pyseekdb and pyobvector
These are ecosystem siblings—pyseekdb is OceanBase's specialized SDK for the SeekDB vector engine, while pyobvector is OceanBase's multimodal vector store SDK, both providing different interfaces (seekdb-native vs. Milvus-compatible/SQLAlchemy) to the same underlying OceanBase database platform.
About pyseekdb
oceanbase/pyseekdb
A unified python SDK supports OceanBase or OceanBase seekdb, more efficient and easy-to-use.
Supports vector, full-text, and hybrid search capabilities with a collection-first API for semantic operations, while also enabling direct SQL access via MySQL-compatible drivers. Offers flexible deployment with both embedded and server modes using a unified interface, plus built-in embedding model integrations for end-to-end RAG workflows.
About pyobvector
oceanbase/pyobvector
A Python SDK for OceanBase Multimodal Store—enabling vector search, full-text search, and JSON table operations—offers both Milvus-compatible API and SQLAlchemy-based SQL mode, and supports both OceanBase and OceanBase seekdb.
The SDK provides dual-API access through Milvus-compatible endpoints and SQLAlchemy ORM bindings, enabling developers to choose between vector-native or relational query patterns interchangeably. It supports embedded SeekDB mode for serverless local deployments and hybrid search combining full-text and vector similarity with Elasticsearch-compatible syntax. Built on OceanBase's multimodal storage layer, it handles vector indexes (HNSW, VSAG), JSON extraction, and range partitioning with distance-threshold filtering for precision control.
Scores updated daily from GitHub, PyPI, and npm data. How scores work