How to beginner · 3 min read

How to build a simple LLM chain in LangChain

Q: How to build a simple LLM chain in LangChain

Use the ChatOpenAI class from langchain_openai to instantiate an LLM, then create a LLMChain with a PromptTemplate to build a simple chain. Call the chain with input variables to get the generated output.

Quick answer

Use the ChatOpenAI class from langchain_openai to instantiate an LLM, then create a LLMChain with a PromptTemplate to build a simple chain. Call the chain with input variables to get the generated output.

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 simple LLM chain that takes a user's name and returns a greeting using ChatOpenAI and LLMChain.

python

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

# Initialize the LLM with your OpenAI API key
llm = ChatOpenAI(model_name="gpt-4o", temperature=0, openai_api_key=os.environ["OPENAI_API_KEY"])

# Define the prompt template with an input variable
prompt = ChatPromptTemplate.from_messages([
    HumanMessagePromptTemplate.from_template("Say hello to {name}!")
])

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

# Run the chain with input
result = chain.run({"name": "Alice"})
print(result)

output

Hello, Alice!

Common variations

You can customize the chain by:

Using different models like gpt-4o-mini for faster responses.
Running chains asynchronously with await chain.arun().
Streaming output by enabling streaming in ChatOpenAI.

python

import asyncio

async def async_chain():
    llm_async = ChatOpenAI(model_name="gpt-4o-mini", temperature=0, streaming=True, openai_api_key=os.environ["OPENAI_API_KEY"])
    chain_async = LLMChain(llm=llm_async, prompt=prompt)
    response = await chain_async.arun({"name": "Bob"})
    print(response)

asyncio.run(async_chain())

output

Hello, Bob!

Troubleshooting

If you see authentication errors, verify your OPENAI_API_KEY environment variable is set correctly.
If the chain returns unexpected output, check your prompt template syntax and input variables.
For rate limit errors, consider lowering request frequency or switching to a smaller model.

✅

Key Takeaways

Use ChatOpenAI and LLMChain to build simple chains easily.
Define prompts with ChatPromptTemplate and input variables for flexibility.
Leverage async and streaming features for advanced use cases.
Always set your API key securely via environment variables.
Test prompt templates carefully to ensure expected outputs.

Verified 2026-04 · gpt-4o, gpt-4o-mini

Verify ↗