title | emoji | colorFrom | colorTo | sdk | sdk_version | app_file | pinned | license | short_description |
---|---|---|---|---|---|---|---|---|---|
AWS Guard Bot |
🚀 |
blue |
red |
gradio |
4.26.0 |
app.py |
false |
mit |
Experiment on langchain with NeMo Guardrails |
The application showcases the integration Langchain with documents loaded and Nemo Guardrails. By combining these technologies, the application ensures advanced safety features and effective mitigation's, enhancing the overall security and reliability of the chatbot system.
Note: It has only minimal guards added from NeMo for demo
Without Guardrails |
---|
With Guardrails |
---|
git clone https://github.com/SSK-14/chatbot-guardrails.git
- Create virtual environment
pip3 install env
python3 -m venv env
source env/bin/activate
- Install required libraries
pip3 install -r requirements.txt
OPENAI_API_KEY = "Your openai API key"
or
GOOGLE_API_KEY = "Your Gemini API key"
- Keep you data or documentations in the knowledge_base folder
- Get an Gemini API key or OpenAI API key
- Update the constants & vectorstore client in
vectorstore.py
- Run the command -
python vectorstore.py
gradio app.py
chatbot-guardrails/
│
├── config // Contains all files for Guardrails
├── knowledge_base // Documents need for the chatbot context
├── app.py // Main file to run
├── create_index.py // Run this to create vectorstore
├── README.md
└── requirements.txt
Contributions to this project are welcome! If you find any issues or have suggestions for improvement, please open an issue or submit a pull request on the project's GitHub repository.
This project is licensed under the MIT License. Feel free to use, modify, and distribute the code as per the terms of the license.