Tencent Cloud Vector Database SDK announced the official open source . According to the introduction, the Python SDK and Java SDK of Tencent Cloud VectorDB are based on the database design model, follow the HTTP protocol, and encapsulate the API into easy-to-use Python and Java functions or classes, providing developers with more friendly, More convenient database usage and management.
Tencent Cloud VectorDB is a fully managed self-developed enterprise-level distributed database service, dedicated to storing, retrieving, and analyzing multi-dimensional vector data, and supports multiple index types and similarity calculation methods. This database can not only provide an external knowledge base for large models and improve the accuracy of large model answers, but can also be widely used in AI fields such as recommendation systems, NLP services, computer vision, and intelligent customer service.
product capability
-
high performance
A single index supports a billion-level vector data scale, and can support million-level QPS and millisecond-level query latency.
-
high availability
Provides multi-copy high-availability features, and its multi-availability zone and three-node architecture availability can reach 99.99%, which significantly improves system reliability and fault tolerance, ensuring that the database can still operate normally in the face of node failures and load changes.
-
massive
Supports horizontal expansion, and a single instance can support millions of QPS, easily meeting the vector storage and retrieval requirements in AI scenarios.
-
low cost
Just follow the instructions on the management console and operate a few simple steps to quickly create a vector database instance. The whole process of platform hosting does not require any installation, deployment, and operation and maintenance operations, effectively reducing machine costs, operation and maintenance costs, and labor costs. overhead.
-
easy to use
Rich vector retrieval capabilities, support for dynamic schemas, and support for flexible expansion of scalar fields when writing data, without the need to pre-define all fields. A variety of vector indexing algorithms, including mainstream methods such as FLAT, HNSW, and IVF series, and rich similarity calculation methods, which can cover the application needs of various scenarios. Users can quickly operate the database through the HTTP API interface, and the development efficiency is high. At the same time, the console provides comprehensive data management and monitoring capabilities, and the operation is simple and convenient.
-
Stable and reliable
The vector database is derived from OLAMA, a vector search engine developed by Tencent Group. Nearly 40 business lines are running stably, and the average daily search requests are as high as 100 billion times. Service continuity and stability are guaranteed.