About NVIDIA Agent Intelligence Toolkit Workflows#
Workflows are the heart of AIQ toolkit because they define which agentic tools and models are used to perform a given task or series of tasks.
Understanding the Workflow Configuration File#
The workflow configuration file is a YAML file that specifies the tools and models to use in a workflow, along with general configuration settings. This section examines the configuration of the examples/simple workflow to show how they’re organized.
examples/simple/configs/config.yml:
functions:
webpage_query:
_type: webpage_query
webpage_url: https://docs.smith.langchain.com
description: "Search for information about LangSmith. For any questions about LangSmith, you must use this tool!"
embedder_name: nv-embedqa-e5-v5
chunk_size: 512
current_datetime:
_type: current_datetime
llms:
nim_llm:
_type: nim
model_name: meta/llama-3.1-70b-instruct
temperature: 0.0
embedders:
nv-embedqa-e5-v5:
_type: nim
model_name: nvidia/nv-embedqa-e5-v5
workflow:
_type: react_agent
tool_names: [webpage_query, current_datetime]
llm_name: nim_llm
verbose: true
retry_parsing_errors: true
max_retries: 3
This workflow configuration is divided into four sections: functions, llms, embedders, and workflow. The functions section contains the tools used in the workflow, while llms and embedders define the models used in the workflow, and lastly the workflow section ties the other sections together and defines the workflow itself.
In this workflow the webpage_query tool is used to query the LangSmith User Guide, and the current_datetime tool is used to get the current date and time. The description entry is what is used to instruct the LLM when and how to use the tool. In this case, the description is explicitly defined for the webpage_query tool.
The webpage_query tool makes use of the nv-embedqa-e5-v5 embedder, which is defined in the embedders section.
For details on workflow configuration, including sections not utilized in the above example, refer to the Workflow Configuration document.