feat: updated tictactoe agent README
This commit is contained in:
ShubhamSaboo
parent
8feb6b0c5d
commit
bae1526a4a
2 changed files with 27 additions and 39 deletions
|
|
@ -1,30 +1,32 @@
|
|||
# AI vs AI Tic-Tac-Toe Game 🎮
|
||||
# 🎮 Agent X vs Agent O: Tic-Tac-Toe Game
|
||||
|
||||
An interactive Tic-Tac-Toe game where two AI agents powered by different language models compete against each other built on phidata Agent Framework and Streamlit as UI. Watch as GPT-4O battles against either DeepSeek V3 or Google's Gemini 1.5 Flash in this classic game!
|
||||
An interactive Tic-Tac-Toe game where two AI agents powered by different language models compete against each other built on phidata Agent Framework and Streamlit as UI. Watch as GPT-4O battles against either DeepSeek V3 or Google's Gemini 1.5 Flash in this classic game.
|
||||
|
||||
## Demo
|
||||
## Features
|
||||
|
||||
### Multi-Agent System
|
||||
- Player X: OpenAI's Gemini Flash 2.0
|
||||
- Player O: DeepSeek v3
|
||||
- Judge: GPT-4o for game outcome validation
|
||||
|
||||
https://github.com/user-attachments/assets/071597e8-0f06-4cb0-bd19-dccf229b7317
|
||||
### Interactive Interface
|
||||
- Real-time game board visualization
|
||||
- Move-by-move analysis
|
||||
- Agent response tracking
|
||||
- Clear game status updates
|
||||
|
||||
### Strategic Gameplay
|
||||
- AI-powered move decisions
|
||||
- Winning strategy implementation
|
||||
- Opponent move blocking
|
||||
- Victory condition monitoring
|
||||
|
||||
|
||||
## Features 🌟
|
||||
|
||||
- Player X: Powered by OpenAI's GPT-4o (o1 models as api is yet to roll out for tier)
|
||||
- Player O: Choice between DeepSeek AI or Google's Gemini
|
||||
- Interactive game board using Streamlit
|
||||
- Real-time move visualization
|
||||
- AI Judge to determine game outcomes
|
||||
- Clean and intuitive user interface
|
||||
|
||||
## Prerequisites 📋
|
||||
|
||||
## Prerequisites
|
||||
- Python 3.8+
|
||||
- OpenAI API key
|
||||
- Either DeepSeek API key or Google API key (for Player O)
|
||||
|
||||
## How to Run 🚀
|
||||
## How to Run
|
||||
|
||||
1. **Setup Environment**
|
||||
```bash
|
||||
|
|
@ -52,16 +54,16 @@ https://github.com/user-attachments/assets/071597e8-0f06-4cb0-bd19-dccf229b7317
|
|||
- Watch as the AI agents battle it out!
|
||||
- Monitor the game progress and final results
|
||||
|
||||
## Game Components 🎯
|
||||
## Game Components
|
||||
|
||||
- **Game Board**
|
||||
- 3x3 interactive grid
|
||||
- Real-time move visualization
|
||||
- Clear symbol placement (X/O)
|
||||
|
||||
- **AI Players**
|
||||
- Player X (GPT-4o): Strategic offensive moves
|
||||
- Player O (DeepSeek/Gemini): Defensive countermoves since this agent started later
|
||||
- **AI Agent Players**
|
||||
- Player X: Strategic offensive moves
|
||||
- Player O: Defensive countermoves since this agent started later
|
||||
- AI Judge: Game outcome validation
|
||||
|
||||
- **Game Flow**
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@ from phi.model.deepseek import DeepSeekChat
|
|||
from phi.model.google import Gemini
|
||||
|
||||
# Streamlit App Title
|
||||
st.title("🤖 Tic-Tac-Toe: AI vs AI")
|
||||
st.title("🎮 Agent X vs Agent O: Tic-Tac-Toe Game")
|
||||
|
||||
# Enhanced Welcome Message
|
||||
with st.chat_message("assistant"):
|
||||
|
|
@ -16,8 +16,8 @@ with st.chat_message("assistant"):
|
|||
Here's what you need to know:
|
||||
""")
|
||||
st.info("""
|
||||
- **Player X**: Powered by OpenAI's GPT-4.
|
||||
- **Player O**: Powered by DeepSeek's AI or Google's Gemini (if DeepSeek API key is not provided).
|
||||
- **Player X**: Powered by Google's Gemini Flash 2.0.
|
||||
- **Player O**: Powered by DeepSeek v3.
|
||||
- **How to Play**: Enter your API keys in the sidebar, click **Start Game**, and watch the AI battle it out!
|
||||
- **Goal**: The first player to get three of their symbols in a row (horizontally, vertically, or diagonally) wins.
|
||||
- **Draw**: If the board fills up without a winner, the game ends in a draw.
|
||||
|
|
@ -106,7 +106,7 @@ if google_api_key:
|
|||
if 'openai_api_key' in st.session_state:
|
||||
player_x = Agent(
|
||||
name="Player X",
|
||||
model=OpenAIChat(id="gpt-4o", temperature=0.1, api_key=st.session_state.openai_api_key),
|
||||
model=Gemini(id="gemini-2.0-flash-exp", api_key=st.session_state.google_api_key),
|
||||
instructions=[
|
||||
"You are a Tic-Tac-Toe player using the symbol 'X'.",
|
||||
"Your opponent is using the symbol 'O'. Block their potential winning moves.",
|
||||
|
|
@ -133,20 +133,6 @@ if 'openai_api_key' in st.session_state:
|
|||
],
|
||||
markdown=True,
|
||||
)
|
||||
elif 'google_api_key' in st.session_state:
|
||||
player_o = Agent(
|
||||
name="Player O",
|
||||
model=Gemini(id="gemini-1.5-flash", api_key=st.session_state.google_api_key),
|
||||
instructions=[
|
||||
"You are a Tic-Tac-Toe player using the symbol 'O'.",
|
||||
"Your opponent is using the symbol 'X'. Block their potential winning moves.",
|
||||
"Make your move in the format 'row, col' based on the current board state.",
|
||||
"Strategize to win by placing your symbol in a way that blocks your opponent from forming a straight line.",
|
||||
"Do not include any explanations or extra text. Only provide the move.",
|
||||
"Row and column indices start from 0.",
|
||||
],
|
||||
markdown=True,
|
||||
)
|
||||
else:
|
||||
st.warning("Please provide either a DeepSeek API key or a Google API key for Player O.")
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue