An chatbot project on JTCG
This is a chatbot project developed for JTCG. The chatbot is designed to provide automated conversational capabilities for customer support.
- Multi Agents System: Understands and responds to user queries with multi-Agents
- Multi-turn Conversations: Maintains context across multiple interactions
- Customizable Responses: Easy to configure and extend response patterns
- Reasoning and Flexible: Give you the answers with the reasons and can generate flexible content
Before you begin, ensure you have the following installed:
- Miniconda
- Python 3.11+ (or appropriate language version)
- poetry
- Git
-
Clone the repository
git clone https://github.com/smalldan1022/chatbot.git cd chatbot -
Create a virtual environment (recommended)
conda create -n YOUR_ENV_NAME python=3.11
-
Install dependencies
poetry install
-
Set up environment variables
# Set up your own OpenAI API Key # at the root of the folder vim .env (Inside the .env) OPENAI_API_KEY=xxxxxxx
-
Start the application
# interactive mode chatbot -i # interactive mode without other display chatbot -d -i
-
Access the chatbot
# or at the root folder python src/chatbot/main.py
# Example of using the chatbot
from chatbot import ChatBot
chatbot = ChatBot()
response = chatbot.process_single_user_message("Hello, how are you?")
print(response)-
The Agent
The agent can be configured through the
config.yamlfiles: -
The Prompt
The prompt can be configured through the
config.yamlfiles: -
The Orchestrator Route
The orchestrator route can be configured through the
config.yamlfiles:
- Follow PEP 8 style guide for Python code
- Write unit tests for new features
- Update documentation as needed
- Keep commits atomic and well-described
This project is licensed under the MIT License - see the LICENSE file for details.
smalldan1022
- GitHub: @smalldan1022
- Email: asign1022@gmail.com
- Thanks for JTCG team's project support
⭐ If you find this project useful, please consider giving it a star on GitHub!