{"slug": "tencent-just-released-a-rag-framework-and-nobody-s-talking-about-it", "title": "Tencent just released a RAG framework and nobody's talking about it", "summary": "In April 2026, Tencent's WeChat team released WeKnora, an open-source RAG framework under the MIT license, which is production-tested at scale on WeChat's Dialog Open Platform. It features an autonomous reasoning agent that decomposes complex queries into sub-queries before retrieval and a self-updating knowledge base that monitors and refreshes content from URLs or folders automatically. Despite its capabilities, the framework has almost no English-language documentation or community presence, with its user base primarily on Chinese platforms like WeChat groups and Zhihu.", "body_md": "In April 2026, Tencent's WeChat team released WeKnora as open source. MIT licensed. Ollama support built-in. Almost zero English content about it.\nI spent a few days setting it up, writing the first English integration guide, and comparing it to the alternatives. Here's what I found.\nWeKnora is the RAG framework that powers WeChat's Dialog Open Platform — production-tested at a scale most of us will never reach.\nAt its core it does what every RAG tool does: upload documents, ask questions, get answers grounded in your content.\nBut it adds two things I haven't seen elsewhere:\n1. Autonomous reasoning agent\nWhen you ask a complex question, WeKnora doesn't just search. It plans.\n\"Compare the pricing strategy in document A with the market analysis in document B\" gets decomposed into sub-queries before any retrieval happens. Most RAG tools dump a random mix of chunks into the LLM and hope for the best. WeKnora's agent actually thinks about how to answer before searching.\n2. Self-updating knowledge base\nPoint WeKnora at a URL or folder, set a refresh interval, and it monitors the source and updates the knowledge base automatically when content changes. For internal docs, product catalogs, or anything that evolves — this is genuinely useful.\nTwo modes. Pick based on what you already have running.\nIf you already have Ollama running:\n\"bash\ngit clone https://github.com/retrovirusretro/weknora-english-guide\ncd weknora-english-guide\ncp .env.example .env\ndocker compose up -d\"\nWeKnora joins your existing Docker network. No duplicate Ollama container.\nFresh install (includes Ollama):\n\"docker compose -f docker-compose.standalone.yml up -d\ndocker exec -it weknora-ollama ollama pull llama3\"\nOpen http://localhost:8083 → admin / weknora123 → connect Ollama → upload a PDF → ask a question.\n*FastGPT prohibits commercial SaaS resale.\nWhen to pick WeKnora over RAGFlow:\nYou need the reasoning agent for complex multi-document questions\nMIT license matters (embedding in a commercial product)\nYou want the self-updating KB feature\nWhen to pick RAGFlow instead:\nYour PDFs have complex layouts (tables, multi-column, images)\nYou want a larger English community with more answered questions\nn8n Integration\nWeKnora exposes a REST API. Connect it to n8n for automation pipelines:\nWebhook → WeKnora /api/query → Slack / Email / Notion\nA ready-to-import n8n workflow JSON is in the repo:\nexamples/with-n8n/weknora-query-workflow.json\nImport it in n8n → Workflows → Import from file. One click, working webhook.\nWhy Almost No English Content?\nThe WeKnora community is on WeChat groups and Zhihu. The maintainers write English READMEs but the tutorial ecosystem never crossed over.\nSame story with FastGPT (27K stars), MaxKB (20K stars), DB-GPT (17K stars). Massive Chinese communities, almost nothing in English.\nI'm documenting all of them:\n→ chinese-ai-tools-english-guide\nFull Guide\nEverything in this post plus Ollama model selection, production deployment with Nginx + SSL, and the WeKnora vs RAGFlow deep-dive:\n→ github.com/retrovirusretro/weknora-english-guide\nHave you tried WeKnora? Curious if others run into setup issues I haven't documented yet.", "url": "https://wpnews.pro/news/tencent-just-released-a-rag-framework-and-nobody-s-talking-about-it", "canonical_source": "https://dev.to/retrovirusretro/tencent-just-released-a-rag-framework-and-nobodys-talking-about-it-2c9g", "published_at": "2026-05-20 21:08:48+00:00", "updated_at": "2026-05-20 21:33:17.568598+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "open-source", "developer-tools", "products"], "entities": ["Tencent", "WeChat", "WeKnora", "Ollama", "Dialog Open Platform"], "alternates": {"html": "https://wpnews.pro/news/tencent-just-released-a-rag-framework-and-nobody-s-talking-about-it", "markdown": "https://wpnews.pro/news/tencent-just-released-a-rag-framework-and-nobody-s-talking-about-it.md", "text": "https://wpnews.pro/news/tencent-just-released-a-rag-framework-and-nobody-s-talking-about-it.txt", "jsonld": "https://wpnews.pro/news/tencent-just-released-a-rag-framework-and-nobody-s-talking-about-it.jsonld"}}