Ground it in your PDFs: a RAG Q&A bot

🎯Goal. Turn one of your own PDFs into a chatbot that answers from the document, not from generic knowledge.

1. 1Create a New Chatflow and drag a PDF File loader onto the canvas; upload one paper or set of lab notes.
2. 2Add a vector store node and connect it — this is the technique called RAG (retrieval-augmented generation): your document is indexed so the model can retrieve the relevant passages before answering.
3. 3Connect an OpenAI chat node, open the chat panel, and ask the prompt above. The reply should be grounded in your uploaded PDF. Concepts like vector stores and embeddings have a real learning curve — Flowise lets you wire them visually instead of coding them.

✓You'll see. A chat answer drawn from the passages in your uploaded PDF — a document-grounded Q&A bot, not a generic chatbot.

💳Cost. Within the Free plan's 100 predictions/month and 5MB storage; each answer also spends your own LLM + embedding API usage.

💡Takeaway. RAG is Flowise's sweet spot: drop in a PDF and a vector store, and your own documents become an answerable knowledge base.