Karini AI Documentation
Go Back to Karini AI
  • Introduction
  • Installation
  • Getting Started
  • Organization
  • User Management
    • User Invitations
    • Role Management
  • Model Hub
    • Embeddings Models
    • Large Language Models (LLMs)
  • Prompt Management
    • Prompt Templates
    • Create Prompt
    • Test Prompt
      • Test & Compare
      • Prompt Observability
      • Prompt Runs
    • Agentic Prompts
      • Create Agent Prompt
      • Test Agent Prompt
    • Prompt Task Types
    • Prompt Versions
  • Datasets
  • Recipes
    • QnA Recipe
      • Data Storage Connectors
      • Connector Credential Setup
      • Vector Stores
      • Create Recipe
      • Run Recipe
      • Test Recipe
      • Evaluate Recipe
      • Export Recipe
      • Recipe Runs
      • Recipe Actions
    • Agent Recipe
      • Agent Recipe Configuration
      • Set up Agentic Recipe
      • Test Agentic Recipe
      • Agentic Evaluation
    • Databricks Recipe
  • Copilots
  • Observability
  • Dashboard Overview
    • Statistical Overview
    • Cost & Usage Summary
      • Spend by LLM Endpoint
      • Spend by Generative AI Application
    • Model Endpoints & Datasets Distribution
    • Dataset Dashboard
    • Copilot Dashboard
    • Model Endpoints Dashboard
  • Catalog Schemas
    • Connectors
    • Catalog Schema Import and Publication Process
  • Prompt Optimization Experiments
    • Set up and execute experiment
    • Optimization Insights
  • Generative AI Workshop
    • Agentic RAG
    • Intelligent Document Processing
    • Generative BI Agentic Assistant
  • Release Notes
Powered by GitBook
On this page
  • AWS Commercial Releases
  • Sentinel Release Notes
  • CoreML Release Notes
  • AWS GovCloud Releases

Release Notes

AWS Commercial Releases

Sentinel Release Notes

v1.6.217 (April 15, 2025)

  • Enhanced Data Management & Export: Added export functionality for catalog data (JSON/CSV), new recipe output options for S3, Knowledge Base and Knowledge Graph, and improved metadata extraction with OpenSearch schema.

  • Model Thinking Capabilities: Introduced "Thinking Lens" feature for model processing insights and new "thinkerForm" for managing advanced thinking settings.

  • Improved User Experience: Enhanced tooltips, form descriptions, dashboard labels with multiline support, and added multiple user invitations with comma-separated emails.

  • Bug Fixes & Access Controls: Resolved duplicate name checks in connectors and prompt experiments (case-insensitive), and fixed uniqueness checks for power users to consider only current user's items.

  • New Administrative Tools: Added bug report management interface, webhook usage monitoring dashboard, and tool configuration with Neo4j and Neptune provider selection.

CoreML Release Notes

v1.8.86 (May 3, 2025)

  • Expanded Document Processing Capabilities: Added support for PowerPoint, Excel, and legacy Word (.doc) files, along with enhanced file type detection, metadata processing, and chunking mechanisms.

  • New Connectivity Options: Introduced SharePoint connector, PostgreSQL database connection testing endpoint, and fixed Box connector token errors and UTF-8 handling issues.

  • Enhanced AI Model Support: Added several new LLM models including Amazon Nova Premier v1, Meta Llama 4 series, and multiple OpenAI models (GPT 4.1, 4.1 Mini, 4.1 Nano, O4 Mini, O3, GPT 4.5 Preview) with expanded context length limits.

  • Knowledge Graph Improvements: Enhanced Neptune knowledge graph tools and improved Gremlin query handling for more sophisticated data relationships.

  • DevOps Enhancements: Introduced automation workflow for Docker image building and deployment in staging environments, improving the development pipeline.

  • System Stability & Performance: Implemented various stability enhancements, performance optimizations, and bug fixes across multiple releases, particularly focusing on production deployment reliability.

AWS GovCloud Releases

PreviousGenerative BI Agentic Assistant

Last updated 16 hours ago