AI & LangChain Nodes Reference

Complete guide to AI and LangChain nodes — LLMs, agents, memory, parsers, and tools.

Written By pvdyck

Last updated About 5 hours ago

AI & LangChain Nodes Reference

AI nodes enable workflows to use large language models (LLMs), AI agents, and related capabilities.

LLM Chat Models

Model ProviderDescriptionVendor Page
OpenAI Chat ModelGPT models for text generation and conversationOpenAI
Anthropic Chat ModelClaude models with extended thinkingAnthropic
OpenRouter Chat ModelUnified access to 100+ models (recommended)OpenRouter

All AI model requests route through OpenRouter. See individual vendor pages for supported operations, authentication, and limitations.

AI Agents & Chains

Agent Node

ID: agent-node

Create autonomous AI agents that use tools to complete multi-step tasks.

How It Works: The agent decides which tools to use and in what order based on the objective.

Chain LLM Node

ID: chain-llm-node

Chain multiple LLM calls together for complex workflows (e.g., extract → transform → summarize).

AI-Powered Analysis

Information Extractor

ID: information-extractor

Extract structured data from unstructured text using LLMs (e.g., extract names, dates, prices from emails).

Sentiment Analysis

ID: sentiment-analysis

Analyze text sentiment (positive, negative, neutral) for reviews, feedback, or social media.

Text Classifier

ID: text-classifier

Categorize text into predefined classes using LLMs.

Output Parser (Structured)

ID: output-parser-structured

Ensure LLM outputs match a specific schema (JSON, types, required fields).

Memory & Context

Memory Buffer Window

ID: memory-buffer-window

Maintain conversation history or context window for AI agents. Stores recent messages for context-aware responses.

Limitation: Use instead of LangChain external memory nodes (not supported).

AI Tools

Tool: Calculator

ID: tool-calculator

Enable LLMs to perform mathematical calculations accurately.

Supported Features

✅ Fully Supported:

  • Chat completions (OpenAI, Anthropic, OpenRouter)
  • AI agents with tools
  • Memory buffer for conversation context
  • Structured output parsing
  • Sentiment analysis and text classification

❌ Not Supported:

  • LangChain external memory nodes (use Memory Buffer Window instead)
  • LangChain embedding and vector store nodes
  • Custom LangChain tools beyond Calculator
  • Direct LLM provider nodes (Google Gemini, Ollama, etc.) — use OpenRouter Chat Model instead, which routes to 100+ models including Gemini
  • Document processing nodes: chainSummarization, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, toolWikipedia — require filesystem or @langchain/community dependencies unavailable in Cloudflare Workers

Related