The RAG Index / Embeddings / #54
infiniflow/infinity
by infiniflow · Embeddings · updated today
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
71
momentum
4,744
stars
456
forks
#54
rank
ai-nativeapproximate-nearest-neighbor-searchbm25cpp20cpp20-modulesembeddingfull-text-searchhnswhybrid-searchinformation-retrivalmulti-vectornearest-neighbor-search
View on GitHub →