Tencent Cloud VectorDB

Spec sheet

Product

Tencent Cloud VectorDB is a fully managed, self-developed distributed database for storing, indexing, retrieving, and managing multidimensional embedding vectors.Read 9 Oct 2026 · cloud.tencent.cn

Security

The product documentation describes account and API-key authentication, VPC isolation, security-group traffic controls, and CAM-based resource permissions.Read 9 Oct 2026 · cloud.tencent.cn

Support

Tencent directs product questions to online customer service or support tickets and also points users to its developer community.Read 9 Oct 2026 · cloud.tencent.cn

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.Read 9 Oct 2026 · cloud.tencent.cn

Embedding

Embedding can automatically convert input text into vectors during insertion, updates, and similarity searches; usage is billed by token volume.Read 9 Oct 2026 · cloud.tencent.cn

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.Read 9 Oct 2026 · cloud.tencent.cn

Hybrid search

Hybrid search combines dense and sparse vector retrieval and supports RRF and weighted result merging.Read 9 Oct 2026 · cloud.tencent.com

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.Read 9 Oct 2026 · cloud.tencent.cn

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.Read 9 Oct 2026 · cloud.tencent.cn

Model integrations

Tencent documents RAG examples using VectorDB with DeepSeek, Hunyuan, and Baichuan models.Read 9 Oct 2026 · cloud.tencent.cn

RAG suite

Its AI suite combines document parsing, information enrichment, vectorization, and retrieval so users can upload source documents to build a knowledge base.Read 9 Oct 2026 · cloud.tencent.cn

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.Read 9 Oct 2026 · cloud.tencent.cn

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.Read 9 Oct 2026 · cloud.tencent.cn

Use cases

Tencent lists LLM knowledge bases, recommendation systems, and text or image retrieval as application scenarios.Read 9 Oct 2026 · cloud.tencent.cn

Plans and prices

Every Tencent Cloud VectorDB plan and price →

Where Specifiction places it

• Vector Databases#12 of 277.9