A Python SDK that enables programmatic interaction with UiPath Cloud Platform services including processes, assets, buckets, context grounding, data services, jobs, and more. The package also features a CLI for creation, packaging, and deployment of automations to UiPath Cloud Platform.

Use the UiPath LangChain SDK to pack and publish LangGraph Agents.

Check out other UiPath Integrations to pack and publish agents built with LlamaIndex, OpenAI Agents, Google ADK, and more.

This quickstart guide walks you through deploying your first agent to UiPath Cloud Platform.

• Installation
• Configuration
  • Environment Variables
• Basic Usage
• Available Services
• Examples
  • Buckets Service
  • Context Grounding Service
• Command Line Interface (CLI)
  • Authentication
  • Initialize a Project
  • Debug a Project
  • Package a Project
  • Publish a Package
• Project Structure
• Development
  • Setting Up a Development Environment

pip install uipath

using uv:

uv add uipath

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

from uipath.platform import UiPath
# Initialize the SDK
sdk = UiPath()
# Execute a process
job = sdk.processes.invoke(
    name="MyProcess",
    input_arguments={"param1": "value1", "param2": 42}
)
# Work with assets
asset = sdk.assets.retrieve(name="MyAsset")

The SDK provides access to various UiPath services:

• sdk.processes - Manage and execute UiPath automation processes

• sdk.assets - Work with assets (variables, credentials) stored in UiPath

• sdk.buckets - Manage cloud storage containers for automation files

• sdk.connections - Handle connections to external systems

• sdk.context_grounding - Work with semantic contexts for AI-enabled automation

• sdk.jobs - Monitor and manage automation jobs

• sdk.queues - Work with transaction queues

• sdk.tasks - Work with Action Center

• sdk.api_client - Direct access to the API client for custom requests

# Download a file from a bucket
sdk.buckets.download(
    bucket_key="my-bucket",
    blob_file_path="path/to/file.xlsx",
    destination_path="local/path/file.xlsx"
)

# Search for contextual information
results = sdk.context_grounding.search(
    name="my-knowledge-index",
    query="How do I process an invoice?",
    number_of_results=5
)

The SDK also provides a command-line interface for creating, packaging, and deploying automations:

uipath auth

This command opens a browser for authentication and creates/updates your .env file with the proper credentials.

uipath init

The uipath.json file should include your entry points in the functions section:

{
  "functions": {
    "main": "main.py:main"
  }
}

Running uipath init will process these function definitions and create the corresponding entry-points.json file needed for deployment.

For more details on the configuration format, see the UiPath configuration specifications.

uipath run ENTRYPOINT [INPUT]

Executes a Python script 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 uipath.json file with your function definitions (e.g., "functions": {"main": "main.py:main"})
• A entry-points.json file (generated by uipath init)
• A bindings.json file (generated by uipath init) to configure resource overrides
• Any Python files needed for your automation

Check out uipath-dev - an interactive application for building, testing, and debugging UiPath Python runtimes, agents, and automation scripts.

Please read our contribution guidelines before submitting a pull request.