This workflow automates the process of scraping, processing, storing, and retrieving essays for intelligent question answering. It begins when triggered manually, fetching a list of essays from Paul Graham’s website, extracting their links, and limiting the selection to the first three. It then retrieves the full texts of these essays and extracts only the main content for analysis. The content is chunked for efficient processing and embedded into a Milvus vector store for fast similarity searches. When a chat message is received, the workflow uses OpenAI’s language models to generate responses based on the retrieved relevant essay chunks, providing citations for transparency. This setup is ideal for researchers, students, or developers who want to create an AI-powered knowledge base from web-scraped documents, supporting advanced Q&A functionality with quick retrieval of relevant information.
Automated Essay Collection and Q&A with Milvus and AI
Node Count | >20 Nodes |
---|---|
Nodes Used | @n8n/n8n-nodes-langchain.chatTrigger, @n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsOpenAi, @n8n/n8n-nodes-langchain.informationExtractor, @n8n/n8n-nodes-langchain.lmChatOpenAi, @n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter, @n8n/n8n-nodes-langchain.vectorStoreMilvus, code, html, httpRequest, limit, manualTrigger, set, splitOut, stickyNote |
Reviews
There are no reviews yet.