langchain/templates/basic-critique-revise
2023-11-16 17:10:08 -08:00
..
basic_critique_revise Add basic critique revise template (#12688) 2023-11-09 17:33:29 -08:00
tests Add basic critique revise template (#12688) 2023-11-09 17:33:29 -08:00
LICENSE Add basic critique revise template (#12688) 2023-11-09 17:33:29 -08:00
poetry.lock IMPROVEMENT Allow openai v1 in all templates that require it (#13489) 2023-11-16 17:10:08 -08:00
pyproject.toml IMPROVEMENT Allow openai v1 in all templates that require it (#13489) 2023-11-16 17:10:08 -08:00
README.md Add basic critique revise template (#12688) 2023-11-09 17:33:29 -08:00

basic-critique-revise

TODO: What does this package do

Environment Setup

TODO: What environment variables need to be set (if any)

Usage

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

pip install -U "langchain-cli[serve]"

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

langchain app new my-app --package basic-critique-revise

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

langchain app add basic-critique-revise

And add the following code to your server.py file:

from basic_critique_revise import chain as basic_critique_revise_chain

add_routes(app, basic_critique_revise_chain, path="/basic-critique-revise")

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

export LANGCHAIN_TRACING_V2=true
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 http://127.0.0.1:8000/docs We can access the playground at http://127.0.0.1:8000/basic-critique-revise/playground

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/basic-critique-revise")