Workbench Example Agentic Rag

Agentic RAG - Web Search with Accuracy and Hallucination Controls

Boost RAG with an Agentic Layer

• Route: Checks the RAG context for relevance to the query and adds live web search if the context is thin
• Evaluate: Checks responses for relevance and accuracy, flags hallucinations
• Iterate: Goes through multiple evaluation and generation cycles

Modify Agentic RAG

• Edit Prompts: Customize results through your own prompts
• Change Parameters: Adjust agent behavior through parameters and runtime variables
• Look and Feel: Change the agent and UI by editing the code yourself

Inference Your Way

• Free Endpoints: use free endpoints on build.nvidia.com
• Self-Hosted: Point to Ollama or NIM on your own GPUs

Get Started

This README has three modes:

• Easy Mode: Use the application
• Intermediate Mode: Modify the application
• Advanced Mode: Self-host gpus for inference

Prerequisites - AI Workbench and an Internet Connection

You can run Agentic RAG without Workbench, but this README requires [NVIDIA AI Workbench](https://www.nvidia.com/en-us/deep-learning-ai/solutions/data-science/workbench/) installed. See [how to install it here](https://docs.nvidia.com/ai-workbench/user-guide/latest/installation/overview.html).

You need internet because Agentic RAG uses an NVIDIA endpoint for document embedding.

Easy Mode (< 5 minutes if Workbench installed)

1. Get NVIDIA and Tavily API keys:
   • NVIDIA_API_KEY → Generate See instructions here.
   • TAVILY_API_KEY → Generate
2. Clone this repo with AI Workbench > configure the keys when prompted.
3. Click Open Chat > Go to the *Document