Guarded RAG Assistant¶
Availability information
The Guarded RAG Assistant application template requires GenAI and MLOps functionality. If you do not currently have access to these features, sign up a 14-day DataRobot trial to try out this template.
Access this application template on GitHub
Build a RAG-powered chatbot using any knowledge base as its source. The Guarded RAG Assistant template logic contains prompt injection guardrails, sidecar models to evaluate responses, and a customizable interface that is easy to host and share.
Key features¶
- Business logic and LLM-based guardrails.
- A predictive secondary model that evaluates response quality.
- GenAI-focused custom metrics.
- DataRobot MLOps hosting, monitoring, and governing of the individual back-end deployments.
Architecture¶
Each template provides an end-to-end AI architecture, from raw inputs to deployed application, while remaining highly customizable for specific business requirements.
App Templates contain three families of complementary logic. For this template, you can opt-in to fully custom AI logic and a fully custom front-end or utilize DataRobot's off-the-shelf offerings:
-
AI logic: Necessary to service AI requests, generate predictions, and manage predictive models.
-
App logic: Necessary for user consumption, whether via a hosted front-end or integrating into an external consumption layer.
-
Operational logic: Necessary to turn on all DataRobot assets.
Warning
Application templates are intended to be starting points that provide guidance on how to develop, serve, and maintain AI applications. They require a developer or data scientist to adapt and modify them for their business requirements before being put into production.