Tag: Gemini
-
Google Cloud Generative AI vs the Field, the Verdict (Google Cloud Gen AI Series, Part 30)
The closing scorecard on Google Cloud generative AI. Where Vertex AI and Gemini win, where they fall short, and how I would choose against AWS Bedrock and Azure AI Foundry in 2026.
-
Vertex AI Gen AI Evaluation Service, Pointwise to Trajectory (Google Cloud Gen AI Series, Part 23)
The Vertex AI Gen AI evaluation service turns a two-example spot check into a number you can gate a release on. How pointwise, pairwise, rubric, and trajectory metrics work, and how to validate the autorater judge before you trust it.
-
Distilling Gemini on Vertex AI, from Teacher to Student Model (Google Cloud Gen AI Series, Part 17)
Distillation trains a small Gemini student to copy a large teacher, so the teacher writes the labels and you serve the result at Flash prices. When it pays, what it costs, and where it fails.
-
Fine-Tuning Gemini with Supervised Tuning on Vertex AI (Google Cloud Gen AI Series, Part 16)
Supervised fine-tuning on Vertex AI adjusts Gemini to your task with a few hundred labelled examples, and because it uses LoRA the tuned model costs the same to run as the base. Here is when to tune, how to build the dataset, the knobs that matter, and what it costs.
-
Grounding Gemini with Google Search and Your Own Data (Google Cloud Gen AI Series, Part 15)
How to ground Gemini on Vertex AI against the live web and your own Vertex AI Search data store, read the grounding metadata, render citations correctly, and size what it costs.
-
Calling Gemini Models with the API, Streaming, and Function Calling (Google Cloud Gen AI Series, Part 11)
The legacy Vertex AI generative SDK was removed in June 2026, so every Gemini call now goes through one library. Here is how to call a model, stream the answer, and wire function calling without letting it run away with your latency.
-
Vertex AI Regions, Quotas, and the Global Endpoint (Google Cloud Gen AI Series, Part 8)
How Vertex AI locations, regional versus global endpoints, and Dynamic Shared Quota decide your latency, data residency, and 429 rate, with a clear default and a worked region choice.
-
Vertex AI Pricing, Provisioned Throughput, and Context Caching (Google Cloud Gen AI Series, Part 6)
A working architect’s breakdown of what you really pay for on Vertex AI: on-demand token rates, Provisioned Throughput and the GSU, context caching, and batch, with a worked cost example you can run.
-
Vertex AI vs the Gemini API in AI Studio, and When to Switch (Google Cloud Gen AI Series, Part 5)
Google AI Studio and Vertex AI are two doors to the same Gemini models. Here is what actually changes between them on auth, data governance, quotas and price, and exactly when to move from one to the other.
-
Gemini Flash vs Pro, and When to Pay for Reasoning (Google Cloud Gen AI Series, Part 3)
Flash or Pro? On Vertex AI the two Gemini tiers differ by about 4x on output tokens. Here is how to pick per request and route only the hard ones to Pro.
-
Vertex AI and Model Garden, from Catalog to Endpoint (Google Cloud Gen AI Series, Part 2)
Vertex AI is Google Cloud’s managed platform and Model Garden is its 200-plus model catalog. Here is how the three access paths, managed API, MaaS, and self-deploy, decide your cost, latency, and data isolation, and which one to start on.
-
Google Cloud Generative AI Stack, End to End (Google Cloud Gen AI Series, Part 1)
A map of the Google Cloud generative AI stack in 2026, from Gemini Enterprise Agent Platform (the service that used to be Vertex AI) down to Ironwood TPUs, and where a real project plugs in.
Architect’s Toolkit
PJ’s Tools
VMware Cloud Foundation
- VCF Documentation
- VCF 9 Planning & Preparation Workbook
- VCF Bill of Materials (BoM)
- VMware Compatibility Guide
- VMware Interoperability Matrix
- VMware Configuration Maximums
- VMware Ports & Protocols
- VMware Hands-on Labs
- RVTools Download
Nutanix
AI & Cloud-Native Platform
- NVIDIA Build (Model Catalog)
- NVIDIA AI Enterprise Reference Architecture
- NVIDIA NIM Performance Benchmarking
- NVIDIA NGC Catalog
- NeMo Microservices Helm Chart
- Helm Charts Repository
- Hugging Face Models
Architecture & Design
About the Author
Dr Pranay Jha
Dr. Pranay Jha is a Cloud and AI Consultant with 18+ years of experience in hybrid cloud, virtualization, and enterprise infrastructure transformation. He specializes in VMware technologies, multi-cloud strategy, and Generative AI solutions. He holds a PhD in Computer Applications with research focused on Cloud and AI, has published multiple research papers, and has been a VMware vExpert since 2016 and a VMUG Community Leader.
You May Have Missed
DrJha