Application Integration Roadmap: The Future Ahead (March 19-20) - Global Sessions
Hi AI/ML Community, I'm excited to invite you to our Application Integration Roadmap: The Future Ahead session...
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
Regarding my “online_prediction_requests_per_base_model” when using the Claude model problem
{ "error": { "code": 429, "message": "Quota exceeded for aiplatform.googleapis.com/online_prediction_requests_...
Structured Output in vertexAI BatchPredictionJob
The title is self-explanatory I guess, but I will try to specify my problem a little bit further.In my use cas...
How to Get a Public URL for Vertex AI Agent Engine to Share with End Users?
Hi Google team,I’ve successfully built and deployed Google AI agents using the Agent Development Kit (ADK) to ...
Error “Invalid Cloud Storage URI for artifact_uri” when deploying gte-qwen2-7b-instruct model on Ver
Hi everyone,I’m trying to deploy the gte-qwen2-7b-instruct from huggingface found in model garden to use it fo...
Unable to see the gemini-embedding-001 model
I am unable to see the gemini-embedding-001 model, which is the one recommended by the gemini docs. When I try...
Adk Agent Deployment Not working
I have an application built with Google’s new Agent Development Kit (ADK) that I’ve successfully deployed to V...
404 Publisher Model `projects/project/locations/us-central1/publishers/google/models/text-bison@00
Hi,I am creating a model to generate insights from BigQuery Ga4 tables using models/text-bison@001`, I have cr...
Get Prompts doesn't work
I have created small application: from flask import Request, jsonifyimport vertexaifrom vertexai.preview impor...
Gemini Flash 2.5 pro output - fluctuating with runs with quality and accuracy going down
We are currently comparing Gemini Flash 2.5 output withAnthropic Claude 3.0 output and trying to work through ...
persistent internal error with multi-image classification in Vertex AI AutoML
Hi, I’m facing an internal error when training an AutoML Vision (multiclass classification) model.Product: Ver...
Streaming Response Support for Custom vLLM Container on Vertex AI?
Hey everyone,I'm currently exploring Vertex AI for custom model deployment and trying to set up LLaMA 3 using ...
Conversational agents exceeding token limits?
Good day all,I'm using conversational agents with a playbook, tied to a third party CCaaS platform.I've set th...
HTTP Links in Conversational Agents
Hi everyone, I've created a Conversational Agent using our company data. The data I'm sourcing is mostly PDFs ...
Automatic refresh for datastore indexation
Hi,I'm using the Discovery Engine of Datastore to index my website content and create a conversational agent.H...
Is Document AI capable of recognizing a parent label area that spans multiple lines?
Hello,I am building a Custom Extractor in Document AI to extract data from a form that has changed over time a...
Audio Integration in Agent Builder with Dialogflow Messenger
Hi,I am developing an agent using Agent Builder and I want to integrate it with Dialogflow Messenger.My goal i...
discovery engine for datastore
does discovery engine for datastore provide the ability to remove and add doc to datastore? how?
Vertex AI agent with fine-tuned models
Hi,i'm trying to create a vertex AI agent that uses a fine-tuned model.I do not see in the web interface any w...
Timeline for Web Search Support for Claude via Vertex AI
Hey everyone,Currently, Anthropic supports web search capabilities for Claude models when accessed via their o...
Prakash Hinduja Geneva, Switzerland - How to improve model accuracy in imbalanced datasets?
I am Prakash Hinduja Geneva, Switzerland and tackling a classification task with a highly imbalanced dataset, ...
Getting blank output in conversational agent tool
I have created a cloud function which retrieve two .tf files form my bitbucket repo. Below is the snippet of f...
Does Vertex AI Model Garden have a model for baby cry detection, or any related audio classification
I'm currently working on a project using Google Cloud Vertex AI, and I’d like to build a model to detect baby ...
discovey engine for dat store
I'm using the Python SDK with Discovery Engine (for Datastore) to create a data store using website content.Th...
Vectors not indexing : Dense vector count appears empty in Vertex AI
Hi ,I’m using Vertex AI Vector Search (streaming update method) and having trouble indexing datapoints. My dat...
Javascript error: Cannot read properties of undefined (reading 'newRowInputsArray')
I am following a lab tutorial and according to instructions there should be a input and output column when you...
Agentspace Vertex Agent Engine integration
Product Google Agentspace Observed error message I have been setting up ADK agents in Vertex AI agent engine. ...
Gemini 1.5 Flash (無料枠) のRPMクォータが期待値より低く、API利用に支障 (例: asia-east1で5 RPM)
Google Cloud Communityの皆様、およびGoogleご担当者様お世話になります。イロミヤと申します。 現在、Obsidianというノートアプリの「Smart Composer」というプラグインを通じて、...
number of datastore documents does not decrease
i 'm using data store to index my website contentwhy the number of datastore documents does not decrease when ...
Discovery Engine Datastore with advanced indexing for the website
I want to create a conversational agent that uses the Datastore tool to retrieve my website content. I have us...
Vertex AI - veo-2.0-generate-001 Quota for "Regional online prediction requests per base model" is 0
Hello Google Cloud Community, I'm working on a project (Project ID: creo-ai-461218) and trying to use the Vert...
Articles from Product Experts and Googlers
Configuring GKE rollout sequencing
You can manage the order of automatic cluster upgrades across Google Kubernetes Engine (GKE) clusters in multiple environments using rollout sequencing. For example, you can qualify a new version in pre-production clusters before upgrading production clusters.
MCP x ADK - Engineering Agents That Execute, Not Just Predict
Unlock the power of AI agents by connecting them to real-world tools and data. This guide explores the Model Context Protocol (MCP) for seamless integration. Follow the code-centric tutorial to build a Financial Advisory Agent with Google's ADK. Learn to equip your agents with external capabilities for complex, real-world tasks.
BigQuery Advanced Runtime and Enhanced Vectorization
BigQuery Advanced Runtime's Enhanced Vectorization expands on vectorized query execution by applying it to key aspects of query processing, such as filter evaluation in BigQuery storage, support for parallel execution of query algorithms, and through specialized data encodings and optimization techniques.
