langchain/templates/vertexai-chuck-norris
2024-01-06 18:31:46 -08:00
..
tests TEMPLATE Add VertexAI Chuck Norris template (#13531) 2023-11-17 12:27:52 -08:00
vertexai_chuck_norris templates: fix deps (#15439) 2024-01-03 13:28:05 -08:00
LICENSE TEMPLATE Add VertexAI Chuck Norris template (#13531) 2023-11-17 12:27:52 -08:00
poetry.lock templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
pyproject.toml templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
README.md TEMPLATE Add VertexAI Chuck Norris template (#13531) 2023-11-17 12:27:52 -08:00

vertexai-chuck-norris

This template makes jokes about Chuck Norris using Vertex AI PaLM2.

Environment Setup

First, make sure you have a Google Cloud project with an active billing account, and have the gcloud CLI installed.

Configure application default credentials:

gcloud auth application-default login

To set a default Google Cloud project to use, run this command and set the project ID of the project you want to use:

gcloud config set project [PROJECT-ID]

Enable the Vertex AI API for the project:

gcloud services enable aiplatform.googleapis.com

Usage

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 pirate-speak

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

langchain app add vertexai-chuck-norris

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

from vertexai_chuck_norris.chain import chain as vertexai_chuck_norris_chain

add_routes(app, vertexai_chuck_norris_chain, path="/vertexai-chuck-norris")

(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/vertexai-chuck-norris/playground

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/vertexai-chuck-norris")