milvus
Vector database
A high-performance cloud-native vector database for next-generation AI applications
A cloud-native vector database, storage for next generation AI applications
31k stars
285 watching
3k forks
Language: Go
last commit: about 2 months ago
Linked from 9 awesome lists
annscloud-nativedistributedembedding-databaseembedding-similarityembedding-storefaissgolanghnswimage-searchllmnearest-neighbor-searchtensor-databasevector-databasevector-searchvector-similarityvector-store
Related projects:
Repository | Description | Stars |
---|---|---|
patterns-ai-core/milvus | A Ruby wrapper around a vector search database API for efficient similarity searches in high-dimensional space | 25 |
marqo-ai/marqo | An end-to-end vector search engine that handles text and image similarity | 4,679 |
lancedb/lancedb | A serverless vector search and storage database built with Rust, enabling efficient similarity searches across multimodal data. | 4,993 |
qdrant/qdrant | A high-performance vector search engine and database for efficient similarity searches in machine learning applications. | 21,001 |
jarvusinnovations/lapidus | Tools for streaming data from relational databases and NoSQL document stores to receive real-time updates | 172 |
miurla/morphic | An AI-powered search engine with a generative UI | 6,461 |
infiniflow/infinity | A high-performance database designed to support the fast and efficient search of various data types in AI applications | 2,780 |
mindsdb/mindsdb | A platform for building AI agents that can learn from and answer questions across multiple data sources using machine learning and natural language processing. | 26,915 |
vespa-engine/vespa | A platform for building scalable, high-performance search and recommendation engines for large datasets | 5,881 |
weaviate/weaviate | A cloud-native vector database that enables fast and scalable search of structured and unstructured data using machine learning models | 11,812 |
different-ai/embedbase | An API to connect LLMs with vector databases for search and retrieval of data. | 499 |
philippgille/chromem-go | An in-memory vector database that enables retrieval augmented generation and other embeddings-based features without relying on external third-party dependencies. | 340 |
vectordotdev/vector | A high-performance observability data pipeline that collects, transforms, and routes logs and metrics to various vendors. | 18,403 |
superduper-io/superduper | A framework for building end-to-end AI applications and workflows without data migration or MLOps implementation | 4,868 |
tiledb-inc/tiledb-vector-search | A serverless, scale-out vector similarity search and storage system with efficient database capabilities | 54 |