
In this video I show how to implement an AI Agent with RAG using n8n and Supabase for the chat memory and vector DB. This AI Agent is the REAL deal – something you could actually use in production and not some dinky n8n workflow using buffer memory and an in-memory vector store that duplicates your vectors every time you insert a document again to update it.
毫无疑问,人工智能不仅是软件开发的未来,也是整个世界的未来。我的使命是掌握它 – 首先专注于掌握人工智能代理。在此视频中,我展示了如何使用 n8n 和 Supabase 为聊天内存和向量数据库实现带有 RAG 的人工智能代理。这个人工智能代理是真正的交易 – 您可以在生产中实际使用它,而不是使用缓冲内存和内存向量存储的某些小巧的 n8n 工作流程,每次您再次插入文档以更新它时都会复制您的向量。
If you want to deploy your own n8n instance for free (all you need to pay for is the server to host it), follow these instructions to self-host n8n super easily with DigitalOcean (n8n documentation):
如果您想免费部署自己的 n8n 实例(您需要支付的只是托管它的服务器费用),请按照以下说明使用 DigitalOcean(n8n 文档)轻松地自行托管 n8n:
https://docs.n8n.io/hosting/installation/server-setups/digital-ocean/