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
datastax/jvector
JVector is a high-performance, embedded vector search engine primarily written in Java, designed for efficient Approximate Nearest Neighbor (ANN) search in large-scale, high-dimensional datasets. It combines a hierarchical structure inspired by HNSW with the Vamana algorithm (behind DiskANN) within each layer, allowing for incremental construction and updates. The engine features a multi-layer graph with nonblocking concurrency control, enabling linear scaling with the number of CPU cores. It utilizes a two-pass search mechanism to reduce memory usage and latency while maintaining accuracy. The first pass uses lossily compressed vector representations (Product Quantization, Binary Quantization, Fused PQ) in memory, while the second pass uses more accurate representations (full float32 or NVQ) read from disk. This design allows for building larger-than-memory indexes, preventing the need to merge results from multiple smaller indexes and ensuring logarithmic search times. JVector is built as a multimodule Maven project and is compatible with Java 11+, with optimized vector providers for Java 20+ JVMs. It includes comprehensive documentation, tutorials, and benchmarking tools for evaluation and development. As an embedded library, it's suitable for integrating vector search capabilities directly into Java applications without external dependencies or services.
https://github.com/datastax/jvector
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.