Skip to main content
Version: 2.0.0

LLMWhisperer On-Prem Edition

LLMWhisperer On-Prem Edition is deployed inside your own infrastructure (AWS, Azure, or GCP) as a Kubernetes Helm chart, ensuring your data never leaves your environment. It is ideal for organizations with strict data residency, compliance, or security requirements.

Key Features​

  • Same feature set as LLMWhisperer Cloud Edition
  • Data stays within your VPC — documents are processed entirely within your infrastructure
  • Kubernetes-native deployment via Helm charts
  • Configurable node profiles — resource allocation and scaling configuration
  • GPU support for document insights mode
  • LLMWhisperer Dashboard bundled for usage monitoring and management

Deployment​

For comprehensive instructions on deploying LLMWhisperer in your on-premises environment, including infrastructure prerequisites, Helm chart configuration, and post-deployment validation, see the On-Prem Deployment Guide.

Version History​

For on-prem release versions and changelogs, see the On-Prem Version History.