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
NVIDIA/cuvs
cuVS (cuVectorSearch) is a GPU-accelerated library from NVIDIA that offers state-of-the-art implementations for approximate nearest neighbors (ANN) and clustering algorithms. Its primary goal is to simplify the use of GPUs for vector similarity search and clustering tasks, which are increasingly vital for handling multimedia embeddings and enabling semantic search on unstructured data. The library supports use cases such as generative AI, Retrieval Augmented Generation (RAG), recommender systems, and various data mining applications like clustering and visualization algorithms (UMAP, t-SNE, K-means, HDBSCAN). Key benefits of cuVS include fast index building, support for latency-critical and high-throughput searches, simplified parameter tuning, and cost savings through efficient GPU utilization. It also emphasizes interoperability, allowing models built on GPUs to be deployed on CPUs, and offers multiple language bindings (Python, C++, C, Rust). Built on top of the RAPIDS RAFT library, cuVS provides essential routines for high-performance vector search. The project aims to abstract the complexities of GPU-accelerated code, ensuring ongoing performance and scalability as NVIDIA architectures and CUDA versions evolve. It is suited for foundational vector operations within larger AI systems, such as vector databases or retrieval systems, by offering the core computational power for similarity search.
https://github.com/NVIDIA/cuvs
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.