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
automataIA/graphrag-rs
GraphRAG-rs is a Rust-based, high-performance toolkit for implementing Graph-based Retrieval Augmented Generation (GraphRAG). Its primary function is to construct knowledge graphs from unstructured documents and enable natural language querying against these graphs. The project emphasizes deployment flexibility, providing three main architectures: a traditional server-based approach, a WASM-only client-side solution for privacy and offline use, and a planned hybrid model. It integrates with local LLMs like Ollama for entity extraction and leverages technologies like ONNX Runtime Web and WebLLM for GPU-accelerated embeddings and synthesis in WASM environments. The system incorporates several state-of-the-art research enhancements, such as LightRAG Dual-Level Retrieval, Leiden Community Detection, Cross-Encoder Reranking, HippoRAG Personalized PageRank, and Semantic Chunking, aiming to improve retrieval accuracy and cost efficiency. It also features advanced reasoning capabilities like Symbolic Anchoring, Dynamic Edge Weighting, Causal Chain Analysis, Hierarchical Relationship Clustering, and Graph Weight Optimization. While offering a CLI for quick start, it's also designed as a library for Rust applications. This project focuses on the operational aspect of leveraging LLMs for knowledge retrieval and generation, providing the infrastructure and tooling to serve and query complex knowledge structures derived from text.
https://github.com/automataIA/graphrag-rs
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.