Skip to main content


Implements "Skeleton of Thought" from this paper.

This technique makes it possible to generate longer generations more quickly by first generating a skeleton, then generating each point of the outline.

Environment Setup​

Set the OPENAI_API_KEY environment variable to access the OpenAI models.

To get your OPENAI_API_KEY, navigate to API keys on your OpenAI account and create a new secret key.


To use this package, you should first have the LangChain CLI installed:

pip install -U langchain-cli

To create a new LangChain project and install this as the only package, you can do:

langchain app new my-app --package skeleton-of-thought

If you want to add this to an existing project, you can just run:

langchain app add skeleton-of-thought

And add the following code to your file:

from skeleton_of_thought import chain as skeleton_of_thought_chain

add_routes(app, skeleton_of_thought_chain, path="/skeleton-of-thought")

(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. You can sign up for LangSmith here. If you don't have access, you can skip this section

export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"

If you are inside this directory, then you can spin up a LangServe instance directly by:

langchain serve

This will start the FastAPI app with a server is running locally at http://localhost:8000

We can see all templates at We can access the playground at

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/skeleton-of-thought")

Was this page helpful?

You can also leave detailed feedback on GitHub.