WeKnora

WeKnora is an open-source, LLM-powered knowledge framework developed by Tencent, designed for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning. It integrates RAG (Retrieval-Augmented Generation) for quick Q&A, employs a ReAct Agent for complex multi-step tasks, and introduces an innovative Wiki Mode that distills raw documents into a self-maintaining, interlinked Markdown knowledge base with an interactive knowledge graph. It supports multi-source data ingestion (Feishu, Notion, Yuque, etc.), integrates with over 20 LLM providers, offers Langfuse observability, and supports self-hosted deployments, aiming to transform scattered documents into a queryable, reasoning-capable, and continuously evolving knowledge asset.

• RAG 知识检索与智能问答
• ReAct Agent 自主推理与任务编排
• Wiki 模式与动态知识图谱构建
• 企业级多源数据集成与隐私部署
• 全面的可观测性与LLM/VectorDB兼容