404 issue with Vertex AI - gemini-2.5-flash and europe-west2
I am getting a 404 error when trying to trigger gemini-2.5-flash from europe-west2, using Vertex AI.The code w...
AI/ML
Have questions around Artificial Intelligence or Machine Learning? This is the place to ask questions about all things AI and ML, including products like AutoML, Vertex AI, AI Infrastructure, and more.
Forum Posts
Attaching metadata to chunks in Rag Engine
I have a .jsonl file stored in Google Cloud Storage, and I want to ensure that metadata values are properly at...
Calling Vertex AI ADK Agent via api
Hi team,I tested deploying my agent to Vertex AI Agent Engine and able to query by listing/getting sessions an...
Vertex AI using gemini-2.5-flash in europe-west2
I have some code that hits the Vertex AI endpoint but need to keep it region specific.I am using the London re...
Stuck in Vertex AI Studio Express — Cannot Access Google Cloud Console
Hi everyone,I’m facing a critical issue with my Google Cloud account, and I’ve already seen a few other users ...
Global GPU Instances quota denied
https://cloud.google.com/compute/docs/gpus/about-gpus#restrictionsQuota increases for the Global GPU Instances...
Issue Integrating Dialogflow CX with Twilio Due to Hebrew Language Code
0I'm trying to integrate Dialogflow CX with Twilio using the one-click integration. I successfully connected a...
Agent Engine session does not keep track of the current converation
I created an AI agent using ADK, and then deployed it to Agent Engine with using following code:import os impo...
format custom output in Conversational Agent playbooks
i created a conversational agent with 3 playbooks. I integreted a tool with bigquery connector in order to exe...
No reply to access for Veo 3 Image-to-Video
How long do we have to wait for a response to an access request? We have already sent it twice.And what can in...
Persistent RESOURCE_EXHAUSTED (Code 8) Error on Vertex AI Despite 0% Quota and Basic Requests
Hello,I'm experiencing a persistent, critical failure with the Vertex AI API and I'm hoping to find if others ...
Access Google Chat app from Gemini workspace apps
I'm a developer for a corporate virtual assistant project.We created an internal chatbot available as an app i...
Turn off thinking for gemini-2.5-flash batch api in Vertex AI
gemini-2.5-flash-preview-05-20 support batch predications now (2025-05-21), doc is here: Gemini 2.5 Flash | Ge...
Datasource for websites
Vertex AI agent app , I have created a datasource connecting to a website. It was working and has now stopped ...
Allowlist for Studio Multispeaker Text-To-Speech
Hi,I'm working on creating conversational audio overviews using Text-To-Speech, but I need access to "en-US-St...
Failed to generate API key: permission denied" in Google AI Studio
I am experiencing a critical and persistent "Failed to generate API key: permission denied. Please try again."...
Dialogflow CX Agent Not Using Generative AI (Gen App Builder) for Product Search
Hello everyone,I'm working on building a shopping assistant chatbot using Dialogflow CX and integrating it wit...
Vertex AI : gemini-2.5-flash model available on Montréal (northamerica-northeast1) server ?
Based on GC-Vertex AI documentation, gemini-2.5-flash should be available on the Montréal (northamerica-northe...
Google Push Sub messages delayed
Hi everyone,I'm building a system where a worker node pushes ADK agent responses to a Google Pub/Sub topic. A ...
Conversational agents connector google sheets
Hi allI have limited tech skills. I am currently working on a chatbot, that uses some health databases. I want...
High 429 Error Rates with Gemini 2.0 Flash on Vertex AI
Hi everyone,We’ve recently migrated to the Gemini 2.0 Flash model on Vertex AI and are running into persistent...
Document AI API requests: "Request contains an invalid argument."
I'm trying to integrate the Document AI into a project. The requests worked last week inside of Insomnia, but ...
VertexAI RAG Engine does not work in Europe
Hi,I am experimenting with Google's RAGEngine.According to the docs it should be possible to use the RagEngine...
Issue importing search events into Vertex AI Search for Commerce
Hi all,I'm working on integrating GA4 data with Vertex AI Retail Search (Search for Commerce) using the GA4 sc...
How can i stream word by word from an adk agent deployed in vertex ai agent engine?
I want to stream the response from an ADK agent deployed using Vertex AI Agent Engine.I’ve tried the following...
Long-lasting sessions settings less than 30 mins default
hi,i created a conversational agent by using 3 playbooks, 1 master and 2 sons and i use the Slack integration ...
ADK Agent to ADK Agent
Hi,I created two multi agents in two different gcp project.Now i want to create a orchestrator agent in one gc...
Vertex AI search and loading issue
Hello,I am currently trying to deploy an RAG from Google Cloud with Vertex AI Search. The final goal is to be ...
Pricing - Vertex hosted tuned model
Hello,I am trying to figure out the cost of using a fine-tuned version of Gemini-flash-2.0. I believe all the ...
Unable to enable Firebase App Hosting service account, even as Project Owner
Hola a todos,Estoy desarrollando una aplicación Next.js en Firebase Studio y no puedo publicarla a través de F...
Articles from Product Experts and Googlers
How to build AI agents with long-term memory using Vertex AI Memory Bank & ADK
Is your AI agent suffering from amnesia? Don't let your users get stuck in a conversational loop. It's time to stop relying on clunky, expensive context windows that lead to "context rot." This guide introduces the Vertex AI Agent Engine Memory Bank. Learn how to build agents that remember and recall information across conversations. We'll show you how to generate, store, and retrieve memories, creating an enhanced user experience. Ready to build agents that truly connect? Let's get started.
Protect your LLM applications with Google Cloud Services
Generative AI offers immense power, but with it comes significant risk. This article discuss how to protect your LLM applications from prompt injection, data leakage, and other threats using a multi-layered security approach with Google Cloud services like Natural Language API, Model Armor, and vector databases.
Evaluating success in a multi-agent system: Why trajectory assessment and handoffs matters
Your AI agents are only as good as their ability to collaborate. As we move from single agents using tools to multi-agent ecosystems, our methods for evaluating success must evolve. Learn why trajectory and handoffs matter more than ever.
