Tencent Cloud VectorDB
cloud.tencent.cn
- Free trial
- Linux
- Web
- API
What Tencent Cloud VectorDB is
Tencent Cloud VectorDB is a fully managed distributed database for storing, indexing, retrieving, and managing multidimensional embedding vectors. Its AI suite combines document parsing, information enrichment, vectorization, and retrieval, allowing uploaded source documents to become a knowledge base. Text can be converted into vectors during insertion, updates, and similarity searches, with embedding billed by token volume. Search supports dense and sparse vectors, metadata filtering, and hybrid result merging through RRF or weighted ranking. Standard indexes include FLAT, HNSW, and IVF families; the capacity-enhanced edition adds DISK_FLAT disk indexes 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. The service runs in the cloud and offers API, Linux, and web access, plus Python, Java, and Go SDKs. Tencent states that one index can support up to hundreds of billions of vectors, with million-level QPS and millisecond query latency. Pricing starts at 344 CNY/mo, and a free test instance lasts one month.
Who it suits
VectorDB suits teams building knowledge bases, recommendation systems, or text and image retrieval applications. It is also relevant to developers using RAG workflows, vector search, and Tencent’s SDKs or security controls.
Good to know, and what to watch
- Managed database for multidimensional vectors
- Supports dense, sparse, and hybrid search
- Offers Python, Java, and Go SDKs
- Supports metadata filtering
- One-month free test instance
- Free instance is limited to one month
- AI Suite similarity search accepts one text input
- Embedding usage is billed by token volume
- Paid plans start at 344 CNY/mo
Plans
Every plan and price高可用版(存储型)
高可用版(标准型)
高可用版(计算型)
The verdict
Tencent Cloud VectorDB combines vector storage, indexing, retrieval, and document-to-knowledge-base tooling for cloud applications. Its broad index and search options suit RAG and retrieval workloads, while usage limits and token billing need review.
What the maker publishes
- Availability
- Tencent states an availability SLA of at least 99.97% for three-availability-zone high-availability deployments and 99.95% for two-zone deployments. source
- Embedding
- Embedding can automatically convert input text into vectors during insertion, updates, and similarity searches; usage is billed by token volume. source
- Free test instance
- Tencent describes a free test instance deployed on one node in one availability zone, limited to one month; continued use requires purchasing another instance. source
- Hybrid search
- Hybrid search combines dense and sparse vector retrieval and supports RRF and weighted result merging. source
- Indexes
- The standard edition supports FLAT, HNSW, and IVF index families, while the capacity-enhanced edition supports DISK_FLAT disk indexes from version 3.0. source
- Limits
- The AI suite documentation says AI Suite similarity search accepts only one text input at a time, while regular vector or Embedding searches can accept up to 20 inputs. source
- Model integrations
- Tencent documents RAG examples using VectorDB with DeepSeek, Hunyuan, and Baichuan models. source
- Product
- Tencent Cloud VectorDB is a fully managed, self-developed distributed database for storing, indexing, retrieving, and managing multidimensional embedding vectors. source
- RAG suite
- Its AI suite combines document parsing, information enrichment, vectorization, and retrieval so users can upload source documents to build a knowledge base. source
- Scale
- The product page states that one index supports up to hundreds of billions of vectors, with up to million-level QPS and millisecond query latency. source
- SDKs
- Tencent provides Python, Java, and Go SDKs, and its connection guide specifies minimum versions of Python 3.6, Java 8, and Go 1.15. source
- Security
- The product documentation describes account and API-key authentication, VPC isolation, security-group traffic controls, and CAM-based resource permissions. source
- Support
- Tencent directs product questions to online customer service or support tickets and also points users to its developer community. source
- Use cases
- Tencent lists LLM knowledge bases, recommendation systems, and text or image retrieval as application scenarios. source
Checked against the maker's pages on 9 Oct 2026.