
+    if state["nature"] == "computation":
+        return Send("computation", state)
+    elif state["nature"] == "research":
+        return Send("key_words", state)
     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")
+        return Send("interpretation", state)
+
+builder = StateGraph(State)
+builder.add_node("break_question", BreakQuestion)
+builder.add_node("key_words", KeyWords)
+builder.add_node("search", WikiSearch)
+builder.add_node("answer", ContextAnswer)
+builder.add_node("computation", Computation)
+builder.add_node("interpretation", Reasoning)
+builder.add_node("final_answer", FinalAnswer)
+builder.add_edge(START, "break_question")
+builder.add_conditional_edges("define_nature", Nature)
+builder.add_edge("key_words", "search")
+builder.add_edge("search", "answer")
+builder.add_edge("answer", "final_answer")
+builder.add_edge("computation", "final_answer")
+builder.add_edge("interpretation", "final_answer")
+builder.add_edge("final_answer", END)
+
+graph = builder.compile()
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)