█
LastWrite
  • > Curriculum
  • > Pricing
  • > For Educators
  • > About
  • > Contact
Log InGet Started

Questions, concerns, bug reports, or suggestions? We read every message, write to us at [email protected].

More ways to reach us →
LastWrite

Structured computer science lessons for aspiring developers and security professionals.

[email protected]

(201) 785-7951

Mon–Fri, 9 AM–5 PM EST

Learn

  • Curriculum
  • Pricing

Company

  • About
  • For Educators & Schools
  • Contact Us

Legal

  • Terms of Service
  • Privacy Policy
© 2026 LastWrite. All rights reserved.
Curriculum/AI Agents/Low-Code Agents/LangFlow: Visual LangChain Workflow Builder
60 minIntermediate

LangFlow: Visual LangChain Workflow Builder

After this lesson, you will be able to: Set up LangFlow, build a RAG pipeline visually, and run a multi-turn conversational agent, all from the canvas.

LangFlow is the visual front-end to LangChain. Every node is a real LangChain component, every edge is a Python data flow. This lesson installs LangFlow, builds a document-grounded conversational agent, and walks through what each LangChain component is doing under the hood.

Prerequisites:Low-Code Platforms Overview: LangFlow, Flowise, Dify, Relevance AI

Install LangFlow

  1. 1

    1. Make sure you have Python 3.10+ (`python --version`).

  2. 2

    2. Install: `pip install langflow` (or `uv pip install langflow`).

  3. 3

    3. Run: `langflow run`. It serves at http://localhost:7860.

  4. 4

    4. Sign up locally. You'll see the templates gallery.

The canvas, briefly

Left panel: components organized by type (Models, Memories, Tools, Vector Stores, Loaders). Center: the canvas. Right: an inline chat to test. Drag a component → connect handles by type, handles are color-coded and only compatible types snap together.

Document Loader
→
TextSplitter
→
Embeddings
→
Vector Store
→
Retriever
→
LLM
→
ChatOutput
A RAG pipeline in LangFlow. Documents are chunked and embedded once; at query time the retriever pulls the relevant chunks into the LLM.

Build a RAG pipeline

  1. 1

    1. From templates, pick 'Vector Store RAG'. Or build from scratch:

  2. 2

    2. Drag 'File' loader. Upload a PDF (any 5–20 page doc).

  3. 3

    3. Drag 'Recursive Character Text Splitter'. Connect File output → Splitter input.

  4. 4

    4. Drag 'OpenAI Embeddings' (or 'HuggingFace' for free). Add API key as env var.

  5. 5

    5. Drag 'Astra DB' or 'Chroma' vector store. Connect Splitter + Embeddings into it.

  6. 6

    6. Drag 'Chat Input' → 'Prompt' → 'OpenAI / Claude' LLM → 'Chat Output'. Connect the vector store output as 'context' into the prompt.

  7. 7

    7. Hit Build, then test in the inline chat: ask a question only your PDF can answer.

💡 What's actually happening

Your PDF is split into chunks → each chunk becomes a vector embedding → stored in a vector DB. Your question becomes a vector → top-K most similar chunks are retrieved → those chunks + your question → the LLM. This is RAG. LangFlow just visualised it.

Add memory and turn it conversational

  1. 1

    1. Drag a 'ConversationBufferMemory' node.

  2. 2

    2. Connect it as 'memory' input to the prompt.

  3. 3

    3. Now it remembers within the conversation. Ask follow-up questions like 'expand on point 2', it will use the prior turn as context.

Sign in and purchase access to unlock this lesson.

Sign in to purchase
←Low-Code Platforms Overview: LangFlow, Flowise, Dify, Relevance AI
Back to Low-Code Agents
Flowise: Self-Hosted Open-Source Agent Platform→