32dots HEIDELBERG AI
Curriculum › Langflow course › langflow-02
Session 2 medium

Build a RAG chatbot over your own documents

LESSONLesson 2 · ~30 min

🎯Goal. Start from a ready-made template to build a chatbot that answers questions from your own PDF or website using retrieval-augmented generation (RAG).

▶ Try this prompt

Open the template gallery, pick a document/RAG starter (e.g. Doc Assistant or Content Search), point it at one of your own PDFs, then ask it a question only that document can answer.

Templates give you a working flow to start from instead of a blank canvas — the gallery includes starters like Content Search, Code Debugger, Basic Prompting, Basic Agent and Doc Assistant.

  1. 1Open the template gallery and pick a document-grounded starter. RAG means the bot retrieves the relevant passages from your files first, then asks the model to answer using them — so replies are grounded in your content, not guesses.
  2. 2Load your own source — a PDF or a website — into the document block, then open the Playground and ask a question that only that document can answer.
  3. 3This is the pattern scientists use to chat with their own papers or datasets: the same flow generalises from one PDF to a whole folder, or to a literature-Q&A bot a lab can share.
Langflow's template gallery showing cards for Content Search, Code Debugger, Basic Prompting, Basic Agent and Doc Assistant, with a provider sidebar listing Anthropic, MistralAI, Langchain, Glean, Cohere, OpenAI and NVIDIA
The template gallery gives you working starters — Content Search, Code Debugger, Basic Prompting, Basic Agent, Doc Assistant — and a provider sidebar (Anthropic, MistralAI, Langchain, Glean, Cohere, OpenAI, NVIDIA) so you can wire in any model. Source: https://www.langflow.org

✓You'll see. A chatbot that answers from your uploaded document — citing your content rather than the model's general knowledge.

💳Cost. Free to build and run; you pay only the LLM (and any vector-DB) usage when the bot answers. Templates save you from wiring the flow from scratch.

💡Takeaway. Templates turn a complex RAG pipeline into a starting point — load your documents and you have a grounded chatbot.