VTS (Vector Transport Service) is an open-source tool developed by Zilliz focused on the migration of vectors and unstructured data.
Zilliz developed VTS to meet the growing demand for data migration and support real-time stream data and offline import capabilities.
VTS is a powerful tool for building AI application data pipelines, achieving real-time synchronization of vector data, and converting and loading unstructured data.
Vector database migration is one of the core capabilities of VTS that can handle the migration of vector data, crucial for AI and machine learning applications.
VTS supports cross-platform data integration, meaning it can seamlessly migrate data from one system to another, whether it's a traditional relational database or a modern vector database.
VTS supported connectors include Milvus, Pinecone, Qdrant, Postgres SQL, ElasticSearch, Tencent Vector DB, etc. making it more flexible in data processing.
VTS supports various data types including Float Vector, Sparse Float Vector, multi-vector columns, dynamic columns, and data insertion, including Upsert and Bulk Insert.
VTS is expected to implement the direct insertion of raw data and the use of raw data for search functionalities in Milvus version 2.5.
VTS aims to expand its support to handle more data sources such as Chroma DB, DataStax, DataLake, Mongo DB, Kafka (real-time AI), object storage import, etc.
VTS is an indispensable data migration tool in the fields of AI and machine learning and paves the way for the development of innovative AI applications.