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
Zleap-AI/SAG
SAG (Structured Agent Graphs) is an out-of-the-box workbench designed for document retrieval, employing a novel RAG (Retrieval-Augmented Generation) technique optimized for AI agents. Rather than relying on simple chunking, SAG extracts events and entities from document chunks, maintaining semantic integrity for events and using entities for retrieval and relationship expansion. This approach avoids the high cost of rebuilding knowledge graphs and significantly improves multi-hop question-answering recall compared to traditional RAG methods. The platform allows users to upload Markdown or TXT documents, which are then automatically processed through chunking, vectorization, event extraction, entity extraction, and relationship整理 to build a knowledge graph. Users can then interact with the document knowledge base conversationally, similar to ChatGPT, and also inspect document chunks, events, entities, embeddings, search processes, raw model logs, and the generated knowledge graph. It supports project management, multi-document uploads, visualization of document processing results, conversational retrieval with source citations, and real-time visualization of the RAG pipeline. Additionally, it offers two retrieval modes: 'fast mode' for quicker keyword/BM25 matching combined with multi-hop expansion and reranking, and 'standard mode' for higher precision through LLM-extracted query entities and LLM reranking after multi-path retrieval. The workbench is built with TypeScript, featuring a React + Vite + Tailwind CSS frontend, a Fastify HTTP API backend, PostgreSQL with pgvector for data storage, and compatibility with OpenAI-compatible LLM, Embedding, and Rerank APIs. It also provides MCP (Multi-Agent Communication Protocol) integration, allowing external agents to interact with the project's knowledge base via defined tools.
https://github.com/Zleap-AI/SAG
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.