Skip to main content
WRITER is a platform to generate different language content. This example goes over how to use LangChain to interact with WRITER models.

Setup

To access WRITER models you’ll need to create a WRITER account, get an API key, and install the writer-sdk and langchain-community packages.

Credentials

Head to WRITER AI Studio to sign up for WRITER and generate an API key. Once you’ve done this set the WRITER_API_KEY environment variable:
import getpass
import os

if not os.environ.get("WRITER_API_KEY"):
    os.environ["WRITER_API_KEY"] = getpass.getpass("Enter your Writer API key:")

Installation

The LangChain WRITER integration lives in the langchain-community package:
pip install -qU langchain-community writer-sdk
Now we can initialize our model object to interact with writer LLMs
from langchain_community.llms import Writer as WriterLLM

llm = WriterLLM(
    temperature=0.7,
    max_tokens=1000,
    # other params...
)

Invocation

response_text = llm.invoke(input="Write a poem")
print(response_text)

Streaming

stream_response = llm.stream(input="Tell me a fairytale")
for chunk in stream_response:
    print(chunk, end="")

Async

WRITER support asynchronous calls via ainvoke() and astream() methods

API reference

For detailed documentation of all WRITER features, head to our API reference.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.