Skip to main content
LangChain is a popular framework for building LLM-powered applications. Connect it to Lightweight using the ChatOpenAI class with a custom base_url.

​
Installation

pip install langchain-openai

​
Usage

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="claude-sonnet-4.5",
    api_key="lw_sk_your-key-here",
    base_url="https://api.lightweight.one/v1"
)

response = llm.invoke("What is the capital of France?")
print(response.content)

​
With Chains

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

llm = ChatOpenAI(
    model="gpt-5.4",
    api_key="lw_sk_your-key-here",
    base_url="https://api.lightweight.one/v1"
)

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant that translates {input_language} to {output_language}."),
    ("human", "{input}")
])

chain = prompt | llm
response = chain.invoke({
    "input_language": "English",
    "output_language": "French",
    "input": "Hello, how are you?"
})

print(response.content)

​
Streaming

for chunk in llm.stream("Write a poem about coding"):
    print(chunk.content, end="", flush=True)
Because Lightweight is OpenAI-compatible, any LangChain component that uses ChatOpenAI will work. Swap models by changing the model parameter — see the full catalog.