uipath-langchain-client

What it is and what it does

This package wraps LangChain's chat and embedding interfaces to route requests through UiPath's LLM infrastructure. It supports two modes: passthrough (vendor-specific APIs like OpenAI, Google, Anthropic, AWS Bedrock, Azure AI, and Fireworks) and normalized (a provider-agnostic interface). The factory functions automatically detect the model vendor and return the appropriate client, while direct class instantiation offers finer control. It depends on langchain and uipath-llm-client as runtime dependencies.

The package is designed for developers building LangChain applications within or alongside UiPath's automation platform. It handles streaming, tool binding, LangGraph agent integration, and model-specific features like extended thinking (OpenAI o1/o3 reasoning, Anthropic Claude thinking, Gemini thinking). Configuration options include retry behavior, request timeouts, and reasoning effort tuning.

Use it for:

• Build LangChain agents that invoke multiple LLM providers through a single UiPath gateway without managing separate API keys.
• Stream chat responses and embeddings from various providers using a unified interface within LangChain workflows.
• Bind tools and create ReAct agents with LangGraph that automatically route to the best available model via UiPath.
• Integrate extended reasoning models (o1, o3, Claude with thinking) into automation pipelines with consistent configuration.
• Switch between LLM providers (OpenAI to Anthropic to Google) without rewriting application code by using the normalized API mode.

Worth the install?

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

Provides LangChain-compatible chat models and embeddings that route requests through UiPath's LLM infrastructure, supporting multiple providers including OpenAI, Google, Anthropic, AWS Bedrock, Azure AI, and Fireworks.

Yes, with conditions. Install if you are already using UiPath's LLM infrastructure or plan to adopt it, and want a clean LangChain integration. The low install friction, active maintenance, and multi-provider support make it a solid choice for that use case. However, verify the license treatment before production use, and confirm that the normalized API mode meets your feature and stability requirements if you plan to use it.

Install

uipath-langchain-client on PyPI

pip install uipath-langchain-client

uv add uipath-langchain-client

poetry add uipath-langchain-client

Installing uipath-langchain-client

Before you install

Low install friction with a pure-wheel distribution and only two runtime dependencies (langchain and uipath-llm-client). Active maintenance with a release 8 days old. Optional provider extras allow minimal base installation.

License in practice

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

Quickstart

pip install uipath-langchain-client

from uipath_langchain_client import get_chat_model
from uipath_langchain_client.settings import get_default_client_settings

settings = get_default_client_settings()
chat_model = get_chat_model(model_name="gpt-4o-2024-11-20", client_settings=settings)
response = chat_model.invoke("Hello, how are you?")
print(response.content)

Requires Python 3.11 or later. Credentials and UiPath LLM service configuration must be available via environment variables or explicit settings.

Verify before relying

• Whether the normalized API mode (UiPathChat, UiPathEmbeddings) is production-ready or still experimental.
• Support status and SLA for the UiPath LLM gateway infrastructure.
• Whether streaming and tool-calling work equally across all provider backends or have provider-specific limitations.

Package facts

Evidence: uipath_langchain_client-1.17.3-py3-none-any.whl

Tags

More Artificial Intelligence packages