Introduction to Langup AI Project
Langup is a cutting-edge project in the evolving realm of Artificial General Intelligence (AGI), aiming to serve as a versatile robotic assistant. The project seamlessly integrates large language models (LLM) with chatbots to provide a wide range of functionalities and interactions.
Installation
Langup is compatible with Python environments of version 3.8 and higher. It offers two installation methods:
-
Via pip: Install the package directly using the following command:
pip install langup==0.0.10
-
Using Python Virtual Environment: This method is recommended for isolated setups.
git clone https://github.com/jiran214/langup-ai.git cd langup-ai/ python -m pip install --upgrade pip python -m pip install -r requirements.txt
Quick Start
Once installed, users can easily begin using Langup by creating a new Python file and implementing the provided examples. For method two installation, new files can be created within the src/
directory. Sample codes and additional examples are available under src/examples
.
Bilibili Live Streaming Digital Persona
Langup can be utilized to create a persona for interacting with users in Bilibili live streams. The system is designed to engage with users interactively, encouraging engaging dialogues. Adjust settings such as the room ID, OpenAI API key, and other filters to personalize the experience.
Video Comment Reply Bot
A bot can be set up to automatically respond to tagged comments in video content on Bilibili, delivering summaries or comments based on video content themes. It uses signal words to trigger replies and can be customized in terms of credentials, reply intervals, and model preferences.
Bilibili Private Messaging Bot
This feature allows for a chatbot to work through private messages on Bilibili. Users configure the chatbot with a system description and it listens for text-based events, enabling it to assist users directly through messages.
Real-time Voice Interaction Assistant
Langup empowers real-time voice-based interactions, leveraging speech recognition technology to facilitate instant communication. The assistant can be set to listen to spoken input and respond dynamically, serving as an AI helper.
Console Interaction Assistant
Through the console, this assistant listens to user inputs and provides text-based responses, functioning effectively as an AI assistant for terminal-based interactions.
Things to Keep in Mind
- The API key can be auto-detected from environment variables.
- In regions where direct access to services like OpenAI is restricted, using a proxy or setting
openai_api_base
globally is recommended for seamless operation. - Authentication is necessary for Bilibili-based applications; credentials can be fetched via browser cookies or read directly from the
.env
file.
Architectural Design
The architecture of the Langup project is outlined in its design documentation, though some modules remain under development.
Future Developments (To-Do List)
Langup has an extensive roadmap of features, some of which are already implemented, such as basic functions for Vtuber and concurrent handling, while others are still being developed.
Important Notes
- Users should adhere to ethical guidelines when employing this library.
- The project relies on several open-source libraries like Langchain, Bilibili API, and Bcut-ASR.
Langup aims to be an advanced solution in the AGI space, bringing innovative features to interactive AI assistants. Users are encouraged to explore the project further and contribute to its ongoing development.