A Python SDK that enables developers to build and deploy LangGraph agents to the UiPath Cloud Platform. This package provides programmatic interaction with UiPath Cloud Platform services and human-in-the-loop (HITL) semantics through Action Center integration.
This package is an extension to the UiPath Python SDK.
This quickstart guide walks you through deploying your first agent to UiPath Cloud Platform.
Check out these sample projects to see the SDK in action.
- Python 3.10 or higher
- UiPath Automation Cloud account
pip install uipath-langchain
using uv
:
uv add uipath-langchain
Create a .env
file in your project root with the following variables:
UIPATH_URL=https://cloud.uipath.com/ACCOUNT_NAME/TENANT_NAME
UIPATH_ACCESS_TOKEN=YOUR_TOKEN_HERE
The SDK provides a command-line interface for creating, packaging, and deploying LangGraph Agents:
uipath init [GRAPH]
Creates a uipath.json
configuration file for your project. If [GRAPH]
is omitted, it will create an entrypoint for each graph specified in the langgraph.json
file.
uipath auth
This command opens a browser for authentication and creates/updates your .env
file with the proper credentials.
uipath run GRAPH [INPUT]
Executes the agent with the provided JSON input arguments.
uipath pack
Packages your project into a .nupkg
file that can be deployed to UiPath.
Note: Your pyproject.toml
must include:
- A description field (avoid characters: &, <, >, ", ', ;)
- Author information
Example:
description = "Your package description"
authors = [{name = "Your Name", email = "[email protected]"}]
uipath publish
Publishes the most recently created package to your UiPath Orchestrator.
To properly use the CLI for packaging and publishing, your project should include:
- A
pyproject.toml
file with project metadata - A
langgraph.json
file - A
uipath.json
file (generated byuipath init
) - Any Python files needed for your automation
Please read our contribution guidelines before submitting a pull request.