Skip to main content

V1.0.0

Version information​

  • Release date: November 14, 2025

  • Version: V1.0.0

  • RPM version: seekdb-1.0.0.0-100000262025111218

About this release​

OceanBase seekdb (referred to as seekdb) is an AI-native search database. It unifies relational, vector, text, JSON and GIS in a single engine, enabling hybrid search and in-database AI workflows.

Product architecture​

seekdb-arch

  • Deployment modes: seekdb supports both embedded and client/server deployments. The embedded mode allows seamless integration into Python applications, making it especially convenient for individual developers.

  • Multi-model data and indexing layer: seekdb accommodates a wide range of data types, including vectors, text, JSON, and GIS, and provides robust indexing capabilities. It features HNSW/IVF vector indexes and quantization algorithms, full-text indexes based on BM25 relevance that support various tokenizers and query modes, hybrid indexes for mixed search scenarios, JSON indexes for metadata searches, as well as primary, secondary, and GIS indexes.

  • Multi-model compute layer for hybrid workloads: seekdb enables hybrid searches across vectors, full-text, and scalar conditions, enhancing the accuracy of query results in Retrieval-Augmented Generation (RAG) scenarios. It offers built-in AI function capabilities for real-time inference within the database. seekdb supports full ACID transactions and multi-version concurrency control (MVCC), along with a query optimizer designed for hybrid workloads, an adaptive execution engine, and flexible PL UDF functions to address diverse business needs.

  • Unified application interface: seekdb is compatible with native MySQL drivers and provides a unified SQL-based query language for multi-model data. Additionally, it offers developer-friendly SDKs for vector databases and hybrid search. seekdb integrates with nearly 30 application development frameworks, including popular AI frameworks such as LangChain, LlamaIndex, and Dify, and features an MCP server for seamless connection to the AI ecosystem.

Core advantages​

  • Build fast

    From prototype to production in minutes: create AI apps using Python, run VectorDBBench on 1C2G.

  • Hybrid search

    Combine vector search, full-text search and relational query in a single statement.

  • Multi-model

    Support relational, vector, text, JSON and GIS in a single engine.

  • AI inside

    Run embedding, reranking, LLM inference and prompt management inside the database, supporting a complete document-in/data-out RAG workflow.

  • SQL inside

    Powered by the proven OceanBase engine, delivering real-time writes and queries with full ACID compliance, and seamless MySQL ecosystem compatibility.

AI native​

Full-stack AI capabilities for application development—from search to inference.

  • Support multi-path retrieval in a single SQL query, combining vector-based semantic search with keyword-based search for optimized recall.
  • Query reranking supports weighted scores, Reciprocal Rank Fusion (RRF), and LLM-based reranking for enhanced results
  • Relational filters are pushed down to storage for optimized performance, and multi-table joins allow relational data retrieval.

Vector & full-text search​

  • Supports dense vectors and sparse vectors, with multiple distance metrics including Manhattan, Euclidean, inner product, and cosine similarity.
  • Vector indexes support in-memory types such as HNSW, HNSW-SQ, HNSW-BQ, and disk-based types including IVF and IVF-PQ, optimizing storage costs.
  • Full-text search supports keyword, phrase, and Boolean queries, with BM25 ranking for relevance.

AI functions​

  • Manage built-in AI services via the DBMS_AI_SERVICE package in SQL, and register external LLM services.
  • Convert text to vector embeddings directly in SQL using the AI_EMBED function.
  • Generate text in SQL with AI_COMPLETE, supporting reusable prompt templates.
  • Rerank text using LLM-based models in SQL via AI_RERANK.

Applicable scenarios​

RAG & knowledge retrieval​

Large language models are limited by their training data. RAG introduces timely and trusted external knowledge to improve answer quality and reduce hallucination. seekdb enhances search accuracy through vector search, full-text search, hybrid search, built-in AI functions, and efficient indexing, while multi-level access control safeguards data privacy across heterogeneous knowledge sources.

Applicable scenarios:

  • Enterprise QA
  • Customer support
  • Industry insights
  • Personal knowledge

AI-assisted programming​

seekdb is well-suited for AI-powered programming tasks. It can build vector and full-text indexes for code repositories, making it easy to search for code or generate completions based on keywords or code semantics. seekdb also excels at organizing code data, supporting both structured storage (like syntax trees and dependency graphs) and unstructured storage (such as raw code text). Its dynamic metadata management allows developers to flexibly extend and efficiently query code attributes—like language type, function names, and parameter lists.

Semantic search engine​

Traditional keyword search struggles to capture intent. Semantic search leverages embeddings and vector search to understand meaning and connect text, images, and other modalities. seekdb's hybrid search and multi-model querying deliver more precise, context-aware results across complex search scenarios.

Applicable scenarios:

  • Product search
  • Text-to-image
  • Image-to-product

Agentic AI applications​

Agentic AI requires memory, planning, perception, and reasoning. seekdb provides a unified foundation for agents through metadata management, vector/text/mixed queries, multimodal data processing, RAG, built-in AI functions and inference, and robust privacy controls—enabling scalable, production-grade agent systems.

Applicable scenarios:

  • Personal assistants
  • Enterprise automation
  • Vertical agents
  • Agent platforms

AI-assisted coding & development​

AI-powered coding combines natural-language understanding and code semantic analysis to enable generation, completion, debugging, testing, and refactoring. seekdb enhances code intelligence with semantic search, multi-model storage for code and documents, isolated multi-project management, and time-travel queries—supporting both local and cloud IDE environments.

Applicable scenarios:

  • IDE plugins
  • Design-to-web
  • Local IDEs
  • Web IDEs

Enterprise application intelligence​

AI transforms enterprise systems from passive tools into proactive collaborators. seekdb provides a unified AI-ready storage layer, fully compatible with MySQL syntax and views, and accelerates mixed workloads with parallel execution and hybrid row-column storage. Legacy applications gain intelligent capabilities with minimal migration across office, workflow, and business analytics scenarios.

Applicable scenarios:

  • Document intelligence
  • Business insights
  • Finance systems

AI on-device & edge AI applications​

Edge devices—from mobile to vehicle and industrial terminals—operate with constrained compute and storage. seekdb's lightweight architecture supports embedded and micro-server modes, delivering full SQL, JSON, and hybrid search under low resource usage. It integrates seamlessly with OceanBase cloud services to enable unified edge-to-cloud intelligent systems.

Applicable scenarios:

  • Personal assistants
  • In-vehicle systems
  • AI education
  • Companion robots
  • Healthcare devices

Contents

Edit this page