78 дней 4:14 Ollama and Cloud Run with GPUs
Get started with Cloud Run → goo.gle/4i5oGDB Ollama is the easiest way to get up and running on with large language models.
2 913
11.1
78 дней 5:35 Cloud Run functions with Gemma 2 and Ollama
Learn how to create a Cloud Run functions that talks to the Gemma 2 model hosted in the Ollama service.
681
15.9
78 дней 11:00 Running Diffusion with Cloud Run GPUs
See how quickly GPU support on Cloud Run scales up on demand with Stable Diffusion.
501
10.8
78 дней 5:28 Introduction to Gemini on Vertex AI
Getting started with Vertex AI Gemini 2.0 Flash → goo.gle/3D7UaZB Getting started with Vertex AI Gemini 1.5 Flash → goo.gle/4eZOL58 Getting started with Vertex AI Gemini 1.5 Pro →
15 029
20.6
83 дня 0:54 How do I know my AI app is working?
You’ve built an AI application but now you don’t know how to evaluate if it is effectively working. How do developers know if their AI applications are working effectively?
1 772
7.6
83 дня 8:49 How to evaluate AI applications
Vertex AI Evaluation Service Tutorial Notebooks → goo.gle/4i7vdxl How do developers know if their AI applications are working effectively? How can developers measure AI performance?
5 860
12.7
84 дня 8:29 Choosing between self-hosted GKE and managed Vertex AI to host AI models
Read the blog post → goo.gle/3V41A6f Vertex AI or Google Kubernetes Engine? Which platform is the best fit for unleashing the power of LLMs in your applications? Find out in this video.
831
12.8
84 дня 3:53 How to autoscale a TGI deployment on GKE
Tutorial: Configure autoscaling for TGI on GKE → goo.gle/3Z9a7WK Learn more about observability on GKE → goo.gle/4951bWY Hugging Face TGI (Text Generation Inference) →
1 245
13.5
88 дней 4:52 Looker Conversational Analytics
Conversational Analytics comes to Gemini → goo.gle/3Zh9sUt Query your data in natural language → goo.gle/3ARMNot Gemini in Looker → goo.gle/3ZgC1BC Unlock the power of your
6 413
14
89 дней 0:50 RAG expansion for AI apps
The expansion of material from documents and text (RAG expansion) is a method that powers a lot of information retrieval systems today.
2 155
10.5
89 дней 5:55 Using RAG expansion to improve model speed and accuracy
How Google Search serves pages → goo.gle/4fzNtOh Small to big rag (GitHub) → goo.gle/3ZgpcY1 Vertex AI embeddings and task types → goo.gle/40WFlTt Unlock the potential of
4 196
10.8
89 дней 8:50 Protecting sensitive data in AI apps
Discover essential strategies for safeguarding sensitive data in AI applications on this episode of Serverless Expeditions.
1 963
10.5
89 дней 9:21 Learn Hybrid Search with Vertex AI Vector Search
Notebook: Combining Semantic & Keyword Search: A Hybrid Search Tutorial with Vertex AI Vector Search → goo.gle/3YXW3zp Document: About hybrid search → goo.gle/40R9vrr Semantic
4 131
11.7
90 дней 4:01 Deploy HUGS on GKE with Hugging Face
Getting started with HUGS on Google Cloud → goo.gle/3OhK8aL HUGS in the Google Cloud Marketplace → goo.gle/3ZbVPG6 Blog: Introducing HUGS → goo.gle/4eCs5Xl Deploy open
1 729
11.4
95 дней 8:14 New "task type" embedding from the DeepMind team improves RAG search quality
Blog: Improve Gen AI Search with Vertex AI Embeddings and Task Types→ goo.gle/4equIeX Notebook: Using "task type" embeddings for improving RAG search quality→ goo.gle/4hlRtTO
4 339
8.9
95 дней 5:05 GKE Gemma 2 deployment with Hugging Face
Tutorial: Serve Gemma on GKE with TGI → goo.gle/4fFKt2Q Learn more about TGI (text generation inference) from Hugging Face → goo.gle/4e7qusz Hugging Face Deep Learning containers for
1 384
12.4
95 дней 0:43 What is an AI agent?
Dive into the world of AI agents in the latest episode of Real Terms for AI with Googlers Aja Hammerly and Jason Davenport.
2 436
8.6
96 дней 6:10 Intro to AI agents
Vertex AI Agent Builder quickstart → goo.gle/3UPJ7dN GenAI powered App with Genkit → goo.gle/4fCSTrK Demystifying AI agents, Googlers Aja Hammerly and Jason Davenport provide a
132 186
15.3
96 дней 11:39 RAG vs Model tuning vs Large prompt window
Take a dive into the three primary methods for integrating your data into AI applications: prompts with long context windows, Retrieval Augmented Generation (RAG), and model tuning.
3 473
8.1
97 дней 3:06 65K node Kubernetes AI Platform - A Reality
The size of generative AI models is constantly increasing, with current models reaching hundreds of billions of parameters and the most advanced ones approaching 2 trillion.
2 907
10.3
99 дней 4:50 Semantic modeling for AI
Looker's semantic layer provides a single source of truth → goo.gle/3YHALpz Gemini in Looker overview → goo.gle/4fmgq0f Gemini in Looker announcement → goo.gle/3YYQNwF In
4 628
11.5
102 дня 0:54 Function calling for LLMs, what is it? 🤔
Want to take your AI skills to the next level? Learn about "function calling" and unlock new possibilities for your code and external APIs.
3 433
7.2
102 дня 8:07 AI + your code: Function Calling
Function Calling with Vertex Tutorial (Notebook) → goo.gle/4dGvBzz Function Calling with Gemini API → goo.gle/4eEOLXR Tool Calling with Genkit →
17 454
13.1
103 дня 7:41 Deploy open models with TGI on Cloud Run
Tutorial: How to deploy Gemma 2 on Cloud Run with TGI → goo.gle/3Yoztjh Get started with Cloud Run GPU → goo.gle/4ec7mJS Docs: Text Generation Inference → goo.gle/4e7qusz
2 143
10.9
103 дня 11:34 RAG with LangChain on Google Cloud
Discover how to enhance the accuracy of your AI applications using Retrieval-Augmented Generation (RAG).
5 275
9.2
109 дней 4:04 Looker's Chart Config Editor & Visualization Assistant
Customized Looker charts → goo.gle/3YtK9NB Gemini in Looker → goo.gle/3Amc9uk Chart Config Editor → goo.gle/3AhvUDr Looker introduces two powerful features that
3 296
13.4
110 дней 0:38 Advanced RAG techniques for better retrieval performance
Unlock the full potential of Retrieval Augmented Generation (RAG) with advanced techniques or enhancing the quality of responses from large language models (LLMs).
2 840
7.5
110 дней 8:17 Advanced RAG techniques for developers
Advanced RAG Techniques→ goo.gle/4dQTxQP Combining Semantic & Keyword Search → goo.gle/3NuYQuz Task Type Embedding → goo.gle/3AfAlOS Unlock the full potential of Retrieval
24 232
10.6
110 дней 7:51 Prompt engineering for developers
Are you using chatbots and receiving high quality responses? It may be your prompt that is affecting the chatbot’s response. Take your generative AI skills to the next level by improving your prompts.
5 229
8.8
111 дней 4:08 How to run anything on Google Axion Processors
There are 7 types of workloads developers can migrate to run on Arm-based CPUs.
1 877
11.2