engblogs

Enhance productivity with Databricks Assistant using exclusively Databricks-hosted models and Model Serving endpoints.

Streamline IAM setup on GKE with Workload Identity Federation

Guide to effectively handling 429 errors with Large Language Models (LLMs) using backoff, retry logic, dynamic shared quota, and provisioned throughput

Introducing Mistral AI’s latest models, Large-Instruct-2411 and Codestral-2411, on Vertex AI for advanced language and code generation tasks.

Fine-tune large language models with Amazon SageMaker Autopilot for automating the training and deployment process of pre-trained models on specific tasks using AutoMLV2 SDK.

Enhancing knowledge management with generative AI and AWS services for VW's production domain

Practical approach for incorporating responsible AI guardrails into Amazon Bedrock Batch Inference workflows with step-by-step guidance

Implement audio and video segmentation solution for enhancing speech synthesis and video generation models with detailed human feedback using SageMaker Ground Truth

Integrate notebook insights into polished AI/BI dashboards effortlessly

Examining the resilience of Internet connectivity in Europe amidst multiple cable cuts.

Exploring the exponential growth of DDoS attack sizes over the past decade and its implications on cyber defense strategies.

Empowering Data Governance Transformation with Unity Catalog at bp