Network Security Internet Technology Development Database Servers Mobile Phone Android Software Apple Software Computer Software News IT Information

In addition to Weibo, there is also WeChat

Please pay attention

WeChat public account

Shulou

Havenask, an open source search engine developed by Ali, has been used in Taobao, Gaode, ele.me, etc.

2025-01-31 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >

Share

Shulou(Shulou.com)11/24 Report--

Thanks to CTOnews.com netizen StarDevOps for the clue delivery! CTOnews.com news on December 14, Alibaba opened up the self-developed search engine Havenask, and the project file has been launched in GitHub.

According to the warehouse, Havenask is a search engine developed by Alibaba Group and a large-scale distributed retrieval system widely used within Alibaba. It supports the search business of the entire Alibaba Group, including Taobao, Tmall, Cainiao, Gao de, ele.me and globalization, and provides users with high-performance, low-cost and easy-to-use search services.

At the same time, Havenask has flexible customization and development capabilities, supports rapid iteration of algorithms, helps customers and developers tailor-made intelligent search services suitable for their own business, and promotes business growth.

According to reports, the core competencies and advantages of Havenask are as follows:

Extreme engineering performance: support hundreds of billions of real-time data retrieval, millions of QPS queries, millions of TPS writes, millisecond query latency and second data updates.

The underlying construction of C++: higher guarantee for performance, memory and stability.

SQL query support: support SQL syntax convenient query, query experience is more friendly.

Rich plug-in mechanism: supports all kinds of business plug-ins with strong expansibility.

Support graphical development: to achieve the algorithm minute-level fast iteration, rich customization ability, excellent support effect in the new generation of intelligent retrieval scenarios.

Support vector retrieval: multimodal search can be implemented in cooperation with plug-ins to meet the needs of building search services in more scenarios (to be released).

CTOnews.com learned that the underlying layer of the engine is mainly written in C++, and uses a small amount of Python language, needs to run in a Docker container, the machine memory needs to be greater than 10GB CPU, the CPU needs to be larger than 2 cores, and the disk size is larger than 50GB.

GitHub page: click here to view

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.

Views: 0

*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.

Share To

IT Information

Wechat

© 2024 shulou.com SLNews company. All rights reserved.

12
Report