n8n AI Automations · Lesson 2

n8n's built-in LLM nodes

Chat Model (OpenAI, Anthropic, Google), Basic LLM Chain, Question & Answer Chain, Text Classifier, Summarize — when to use each vs raw HTTP.

25 min read4 questions in quizReady prompt includedIn progress

Practical exercise

What to do after this lesson

Build: Manual Trigger → Text Classifier (categories support / sales / spam) with an OpenAI Chat Model connected. Hang a Set node tagged with the category on each of the three output ports. Run it on three test texts.

Ready-to-use prompt

Template for this lesson

Copy and adapt to your context. Text in angle brackets should be replaced.

Help me pick the right n8n node for an AI task.
Task: <classification / summarization / Q&A over documents / a single LLM call>
Input volume: <…>

Tell me which root LangChain node to use (Basic LLM Chain / Text Classifier /
Question & Answer Chain / Summarize), which Chat Model to connect and why,
and when a raw HTTP Request is needed instead.

Common mistakes

What people get wrong

Adding a Chat Model node on its own and wondering why it "does nothing" — it's a sub-node, it must be connected to a root node.
Doing classification via Basic LLM Chain + text parsing instead of Text Classifier — losing the guarantee of a valid category.
Using the plain Summarize node (aggregation) instead of AI Summarize from the LangChain section.

Chat Model (a sub-node)

Chat Model is not a standalone node — it is a model provider for root nodes:

OpenAI Chat Model — gpt-4o, gpt-4o-mini, the o-series.

Anthropic Chat Model — claude-sonnet-4-5, claude-opus, etc.

Google Gemini Chat Model — gemini-1.5-pro / flash.

The Chat Model node does nothing on its own — its Chat Model output port plugs into Basic LLM Chain, AI Agent, Text Classifier, and so on.

Basic LLM Chain

The simplest root node: "prompt → answer". One pass, no memory, no tools.

Node: Basic LLM Chain Prompt Type: Define below Text: "Compress to 1 sentence: {{ $json.article }}" ← connected: Anthropic Chat Model (claude-sonnet-4-5)

Use it when you need one deterministic LLM call in a pipeline without a conversation.

Text Classifier

A root node that returns not free text but one of a defined set of categories. You list categories with descriptions, and the node is guaranteed to return one of them.

Node: Text Classifier Text to Classify: {{ $json.emailBody }} Categories: - "support" (description: customer question/problem) - "sales" (description: buying interest) - "spam" (description: ads, irrelevant) ← connected: OpenAI Chat Model

The output carries the category, and n8n creates a separate output port per category — handy for routing without IF nodes.

Summarize

A root node for summarizing large text. It supports map_reduce and refine strategies for text that doesn't fit the context window: the document is split into chunks, each summarized, then merged. Don't confuse it with the plain Summarize node (numeric aggregation) — you need the LLM version from the AI section.

Built-in node vs raw HTTP Request

Built-in node: typed output, retries, native memory/tool wiring, less code. Reach for it by default.

Raw HTTP Request: when you need a parameter not exposed in the node (a new response_format, a beta-feature header) or a provider with no built-in node.

Rule: start with the built-in node, fall back to HTTP only when you hit its limits.

Сообщить об ошибке

n8n's built-in LLM nodes

Квиз — 4 вопроса

Map of n8n's LangChain nodes

Chat Model (a sub-node)

Basic LLM Chain

Question & Answer Chain

Text Classifier

Summarize

Built-in node vs raw HTTP Request