текстовая игра на основе llm + interrupt: README.md

This commit is contained in:
2026-05-27 11:43:47 +00:00
parent 3a2d28bddf
commit 1c344658a6
@@ -0,0 +1,133 @@
# Interactive Text Adventure LLM + Interrupt
A lightweight Python project that turns a large language model (LLM) into an interactive “chooseyourownadventure” game.
The story is generated by the LLM, then paused for user input via a console prompt (`questionary`). After the player selects an option, the graph resumes and the LLM writes a short ending based on that choice.
> **TL;DR** Run `python game.py`, answer the prompts, and watch the AI craft your story in real time.
---
## Table of Contents
- [What It Does](#what-it-does)
- [Prerequisites](#prerequisites)
- [Installation](#installation)
- [Running the Game](#running-the-game)
- [Example Session](#example-session)
- [Project Structure](#project-structure)
---
## What It Does
1. **Generate a story hook** The LLM creates an opening paragraph and three possible actions.
2. **Pause for user input** Using `questionary`, the script presents the options and waits for the player to choose one.
3. **Resume & finish** The graph resumes, feeding the chosen option back into the LLM, which writes a short ending that reflects the decision.
The whole flow is orchestrated by **LangGraph**, which manages state (`GameState`) and handles the custom `interrupt` node that triggers the humanintheloop pause.
---
## Prerequisites
| Component | Minimum Version | Notes |
|-----------|-----------------|-------|
| Python | 3.10+ | Tested on 3.12 |
| OpenAI API key | | Set as `OPENAI_API_KEY` environment variable or in a `.env` file. |
| LangGraph | Latest (pip install) | Handles the graph logic and checkpointing. |
| LangChainOpenAI | Latest | Provides the LLM wrapper (`ChatOpenAI`). |
| Questionary | Latest | For interactive console prompts. |
> **Optional** If you want to run locally without an OpenAI key, you can replace `ChatOpenAI` with a local model (e.g., Ollama) and adjust the import accordingly.
---
## Installation
```bash
# Clone the repo (or copy the files)
git clone https://github.com/your-username/interactive-adventure.git
cd interactive-adventure
# Create a virtual environment (recommended)
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
```
`requirements.txt` contains:
```text
langgraph>=0.1.0
langchain-openai>=0.2.0
questionary>=1.10.0
python-dotenv>=1.0.0 # optional, for .env support
```
---
## Running the Game
The entire game is contained in a single script: `game.py`.
```bash
# Make sure your OpenAI key is available:
export OPENAI_API_KEY="sk-..."
# Run the game
python game.py
```
If you prefer to use a `.env` file, create a file named `.env` in the project root with:
```dotenv
OPENAI_API_KEY=sk-...
```
The script will automatically load it via `python-dotenv`.
---
## Example Session
Below is a typical console interaction. The AI generates an opening and three actions; you pick one; the AI finishes.
```
$ python game.py
Welcome to the Interactive Adventure!
[Story Hook]
You find yourself in a dimly lit cavern, the air thick with damp stone. A faint glow emanates from a crystal embedded in the wall.
Choose your action:
1) Inspect the crystal closely.
2) Search for an exit.
3) Call out to see if anyone is nearby.
Your choice: 1
[Ending]
You reach out and touch the crystal. It hums, releasing a burst of light that reveals a hidden passage behind the stone wall. The adventure continues...
```
Feel free to experiment with different choices each run will produce a unique narrative!
---
## Project Structure
```text
interactive-adventure/
├── game.py # Main script containing LangGraph logic
├── requirements.txt
└── README.md
```
- **`game.py`** Defines `GameState`, the graph nodes (`generate_story`, `interrupt_node`, `finish_ending`), and runs the loop.
- **`requirements.txt`** Lists all Python dependencies.
---
Happy adventuring! 🚀