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
Tencent/WeKnora
WeKnora is an open-source, enterprise-grade, LLM-powered knowledge framework designed to transform raw documents into living knowledge assets. Its core capabilities include RAG-based Quick Q&A for efficient information retrieval, a ReAct agent that orchestrates various tools (retrieval, MCP, web search) for complex multi-step tasks, and an innovative Wiki Mode. In Wiki Mode, agents autonomously distill documents into a self-maintaining, interlinked Markdown knowledge base with an interactive knowledge graph. The platform supports multi-source ingestion from platforms like Feishu, Notion, and Yuque, handles over ten document formats, and integrates with more than twenty LLM providers. It offers comprehensive multi-tenant RBAC with a four-tier role matrix, per-resource ownership, and per-tenant audit logs, making it suitable for secure enterprise deployment. WeKnora's modular architecture allows for the flexible swapping of LLMs, vector databases, and storage backends, supporting both local and private cloud deployments for data sovereignty. It also integrates with Langfuse for in-depth observability, providing tracing for agent reasoning, token usage, and pipeline execution. The framework stands out for its ability to convert scattered enterprise documents into a queryable, reasoning-capable, and continuously evolving knowledge asset, supporting a wide array of LLMs and data sources, and offering robust operational features like batch management, IM channel integration, and credential encryption.
https://github.com/Tencent/WeKnora
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...
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.
weaviate/weaviate
Weaviate is an open-source, cloud-native vector database for semantic search, combining vector similarity search with keyword filtering, RAG, and reranking capabilities.