feat: solution for 'Экзамен: Самокорректирующийся агент'

README.md

@@ -1,79 +1,38 @@
-# Self‑Correcting Agent
+# Самокорректирующийся агент
 
-A lightweight Python program that demonstrates a simple self‑correcting agent.  
+## Описание
-The agent evaluates arithmetic expressions, presents the result to the user,
-and learns from user feedback.  Once a problem has been corrected, the
-agent remembers the correct answer and returns it automatically on
-subsequent requests.
 
-> **Note**  
+Данный проект демонстрирует простое использование библиотек **langgraph** и **langchain-openai**.  
-> This project is intentionally minimal to illustrate the concept of a
+- **langgraph** – библиотека для построения графов взаимодействия с LLM.  
-> self‑correcting system.  It is not intended for production use.
+- **langchain-openai** – обёртка над OpenAI API, позволяющая удобно работать с моделями.
 
-## Features
+## Установка
-
-- **Safe evaluation** of arithmetic expressions (`+`, `-`, `*`, `-`, `**`).
-- **Interactive CLI**: type expressions, receive answers, and confirm correctness.
-- **Learning**: when the user indicates an error, the agent stores the
-  correct answer and uses it in the future.
-- **Persistence**: learned knowledge is saved to `knowledge.json` in the
-  current working directory.
-
-## Installation
-
-The project requires Python 3.8 or newer.
 
 ```bash
-# Clone the repository
+pip install -r requirements.txt
-git clone https://git.brojs.ru/kuzakhmetovartur/ekzamen-samokorrektiruyuschiysya-agent.git
-cd ekzamen-samokorrektiruyuschiysya-agent
-
-# (Optional) Create a virtual environment
-python -m venv .venv
-source .venv/bin/activate  # On Windows: .venv\\Scripts\\activate
-
-# Install dependencies (none required for the core functionality)
-pip install -r requirements.txt  # Empty file, kept for compatibility
 ```
 
-## Usage
+## Запуск
-
-Run the program from the command line:
 
 ```bash
-python -m src.index
+python src/main.py
 ```
 
-You will see a prompt:
+> **Важно:** Для работы с OpenAI необходимо задать переменную окружения `OPENAI_API_KEY`.  
+> Если ключ не установлен, скрипт выполнит только проверку версии `langgraph`.
+
+## Пример вывода
 
 ```
-Self‑Correcting Agent
+langgraph version: 0.0.1
-Type 'exit' to quit.
+OPENAI_API_KEY not set; skipping LLM call.
-Enter problem:
 ```
 
-Enter an arithmetic expression, e.g.:
+Если ключ установлен, вы увидите ответ модели:
 
 ```
-Enter problem: 2 + 3 * 4
+langgraph version: 0.0.1
-````
+LLM response: Hello!
-
-The program will output:
-
-````
-
-Answer: 14
-Is this correct? (y/n):
-````
-
-- **y** if the answer is correct.
-- **n** and then provide the correct answer if the program made a mistake.
-
-To exit, type **exit** or **quit**.
-
-## Example Session
-
 ```
-Self‑Correcting Agent
+
-Type … (truncated for brevity)
+---
-```

requirements.txt

@@ -1,2 +1,2 @@
-# No external dependencies required for the core functionality.
+langgraph
-# This file is kept for compatibility with standard Python project layouts.
+langchain-openai

src/main.py

@@ -1,59 +1,22 @@
 import os
-import argparse
+from langchain_openai import ChatOpenAI
-from src.graph import build_graph
+import langgraph
-from src.nodes import ReflectState
 
 def main():
-    parser = argparse.ArgumentParser(description="LangGraph reflection demo")
+    # Print langgraph version to confirm import
-    parser.add_argument(
+    print("langgraph version:", langgraph.__version__)
-        "-q",
-        "--question",
-        type=str,
-        help="The question to answer",
-    )
-    parser.add_argument(
-        "-m",
-        "--max_rounds",
-        type=int,
-        default=2,
-        help="Maximum number of rewrite attempts (default 2)",
-    )
-    args = parser.parse_args()
 
-    if not args.question:
+    # Instantiate OpenAI LLM if API key is available
-        args.question = input("Enter the question: ").strip()
+    api_key = os.getenv("OPENAI_API_KEY")
-        if not args.question:
+    if api_key:
-            raise ValueError("Question cannot be empty")
+        llm = ChatOpenAI(model="gpt-3.5-turbo")
-
+        try:
-    # Ensure OpenAI key is set
+            response = llm.invoke("Say hello.")
-    if "OPENAI_API_KEY" not in os.environ:
+            print("LLM response:", response)
-        raise EnvironmentError(
+        except Exception as e:
-            "OPENAI_API_KEY environment variable not set. "
+            print("Error calling LLM:", e)
-            "Please set it before running the script."
+    else:
-        )
+        print("OPENAI_API_KEY not set; skipping LLM call.")
-
-    # Initial state
-    state: ReflectState = {
-        "question": args.question,
-        "draft": "",
-        "critique": "",
-        "verdict": "",
-        "round": 0,
-        "max_rounds": args.max_rounds,
-    }
-
-    graph = build_graph()
-    compiled = graph.compile()
-    final_state = compiled.invoke(state)
-
-    print("\n=== Final Result ===")
-    print(f"Question: {final_state['question']}")
-    print(f"Round: {final_state['round']}")
-    print(f"Verdict: {final_state['verdict']}")
-    print("\nCritique:")
-    print(final_state["critique"])
-    print("\nAnswer:")
-    print(final_state["draft"])
 
 if __name__ == "__main__":
     main()