Tencent Cloud VectorDB

What Tencent Cloud VectorDB is

Tencent Cloud VectorDB is a cloud-managed distributed database for storing, indexing, retrieving, and managing multidimensional embedding vectors. It is available through API, Linux, and web access, with Python, Java, and Go SDKs. Tencent says one index can hold up to hundreds of billions of vectors, support million-level QPS, and return queries with millisecond latency. Its RAG suite combines document parsing, information enrichment, vectorization, and retrieval, allowing uploaded documents to become a knowledge base. Text embedding can run during insertion, updates, and similarity searches, with usage billed by token volume. Search supports dense and sparse vectors, metadata filtering, and hybrid retrieval with RRF or weighted result merging. Standard indexes include FLAT, HNSW, and IVF families; capacity-enhanced deployments add DISK_FLAT from version 3.0. Tencent lists LLM knowledge bases, recommendation systems, and text or image retrieval as use cases, with RAG examples using DeepSeek, Hunyuan, and Baichuan.