uipath-llm-client

What it is and what it does

UiPath LLM Client is a Python library that wraps UiPath's LLM infrastructure, allowing you to send requests to multiple LLM providers (OpenAI, Google, Anthropic, AWS Bedrock, Fireworks AI, Azure AI) through UiPath's managed backends. It provides both a low-level HTTP client with built-in authentication, retry logic, and request handling, and a separate LangChain-compatible integration for chat models and embeddings. The package supports three backend modes: AgentHub (default, CLI-based authentication), Orchestrator (same auth as AgentHub but different routing), and LLMGateway (S2S authentication). You configure it via environment variables or direct instantiation, and it handles token refresh and endpoint selection automatically.

The client is designed for teams already using UiPath's platform infrastructure who want to integrate LLM capabilities without managing provider credentials directly. It abstracts away backend selection and authentication complexity, making it suitable for enterprise automation workflows, agent-based systems, and applications that need to route LLM requests through a centralized gateway.

Use it for:

• Route LLM requests through UiPath AgentHub for model discovery, routing, and tracing in RPA workflows.
• Use LangChain-compatible chat models and embeddings within UiPath Orchestrator automation jobs.
• Access multiple LLM providers (OpenAI, Google, Anthropic, AWS Bedrock) via a single unified client.
• Integrate LLM capabilities into UiPath agent-based systems with automatic CLI-based authentication.
• Send requests to LLMGateway backend with S2S authentication for enterprise multi-tenant deployments.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

A Python client for accessing LLMs through UiPath's infrastructure, supporting multiple backends (AgentHub, Orchestrator, LLMGateway) and providers (OpenAI, Google, Anthropic, AWS Bedrock, Fireworks AI, Azure AI) with optional LangChain integration.

Yes, if you are already using UiPath's platform and need LLM integration. The package is actively maintained, has low install friction, and supports multiple backends and providers. However, verify the license terms first — the license status is unclear in the metadata, which is a blocker for some use cases. No known security vulnerabilities as of the latest scan.

Install

uipath-llm-client on PyPI

pip install uipath-llm-client

uv add uipath-llm-client

poetry add uipath-llm-client

Installing uipath-llm-client

Before you install

Low friction installation with a pure Python wheel. Actively maintained with a release just 1 day old. Depends on standard libraries (httpx, pydantic, tenacity, uipath-platform) with no compiled dependencies.

License in practice

License status is unclear — no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms before use in proprietary or copyleft-sensitive projects.

Quickstart

pip install uipath-llm-client

from uipath.llm_client.settings import get_default_client_settings

# Authenticate via CLI first: uipath auth login
settings = get_default_client_settings(backend="agenthub")
# settings now contains access_token, base_url, tenant_id, organization_id

Requires Python 3.11 or later. UiPath CLI authentication (uipath auth login) must be run first to populate .uipath/.auth.json, or environment variables (UIPATH_URL, UIPATH_ORGANIZATION_ID, UIPATH_TENANT_ID, UIPATH_ACCESS_TOKEN) must be set manually.

Verify before relying

• Whether the package is open-source or proprietary; license clarity needed before production deployment.
• Documentation availability and completeness for both core client and LangChain integration.
• Support status and SLA for the UiPath backends (AgentHub, Orchestrator, LLMGateway).

Package facts

Evidence: uipath_llm_client-1.17.2-py3-none-any.whl

Tags

More Artificial Intelligence packages