How to beginner · 3 min read

How to create a chain with prompt and LLM in LangChain

Q: How to create a chain with prompt and LLM in LangChain

Use ChatPromptTemplate to define your prompt and ChatOpenAI as the LLM in LangChain. Then create a LLMChain by passing the prompt and LLM instances, and call run() with input variables to generate completions.

Quick answer

Use ChatPromptTemplate to define your prompt and ChatOpenAI as the LLM in LangChain. Then create a LLMChain by passing the prompt and LLM instances, and call run() with input variables to generate completions.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install langchain_openai>=0.2 openai>=1.0

Setup

Install the required packages and set your OpenAI API key as an environment variable.

Install LangChain OpenAI integration and OpenAI SDK:

bash

pip install langchain_openai openai

Step by step

This example creates a prompt template with a variable, initializes the GPT-4o model, builds an LLMChain, and runs it with input to get a response.

python

import os
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.chains import LLMChain

# Set your OpenAI API key in environment variable before running
# export OPENAI_API_KEY='your_api_key'

# Define a prompt template with a variable
prompt = ChatPromptTemplate.from_template("Tell me a joke about {topic}.")

# Initialize the LLM with GPT-4o
llm = ChatOpenAI(model_name="gpt-4o", temperature=0.7, openai_api_key=os.environ["OPENAI_API_KEY"])

# Create the chain with prompt and LLM
chain = LLMChain(llm=llm, prompt=prompt)

# Run the chain with input variable
result = chain.run({"topic": "computers"})
print(result)

output

Why did the computer go to therapy? Because it had too many bytes of emotional baggage!

Common variations

You can use different models like gpt-4o-mini or claude-3-5-sonnet-20241022 with their respective LangChain integrations. Async calls and streaming outputs are also supported by LangChain's LLM classes.

python

from langchain_openai import ChatOpenAI

# Using a smaller model
llm_mini = ChatOpenAI(model_name="gpt-4o-mini", temperature=0.5, openai_api_key=os.environ["OPENAI_API_KEY"])

# Async example (Python 3.8+)
import asyncio

async def async_run():
    result = await llm_mini.acall([{"role": "user", "content": "Say hello"}])
    print(result.content)

asyncio.run(async_run())

output

Hello! How can I assist you today?

Troubleshooting

If you get an authentication error, verify your OPENAI_API_KEY environment variable is set correctly.
If the chain fails to run, ensure your prompt variables match the input dictionary keys.
For rate limits, consider lowering temperature or switching to a smaller model.

✅

Key Takeaways

Use ChatPromptTemplate to create reusable prompt templates with variables.
Instantiate ChatOpenAI with your API key and desired model to create the LLM.
Combine prompt and LLM in LLMChain to run completions with input variables.
LangChain supports async calls and multiple models for flexible integration.
Always verify environment variables and input keys to avoid common errors.

Verified 2026-04 · gpt-4o, gpt-4o-mini, claude-3-5-sonnet-20241022

Verify ↗