langchain/templates/robocorp-action-server
Erick Friis 551640a030
templates: remove lockfiles (#22920)
poetry will default to latest versions without
2024-06-14 21:42:30 +00:00
..
robocorp_action_server
tests
.gitignore
LICENSE
pyproject.toml templates, cli: more security deps (#19006) 2024-03-12 20:48:56 -07:00
README.md templates: readme langsmith not private beta (#20173) 2024-04-12 13:08:10 -07:00

Langchain - Robocorp Action Server

This template enables using Robocorp Action Server served actions as tools for an Agent.

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 robocorp-action-server

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

langchain app add robocorp-action-server

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

from robocorp_action_server import agent_executor as action_server_chain

add_routes(app, action_server_chain, path="/robocorp-action-server")

Running the Action Server

To run the Action Server, you need to have the Robocorp Action Server installed

pip install -U robocorp-action-server

Then you can run the Action Server with:

action-server new
cd ./your-project-name
action-server start

Configure LangSmith (Optional)

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_TRACING_V2=true
export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"

Start LangServe instance

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/robocorp-action-server/playground

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/robocorp-action-server")