Auto Gen-AI App Generator with the Power of Llama 2
Project description
DemoGPT: Auto Gen-AI App Generator with the Power of Llama 2
⚡ With just a prompt, you can create interactive Streamlit apps via 🦜️🔗 LangChain's transformative capabilities & Llama 2.⚡
⭐ Star History
⭐ Consider starring us if you're using DemoGPT so more people hear about us!
🔥 Demo
For quick demo, you can visit our website
https://github.com/melih-unsal/DemoGPT/assets/34304254/8991e296-b6fe-4817-bd08-4dab6d13020d
📚 Documentation
See our documentation site here for full how-to docs and guidelines
⚡ The new release with the power of Llama 2 is within a week. ⚡
📦 Using DemoGPT Package
The DemoGPT package is now available and can be installed using pip. Run the following command to install the package:
pip install demogpt
To use the DemoGPT application, simply type "demogpt" into your terminal:
demogpt
📑 Table of Contents
📌 Introduction
Welcome to DemoGPT, a ground-breaking open-source initiative aimed at optimizing and democratizing the development of Large Language Model (LLM) based applications.
At the heart of DemoGPT lies the potent GPT-3.5-turbo & Llama 2, which enables the auto-generation of LangChain code. This process is fueled by a unique self-refining strategy that seamlessly blends document understanding from the LangChain documentation tree with user prompts. The outcome is a piece of code that doesn't just work, but is inherently robust, adhering to best coding practices while maintaining a deep-rooted alignment with the LangChain library.
The LangChain code, once generated, is not a final product but an intermediate stage. The code is further transformed into a user-friendly Streamlit application, adding an interactive layer to the logic produced.
Alongside this, DemoGPT embraces an iterative development process, wherein each code segment is individually tested. This approach, coupled with the self-refining strategy, enables an efficient and error-minimized workflow, pushing the envelope in traditional code development.
By making software development accessible through simple prompts, DemoGPT is laying the groundwork for a paradigm shift in how we create, refine, and customize LLM-based applications. The end goal is a broader, more inclusive ecosystem where users, regardless of their coding proficiency, can contribute to the continuous evolution of products.
In summary, DemoGPT isn't just a project; it is a forward-thinking approach, redefining the boundaries of LLM-based application development.
In the next release, we are gonna add Llama 2 inside of DemoGPT to make the whole system runnable completely locally.
⚙️ Architecture
DemoGPT Architecture
🔧 Installation
For the Package Version
You can install the DemoGPT package by running the following command:
pip install demogpt
For the Source Code Version
- Clone the repository:
git clone https://github.com/melih-unsal/DemoGPT.git
- Navigate into the project directory:
cd DemoGPT
- Install the necessary dependencies:
pip install -r requirements.txt
🎮 Usage
For the Package Version
Once the DemoGPT package is installed, you can use it by running the following command in your terminal:
demogpt
For the Source Code Version
If you have cloned the repository and wish to run the source code version, you can use DemoGPT by running the following command:
streamlit run src/prompt_based/app.py
If you want to run the more advanced but the experimental version of DemoGPT, you can use the following command:
streamlit run src/plan/app.py
🤝 Contribute
Contributions to the DemoGPT project are welcomed! Whether you're fixing bugs, improving the documentation, or proposing new features, your efforts are highly appreciated. Please check the open issues before starting any work.
Please read
CONTRIBUTING
for details on ourCODE OF CONDUCT
, and the process for submitting pull requests to us.
📜 License
DemoGPT is an open-source project licensed under MIT License.
For any issues, questions, or comments, please feel free to contact us or open an issue. We appreciate your feedback to make DemoGPT better.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.