---
id: nvidia-nat-langchain
version: "1.8.0"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# nvidia-nat-langchain — Subpackage for LangChain/LangGraph integration in NeMo Agent Toolkit

License: permissive · Maintenance: active · Downloads: 250.2K/mo

## What it is and what it does

This is a subpackage that bridges LangChain/LangGraph with NVIDIA's NeMo Agent Toolkit, providing integration points for building agentic AI systems. It bundles 20 runtime dependencies including langchain core, multiple provider integrations (langchain-aws, langchain-openai, langchain-oci, langchain-huggingface, langchain-litellm), langgraph for workflow orchestration, langsmith for monitoring, and evaluation tools. The package targets Python 3.11–3.13 and is designed for developers building production AI agents that need to orchestrate multiple language models, retrieval systems, and tool integrations.

As a subpackage within the NeMo Agent Toolkit ecosystem, it provides the glue layer between LangChain's agent abstractions and NVIDIA's agent framework. The wide array of pre-included dependencies suggests it aims to reduce setup friction by bundling common integrations out of the box, though this also means a larger dependency tree that may pull in more than a minimal agent application needs.

Use it for:

- Build multi-agent systems that route queries to different LLM providers via langchain-aws, langchain-openai, langchain-oci, and langchain-huggingface
- Create retrieval-augmented generation pipelines with langchain-milvus vector storage and wikipedia knowledge sources
- Orchestrate complex agent workflows using langgraph state machines with observability via langsmith
- Integrate NVIDIA's AI endpoints via langchain-nvidia-ai-endpoints with LangChain's tool-calling and agent frameworks
- Evaluate agent performance and behavior using the bundled openevals framework

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Integrates LangChain and LangGraph with NVIDIA's NeMo Agent Toolkit to build agentic AI applications using multiple language model providers and retrieval-augmented generation.

Yes, if you are building agents within the NeMo Agent Toolkit ecosystem and want LangChain/LangGraph integration out of the box. The low install friction, active maintenance, and permissive Apache-2.0 license make it a safe choice. However, verify whether this subpackage can be used independently or requires the parent toolkit, and whether the 20 bundled dependencies align with your actual needs.

## Install

pip install nvidia-nat-langchain
uv add nvidia-nat-langchain
poetry add nvidia-nat-langchain

## Installing nvidia-nat-langchain

Before you install: Low install friction with a pure-Python wheel. Active maintenance status with recent releases; last commit 2026-08-12. Repository has 2576 stars and is not archived.

License in practice: Apache-2.0 permissive license allows commercial and private use with attribution; no restrictions on derivative works or linking.

Quickstart:

pip install nvidia-nat-langchain

from langchain_nvidia_ai_endpoints import ChatNVIDIA
from langchain import LLMChain

llm = ChatNVIDIA()
chain = LLMChain(llm=llm, prompt=...)

Requires Python 3.11 or later (supports 3.11, 3.12, 3.13). Verify that the parent NeMo Agent Toolkit is installed if this subpackage has a hard dependency on it.

Verify before relying:

- Whether this subpackage can be used standalone or requires the parent NeMo Agent Toolkit installation
- Specific version compatibility constraints between the 20 runtime dependencies
- Whether all listed providers (AWS, OCI, OpenAI, Hugging Face, LiteLLM) are optional or required for basic use

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 250.2K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

langchain langraph integration, nemo agent toolkit, rag agents framework, multi-provider llm agents, nvidia ai agent framework, agent-framework, rag, multi-provider-llm

[View on SkillFed](https://skillfed.io/packages/nvidia-nat-langchain) · [View on PyPI](https://pypi.org/project/nvidia-nat-langchain/)