The Lightning ⚡️ AI Style Guide Assistant is a specialized adaptation of the Lightning Chatbot, designed to assist in maintaining consistency and accuracy in code. Powered by Groq LPUs (Language Processing Units), it offers one of the fastest inference speeds on the market as of April 2024.
- ⚡ Real-time style and grammar recommendations powered by Groq LPUs.
- 📘 Supports custom style guide integration for personalized recommendations.
- 📝 Lightning fast style guide rewrites and code translation
- 🌐 Deploy easily using the Streamlit web framework.
- 🦙 Llama3-70B-8192: Experience high-end performance with this large-scale model, ideal for complex language tasks and deep learning insights.
- 🦙 Llama3-8B-8192: Harness robust capabilities with this more accessible version of Llama3, perfect for a wide range of AI applications.
- 🌟 Mixtral-8x7B-32768: Leverage the power of ensemble modeling with Mixtral's extensive capacity for nuanced understanding and response generation.
- 🦙 Llama2-70B-4096: Utilize the proven effectiveness of Llama2 for comprehensive language processing and application development.
- 💎 Gemma-7B-IT: Explore specialized interactions and tech-focused solutions with Gemma, tailored for IT and technical content.
-
Clone the repository:
git clone https://github.com/MaxMLang/lightningAI-styleguide-assistant.git
-
Navigate to the project directory:
cd lightningAI-styleguide-assistant
-
Install the required dependencies:
pip install -r requirements.txt
-
Configure the Groq API key:
- Create a
.env
file in the project directory. - Add the following line, replacing
your_api_key
with your actual Groq API key:GROQ_API_KEY=your_api_key
- Create a
-
Launch the assistant:
streamlit run app.py
-
Open the provided URL in your browser to access the AI Style Guide Assistant interface.
- Select your custom style guide settings from the sidebar.
- Type a block of text into the input field and submit.
- Receive style and grammar recommendations based on your settings.
- Apply or dismiss suggestions and see the edits in real-time.
- Continue refining your text with further input and revisions.
This project is licensed under the MIT License.