English | 简体中文
superduper is an AI application development and database integration platform for developers and enterprises, which can simplify the interaction between AI models and various databases such as Qdrant and MySQL. Aim to lower the threshold for AI application implementation, provide a modular and scalable toolchain, and help quickly achieve scenarios such as enhanced generation of RAG retrieval and intelligent question answering. This product provides an out-of-the-box superduper based on the Huawei Cloud EulerOS 2.0 64-bit system of Kunpeng servers.
- Seamless integration of AI models and databases: Support the direct insertion of AI models such as big language models, embedding models, classifiers, etc. into existing databases (such as MongoDB, SQLite) to achieve automatic data expansion and intelligent enhancement
- Dynamic Vector Storage and Retrieval: Automatically call the model to generate embedding vectors and store them during data writing, with out of box support for semantic search, similarity matching, and vectorized queries, without the need to build additional synchronization pipelines
The open-source image product Superduper Intelligent Data Fusion Platform provided by this project has pre-installed the the 0.7.0 version of superduper and its related runtime environment, and provides deployment templates. Come and refer to the usage guide to easily start an efficient "out-of-the-box" experience!
System requirements are as follows:
- CPU: 2vCPUs or higher
- RAM: 4GB or larger
- Disk: At least 40GB
Register a Huawei account and activate Huawei Cloud
| Image Specification | Feature Description | Remarks |
|---|---|---|
| superduper-0.7.0-kunpeng | Installed and deployed based on Kunpeng servers + Huawei Cloud EulerOS 2.0 64-bit |
- For more questions, you can contact us through issues or the service support of the specified product in the Huawei Cloud Marketplace.
- For other open-source images, please refer to open-source-image-repos.
- Fork this repository and submit a merge request.
- Synchronously update README.md based on your open-source image information.