This workflow enables automatic processing of PDF documents for intelligent question-answering using Weaviate vector database and OpenAI models. The process begins with manual PDF upload, followed by text extraction and chunking. The text is then embedded with OpenAI’s embeddings and stored in Weaviate for semantic search. Users can then interactively ask questions via a chat interface, which retrieves relevant context from Weaviate and answers using GPT-4. This setup is ideal for creating knowledge bases, document analysis tools, or customer support chatbots that understand and answer queries grounded in large documents.

Node Count

11 – 20 Nodes

Nodes Used

@n8n/n8n-nodes-langchain.chainRetrievalQa, @n8n/n8n-nodes-langchain.chatTrigger, @n8n/n8n-nodes-langchain.documentDefaultDataLoader, @n8n/n8n-nodes-langchain.embeddingsOpenAi, @n8n/n8n-nodes-langchain.lmChatOpenAi, @n8n/n8n-nodes-langchain.retrieverVectorStore, @n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter, @n8n/n8n-nodes-langchain.vectorStoreWeaviate, extractFromFile, formTrigger, set, stickyNote