pathwaycom/llm-app
Ready-to-run cloud templates for building real-time RAG, AI pipelines, and enterprise search applications that synchronize with various live data sources.
Awesome Infra for AI › Vector Databases & Retrieval Infrastructure
microsoft/SPTAG
SPTAG (Space Partition Tree And Graph) is an open-source library developed by Microsoft Research and Microsoft Bing, designed for fast and scalable approximate nearest neighbor (ANN) search on large datasets of vectors. It assumes that data samples are represented as vectors and can be compared using L2 or cosine distances. The library aims to return vectors with the smallest distances to a given query vector efficiently. SPTAG offers two primary methods for index construction: kd-tree combined with a relative neighborhood graph (SPTAG-KDT) and balanced k-means tree with a relative neighborhood graph (SPTAG-BKT). SPTAG-KDT is optimized for lower index building costs, while SPTAG-BKT provides superior search accuracy, particularly for very high-dimensional data. The core mechanism involves building a robust graph structure on the k-nearest neighborhood to enhance connectivity, using space partition trees (either kd-trees or balanced k-means trees) to find initial search seeds. The search process then iteratively traverses both the trees and the graph to locate approximate nearest neighbors. Key features of SPTAG include support for online vector deletion and insertion, enabling fresh updates to the index, and capabilities for distributed serving, allowing vector searches across multiple machines. This makes it suitable for demanding, large-scale, and dynamic vector search applications. The project provides detailed documentation on building, installing, and using the library, including Python wrappers for integrating into vector search online services.
https://github.com/microsoft/SPTAG
Also in Vector Databases & Retrieval Infrastructure
run-llama/llama_index
LlamaIndex is an open-source data framework for building LLM applications by connecting custom data sources to large language models, focusing on data ingestion, indexing, and retrieval augmented g...
milvus-io/milvus
Milvus is a high-performance, cloud-native vector database designed for scalable vector Approximate Nearest Neighbor (ANN) search, efficiently organizing and searching vast amounts of unstructured ...
VectifyAI/PageIndex
PageIndex is a vectorless, reasoning-based RAG system that builds hierarchical tree indexes from documents and uses LLMs to reason over them for context-aware retrieval.
qdrant/qdrant
Qdrant is an open-source, high-performance vector similarity search engine and vector database designed specifically for AI applications, enabling fast storage, search, and management of vectors wi...
Tencent/WeKnora
WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval, and autonomous reasoning, featuring RAG, ReAct agents, and an auto-maintaining ...
topoteretes/cognee
Cognee is an open-source AI memory platform that provides AI agents with persistent long-term memory through a self-hosted knowledge graph, combining vector embeddings and graph reasoning.
RyanCodrai/turbovec
TurboVec is a Rust-based approximate nearest neighbor (ANN) vector index with Python bindings, built on Google Research's TurboQuant algorithm for efficient, memory-optimized vector similarity search.