The 'golden partner' of large models is here! Tencent Cloud officially releases AI native vector database, providing 1 billion-level vector retrieval capabilities

On July 4, Tencent Cloud officially released the AI ​​native (AI Native) vector database Tencent Cloud VectorDB. This database can be widely used in scenarios such as large model training, inference, and knowledge base supplementation. It is the first vector database in China that provides full life cycle AI from the access layer, computing layer, to storage layer.

Known in the industry as the "hippocampus" of large models, vector databases are specifically designed to store and query vector data. According to reports, Tencent Cloud's vector database supports up to 1 billion vector retrieval scale, with latency controlled at the millisecond level. Compared with traditional stand-alone plug-in databases, the retrieval scale is increased by 10 times, and it also has a peak query capacity of one million levels per second (QPS).

Tencent Cloud defines AI Native vector database

With the advent of the big model era, embracing big models has become a necessity for enterprises.

By vectorizing data for storage, vector databases can significantly improve efficiency and reduce costs. It can solve the problems of high pre-training costs for large models, no "long-term memory", insufficient knowledge updates, and complex prompt word engineering. It breaks through the time and space limitations of large models and accelerates the implementation of large models in industry scenarios.

Statistics show that using Tencent Cloud Vector Database for classification, deduplication and cleaning of large model pre-training data can achieve a 10 times improvement in efficiency compared to traditional methods. If the vector database is used as an external knowledge base for model reasoning, Then the cost can be reduced by 2-4 orders of magnitude.

It is worth noting that Tencent Cloud has redefined the development paradigm of AI Native and provided a comprehensive AI solution for the access layer, computing layer, and storage layer, enabling users to use vector databases throughout the entire life cycle. Apply to AI capabilities.

Specifically, at the access layer, Tencent Cloud Vector Database supports the input of natural language text, adopts the "scalar vector" query method, supports full memory indexing, and supports up to one million queries per second (QPS). ; At the computing layer, the AI ​​Native development paradigm can realize full-scale data AI calculations, and one-stop solves problems such as text segmentation (segmentation) and vectorization (embedding) when enterprises build private domain knowledge bases; at the storage layer, Tencent Cloud Vector database supports intelligent storage distribution of data, helping enterprises reduce storage costs by 50%.

It used to take about a month for enterprises to access a large model. After using Tencent Cloud Vector Database, it can be completed in 3 days, which greatly reduces the enterprise's access costs.

It is understood that the vectorization capability (embedding) of Tencent Cloud Vector Database has been recognized by authoritative organizations many times. In 2021, it topped the MS MARCO list and related results have been published in the NLP Summit ACL.

Luo Yun, deputy general manager of Tencent Cloud Database, said that the era of AI Native has arrived. "Vector database large model data" and the three will produce a "flywheel effect" and jointly help enterprises enter the AI ​​Native era. )era.

Tencent Cloud Vector Database helps data access efficiency increase by 10 times

Tencent Cloud Vector Database is based on Tencent Group’s vector engine (OLAMA), which processes hundreds of billions of searches every day. After practice in Tencent’s internal massive scenarios, the efficiency of data access to AI is also 10 times higher than that of traditional solutions, and the operational stability is as high as 99.99%, it has been used in more than 30 national-level products such as Tencent Video, QQ Browser, QQ Music, etc.

Tencent Cloud vector database can effectively help products improve operational efficiency. Data shows that after using Tencent Cloud Vector Database, the per capita listening time of QQ Music increased by 3.2%, the per capita effective exposure time of Tencent Video increased by 1.74%, and the cost of QQ Browser decreased by 37.9%.

Take the application of Tencent Video as an example. Images, audio, title text and other contents in the video library use Tencent Cloud vector database. The average monthly retrieval and calculation volume is up to 20 billion times, which effectively meets the needs of copyright protection and original identification. , similarity retrieval and other scenario requirements.

Large model accelerated vector databases have entered a period of rapid development. According to Northeast Securities’ forecast, the global vector database market is expected to reach US$50 billion by 2030, and the domestic vector database market is expected to exceed RMB 60 billion.

Vector databases can help enterprises use large models more efficiently and conveniently to maximize the value of data. With the continuous development and popularization of large models, AI Native vector databases will become the standard for enterprise data processing.

The above is the detailed content of The 'golden partner' of large models is here! Tencent Cloud officially releases AI native vector database, providing 1 billion-level vector retrieval capabilities. For more information, please follow other related articles on the PHP Chinese website!