Skip to content

installing.md

Latest commit

 

History

History
178 lines (129 loc) · 7.44 KB

installing.md

File metadata and controls

178 lines (129 loc) · 7.44 KB

Installing NVIDIA NeMo Agent Toolkit

This guide will help you set up your NVIDIA NeMo Agent toolkit development environment, run existing workflows, and create your own custom workflows using the aiq command-line interface.

Supported LLM APIs

The following LLM APIs are supported:

  • NIM (such as Llama-3.1-70b-instruct and Llama-3.3-70b-instruct)
  • OpenAI
  • AWS Bedrock

Framework Integrations

To keep the library lightweight, many of the first-party plugins supported by NeMo Agent toolkit are located in separate distribution packages. For example, the aiqtoolkit-langchain distribution contains all the LangChain-specific plugins and the aiqtoolkit-mem0ai distribution contains the Mem0-specific plugins.

To install these first-party plugin libraries, you can use the full distribution name (for example, aiqtoolkit-langchain) or use the aiqtoolkit[langchain] extra distribution. The following extras are supported:

  • aiqtoolkit[agno] or aiqtoolkit-agno - Agno specific plugins
  • aiqtoolkit[crewai] or aiqtoolkit-crewai - CrewAI specific plugins
  • aiqtoolkit[langchain] or aiqtoolkit-langchain - LangChain specific plugins
  • aiqtoolkit[llama-index] or aiqtoolkit-llama-index - LlamaIndex specific plugins
  • aiqtoolkit[mem0ai] or aiqtoolkit-mem0ai - Mem0 specific plugins
  • aiqtoolkit[semantic-kernel] or aiqtoolkit-semantic-kernel - Microsoft Semantic Kernel specific plugins
  • aiqtoolkit[test] or aiqtoolkit-test - NeMo Agent toolkit test specific plugins
  • aiqtoolkit[weave] or aiqtoolkit-weave - Weights & Biases Weave specific plugins
  • aiqtoolkit[zep-cloud] or aiqtoolkit-zep-cloud - Zep specific plugins

Prerequisites

NVIDIA NeMo Agent toolkit is a Python library that doesn't require a GPU to run the workflow by default. You can deploy the core workflows using one of the following:

  • Ubuntu or other Linux distributions, including WSL, in a Python virtual environment.

Before you begin using NeMo Agent toolkit, ensure that you meet the following software prerequisites:

Install From Source

  1. Clone the NeMo Agent toolkit repository to your local machine.

    git clone git@github.com:NVIDIA/AIQToolkit.git aiqtoolkit
cd aiqtoolkit

  2. Initialize, fetch, and update submodules in the Git repository.

    git submodule update --init --recursive

  3. Fetch the data sets by downloading the LFS files.

    git lfs install
git lfs fetch
git lfs pull

  4. Create a Python environment.

    uv venv --seed .venv
source .venv/bin/activate

  5. Install the NeMo Agent toolkit library. To install the NeMo Agent toolkit library along with all of the optional dependencies. Including developer tools (--all-groups) and all of the dependencies needed for profiling and plugins (--all-extras) in the source repository, run the following:

    uv sync --all-groups --all-extras

    Alternatively to install just the core NeMo Agent toolkit without any plugins, run the following:

    uv sync

    At this point individual plugins, which are located under the packages directory, can be installed with the following command uv pip install -e '.[<plugin_name>]'. For example, to install the langchain plugin, run the following:

    uv pip install -e '.[langchain]'

    :::{note} Many of the example workflows require plugins, and following the documented steps in one of these examples will in turn install the necessary plugins. For example following the steps in the examples/basic/functions/simple/README.md guide will install the aiqtoolkit-langchain plugin if you haven't already done so. :::

    In addition to plugins, there are optional dependencies needed for profiling. To install these dependencies, run the following:

    uv pip install -e '.[profiling]'

  6. Verify that you've installed the NeMo Agent toolkit library.

    aiq --help
aiq --version

    If the installation succeeded, the aiq command will log the help message and its current version.

Obtaining API Keys

Depending on which workflows you are running, you may need to obtain API keys from the respective services. Most NeMo Agent toolkit workflows require an NVIDIA API key defined with the NVIDIA_API_KEY environment variable. An API key can be obtained by visiting build.nvidia.com and creating an account.

Running Example Workflows

Before running any of the NeMo Agent toolkit examples, set your NVIDIA API key as an environment variable to access NVIDIA AI services.

export NVIDIA_API_KEY=<YOUR_API_KEY>

:::{note} Replace <YOUR_API_KEY> with your actual NVIDIA API key. :::

Running the Simple Workflow

  1. Install the aiq_simple Workflow

    uv pip install -e examples/basic/functions/simple

  2. Run the aiq_simple Workflow

    aiq run --config_file=examples/basic/functions/simple/configs/config.yml --input "What is LangSmith"

  3. Run and evaluate the aiq_simple Workflow

    The eval_config.yml YAML is a super-set of the config.yml containing additional fields for evaluation. To evaluate the aiq_simple workflow, run the following command:

    aiq eval --config_file=examples/basic/functions/simple/configs/eval_config.yml

NeMo Agent Toolkit Packages

Once an NeMo Agent toolkit workflow is ready for deployment to production, the deployed workflow will need to declare a dependency on the aiqtoolkit package, along with the needed plugins. When declaring a dependency on NeMo Agent toolkit it is recommended to use the first two digits of the version number. For example if the version is 1.0.0 then the dependency would be 1.0.

For more information on the available plugins, refer to Framework Integrations.

Example dependency for NeMo Agent toolkit using the langchain plugin for projects using a pyproject.toml file:

dependencies = [
"aiqtoolkit[langchain]~=1.0",
# Add any additional dependencies your workflow needs
]

Alternately for projects using a requirements.txt file:

aiqtoolkit[langchain]==1.0.*

Next Steps

  • Explore the examples in the examples directory to learn how to build custom workflows and tools with NeMo Agent toolkit.
  • Review the NeMo Agent toolkit tutorials for detailed guidance on using the toolkit.