Transwarp Data Hub
Transwarp Data Cloud
Transwarp ArgoDB
Transwarp KunDB
Transwarp Data Studio
Transwarp Sophon
Transwarp Knowledge Hub
TxData (ARM)
TxData (x86)
TxIRA
Transwarp Hippo
Transwarp Distributed Vector Database
Product Introduction
Transwarp Hippo is an enterprise-level cloud-native distributed vector database that supports storage, retrieval, and management of massive vector-based datasets. It efficiently solves problems such as vector similarity search and high-density vector clustering. Hippo features high availability, high performance, and easy scalability. It has many functions，such as multiple vector search indexes, data partitioning and sharding, data persistence, incremental data ingestion, vector scalar field filtering, and mixed queries. It can effectively meet the high real-time search demands of enterprises for massive vector data.
Product Advantages
Cloud Native System
Hippo adopts a comprehensive containerized deployment, supporting elastic scaling of services. It also has multi-tenancy and powerful resource management capabilities.
Distributed Deployment
It has the ability of distributed deployment for large-scale cluster deployment; ensuring strong consistency of data through Raft algorithm; and providing data protection capabilities such as fault migration and data repair.
Enterprise-Level Security
Hippo provides user authentication capabilities based on SASL, and data encryption transmission based on SSL/TLS.
High Performance Retrieval
Hippo supports multi-process architecture and GPU acceleration, which can fully utilize parallel retrieval capabilities. It also supports various types of indexes to meet different business scenarios. Hippo supports specific optimizations for retrieval speed and memory usage, as well as register-level algorithm optimization.
Multi-Model Joint Analysis
Based on a multi-model unified technical architecture, vector data and various model data such as relational data, graph data, and time-series data are stored and managed uniformly. Data cross-model joint analysis is realized through a unified interface.
Diverse Interfaces
Hippo provides SQL-like syntax support; Supports rich APIs，like Python, Restful, and Java.
Application Scenarios
Text Retrieval
Traditional search engines tend to lean towards precise queries of words and sentences. Hippo provides natural language processing capabilities through its vector engine, which can better support semantic-based query analysis, making queries more human-oriented.
Voice, Image, and Video Retrieval
Through machine learning analysis, various types of data can be abstracted into high-dimensional vector features. Hippo can construct efficient vector indexes for all features. Users can perform similarity retrieval based on vector indexes, which can cover various AI scenarios such as face recognition, voice recognition, and video fingerprinting.
Personalized Recommendation
Hippo supports coupling with various deep learning platforms to analyze and mine behavior across multiple aspects, storing the relevant data in vectorized form. By performing vector similarity search, it can help make personalized recommendation.
Large Language Model Application
Hippo can serve as an intermediate carrier for hosting various content generated by LLM, effectively expanding the temporal and spatial boundaries of LLM. This enables LLM to possess 'long-term memory' and assists in sovling the privacy leakage problems in enterprises.
Transwarp, Shaping the Future Data World
