PromptTemplate + LLM Example (LangChain Port)

[allanbunch]

PromptTemplate + LLM

A PromptTemplate -> LLM is a core flow that is used in most other larger flows/systems.

Download: Example Node-RED Flow JSON

This example is a port of LangChain's Prompt Template chain.

For this example, the default API configuration is Ollama backed by Stability AI's amazing Stable LM 2 Zephyr 1.6B small language model (SLM). You'll want to configure the AI API node for your specific needs.

Instructions

1. Configure the AI API node as needed.
2. Set the Topic node's msg.topic to whatever you like--the Prompt Template is configured to tell a joke.

---

LangChain JS Equivalent

import { ChatOpenAI } from "@langchain/openai";
import { PromptTemplate } from "@langchain/core/prompts";

const model = new ChatOpenAI({});
const promptTemplate = PromptTemplate.fromTemplate(
  "Tell me a joke about {topic}"
);

const chain = promptTemplate.pipe(model);

const result = await chain.invoke({ topic: "bears" });

console.log(result);