SkywardAI is an open-source community dedicated to advancing the field of Retrieval-Augmented Generation (RAG) technology. It is created by a group of passionate students from the RMIT University, Melbourne, Australia. Our goal is to provide the free, real open-source RAG framework and data analysis solutions that enable anyone to democratize and run AI on consumer-grade hardware. And also support cloud-native deployment. The community is inspired by an open-source OpenAI alternative API LocalAI.
WE are decicated to providing an Open-Source Retrieval-Augmented Generation (RAG) Framework that empowers you build, customize, and deploy RAG solutions for your specific needs.
Our open-source framework provides the building blocks you need to develop and implement RAG models for live chat, including modules for data retrieval, knowledge base integration, response generation, and conversation management.
Gain valuable insights into your live chat interactions with our data analysis tools. Analyze user queries, track response effectiveness, and identify areas for improvement.
Share your experiences, collaborate on projects, and contribute to the advancement of open-source RAG technology.
Our mission is to make RAG accessible and beneficial for everyone. By providing an open-source framework and data analysis tools, we aim to empower developers and businesses to:
Tailor your RAG models to your specific domain and use case, ensuring optimal performance and relevance.
Analyze chat data to identify trends, understand user behavior, and improve customer satisfaction.
Share your knowledge, collaborate on projects, and help advance the state-of-the-art in RAG technology.
Our vision is to create a thriving community of developers and enthusiasts who are passionate about RAG technology. By fostering collaboration, innovation, and knowledge sharing, we aim to:
Promote the use of RAG models in a wide range of applications, from customer support to education to entertainment.
Provide the tools, resources, and support developers need to create powerful and effective RAG models.
Create a welcoming and supportive community where members can learn, grow, and contribute to the advancement of RAG technology.
We welcome contributions from the community! If you're interested in joining us and contributing to our projects, here's how you can get involved:
- Fork the repository and clone it to your local machine.
- Create a new branch for your feature or bug fix.
- Make your changes, following our coding guidelines.
- Commit and push your changes to your forked repository.
- Open a pull request, and we'll review your contribution.
Please check out our Contribution Guidelines for more details.
Want to learn more about our projects? Here are some helpful resources:
Let's build something awesome together! 🎉