5 дней 5:30 Agentic AI: Workflows vs. agents
Building a research multi agent system → goo.gle/41TYswp Agent starter pack → goo.gle/4iZiz35 Human-in-the-Loop LangGraph app → goo.gle/4iyii7h What is agentic AI and how
27 836
9.7
6 дней 2:56 Function calling with the Gemini API
Intro to function calling → goo.gle/3Cm13Gc Function calling tutorial → goo.gle/40AUzgK Extract structured data using function calling → goo.gle/48A7FgA Unlock the power
4 216
6.1
6 дней 0:19 Connect your language model with external systems and APIs
With function calling, you can teach Gemini to use tools and create truly interactive and powerful applications.
1 970
5.4
12 часов 4:34 How Improving Aviation uses Gemini and Google Cloud to predict and combat wildfires
Wildfires are a growing threat, but what if we could predict them with near real-time accuracy?
942
5.9
6 дней 2:10 Fine-tuning use cases
Discover the top 5 use cases for fine-tuning a foundation model. In this video, you'll learn how this powerful technique allows you to tailor pre-trained models to your specific needs.
784
3.7
3 дня 6:55 Understanding and unifying Looker and Looker Studio
Looker Shared terms and concepts → goo.gle/41hI4XF Join the Looker community → goo.gle/3QjggM4 Learn the key differences between Looker and Looker Studio.
91
10.8
6 часов 2:14 Cluster toolkit: The secret to making AI setup easy
See the detailed reference architecture → goo.gle/4iqFyo2 Learn how to use the open-source Cluster Toolkit and get pre-built blueprints and modules for rapid, repeatable cluster deployments.
29
6 часов 3:05 Cloud Load Balancer, the secret to uptime for AI inference
See the detailed reference architecture → goo.gle/4bLQdap Learn how to pair new cloud load balancing capabilities like custom metrics and service extensions with GKE Autopilot, which
22
6 часов 2:57 The secret to cost-efficient AI inference
See the detailed reference architecture → goo.gle/4bKh5aR Learn how to use JAX, Google Kubernetes Engine (GKE) and NVIDIA Triton Inference Server as a winning combination for low cost AI
10
6 часов 0:49 Cost-efficient AI inference
Learn how to use JAX, Google Kubernetes Engine (GKE) and NVIDIA Triton Inference Server as a winning combination for low cost AI inference.
9
6 часов 2:23 Hypercomputer Clusters: The secret to AI training at Google scale
See the detailed reference architecture → goo.gle/4isJtkc Learn how to use Hypercompute Cluster to train models using physically co-located accelerators, targeted workload placement
4
6 часов 0:38 Develop with AI Hypercomputer
Learn how to pair new cloud load balancing capabilities like custom metrics and service extensions with GKE Autopilot, which includes features like node auto-repair to automatically replace
3
6 часов 0:32 The secret to AI training at Google scale
Learn how to use Hypercompute Cluster to train models using physically co-located accelerators, targeted workload placement, advanced maintenance controls to minimize workload disruption, and
2
13 видео