MindSDK
MindSDK delivers various AI software development kits (SDKs) accelerated by Ascend AI Processors and provides simplified APIs to accelerate the development of high-performance AI applications for thousands of industries.
- Release Notes
This document describes the MindSDK version information, including the software and hardware mapping and compatibility.
Visual Analysis
Feature Retrieval
- Index SDK
It is an Ascend NPU heterogeneous retrieval acceleration framework that is built on Faiss, providing high-performance retrieval for massive data in high-dimensional space. It is developed based on TBE operators and the C++ language that is consistent with Faiss and supports Arm and x86_64 platforms.
Search and Recommendation
- Rec SDK
As an SDK for search, recommendation, and advertising services in the Internet market, it provides a framework for these services based on the Ascend platform to meet related model training requirements, thus supporting large-scale search-recommendation-advertising scenarios and facilitating efficient training of search-recommendation-advertising models.
Knowledge Augmentation
- RAG SDK
It is a development kit for knowledge augmentation of large language models (LLMs). To address issues such as slow knowledge updates and limited answering abilities in vertical industries, it offers features such as domain-specific tuning, augmented generation, and knowledge management for LLMs' knowledge repositories. These capabilities enable users to create dedicated question-answering (QA) systems with high performance and accuracy.