Zilliz offers Milvus
Product
World's leading open-source vector database for high-dimensional AI similarity search and embeddings.
- Currently Offered
Milvus is the world's most popular open-source vector database, built for storing, indexing, and searching billions of high-dimensional vector embeddings with high performance and scalability. It powers AI applications including recommendation systems, image and video analysis, natural language processing, and retrieval-augmented generation across enterprises worldwide.
Developed by the team behind Zilliz, Milvus leverages advanced indexing algorithms and GPU acceleration to deliver fast similarity search at massive scale. Its open-source nature has fostered a large community, with millions of downloads and widespread adoption in production AI workloads.
World's leading open-source vector database for high-dimensional AI similarity search and embeddings.
ManyVector is an object-storage-native vector search engine for engineers building retrieval and RAG workloads.
turbopuffer is a serverless vector and full-text search database built on object storage, priced from $16 per month.
Redis Cloud provides managed in-memory databases for developers combining caching, real-time data, and vector search across cloud platforms.
Distributed, RESTful search and analytics engine built on Apache Lucene, capable of handling large-scale data search and log analytics.
Serverless Postgres platform with instant provisioning, autoscaling, and database branching.
API that trains compact reusable memories on organizational context for agent inference.
ZeroEntropy's neural rerankers rescore search results to surface the most relevant documents for RAG pipelines.
ZeroEntropy's zembed-1 embedding model converts documents into dense vectors for semantic search and retrieval-augmented generation.
Weaviate is an open-source AI-native vector database that stores and searches embeddings for semantic and hybrid retrieval.
ManyVector is an object-storage-native vector search engine for engineers building retrieval and RAG workloads.
Serverless vector database for AI, semantic search, and RAG pipelines.
LanceDB is a vector database built on the Lance format for vector search and feature engineering on multimodal data.
turbopuffer is a serverless vector and full-text search database built on object storage, priced from $16 per month.
Redis Cloud provides managed in-memory databases for developers combining caching, real-time data, and vector search across cloud platforms.
Vespa is an open-source AI search platform combining hybrid retrieval, multi-phase ranking, and machine-learned inference in a distributed engine.
Distributed, RESTful search and analytics engine built on Apache Lucene, capable of handling large-scale data search and log analytics.
Serverless Postgres platform with instant provisioning, autoscaling, and database branching.
MongoDB Atlas is a fully managed multi-cloud document database service.
API that trains compact reusable memories on organizational context for agent inference.
ZeroEntropy's neural rerankers rescore search results to surface the most relevant documents for RAG pipelines.
ZeroEntropy's zembed-1 embedding model converts documents into dense vectors for semantic search and retrieval-augmented generation.