Custom model training with preemptible machines?
This post asked a similar question last year:https://www.googlecloudcommunity.com/gc/AI-ML/Usage-of-spot-machi...
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
Using @parameters chip for testing in the Conversational Agents Console Simulator?
Hi, In the preview of Conversational Agents there is now the ability to pass parameters and events into a agen...
Dialogflow CX conditional response always appears last - unable to reorder?
HIIn entry fulfilment for a page in a flow I'm trying to use a conditional response, followed by a custom payl...
Conversational Agents - syntax for parameters when creating playbook examples
When creating examples in playbooks, I'm noticing some console errors for input and output parameters I try to...
Embedding Vertex AI agent behind user log in
Hi, new to building agents but enjoying Vertex AI Agent Builder so far. I've been looking through the document...
Failling test cases - Conversational Agent
I have a Playbook in Conversation Agent, and test cases created through the "Simulator" based on conversations...
different result between public/invoice parser
Hello,I don't know why there is a difference in the result of Document AI (the public version is better in the...
ERROR: (gcloud.builds.submit) FAILED_PRECONDITION: failed precondition: due to quota restrictions
Greetings,I was practicing deploying a custom container over vertex ai, using the following colab notebook:htt...
Link in Conversational Agent not public
Hi, I have some problems in a Conversational Agents project, where I use a public availlible bucket in GC whic...
Suddenly receving an "Error: ClientError: [VertexAI.ClientError]: got status: 400 Bad Request" error
Hello,Today, I suddenly started receiving errors from my Firebase function that uses Vertex AI with the Gemini...
How to create run test cases in Agent Builder
Hello!I created a Playbook and can interact with my agent. I can create test cases through the "Simulator". Ho...
Fail to deploy my registered model to endpoint on Vertex AI
Whenever I want to deploy my registered model to the endpoint on Vertex AI it will fail here. I don't even kno...
Unable to Create VM with GPU - no A100 GPUs available
Hi everyone,I recently requested an A100 GPU and also applied for "All GPUs" quota in my GCP project. Both quo...
Gemini Flash 1.5-002 suddenly shorter context window (1M -> 32K)
Hello,I got error when I called VertexAI API with gemini-1.5-flash-002.Error message is "400 The input token c...
Can we please get an offline token-counter so RAG chunkers can work reliably w/ embedding-exp-03-07
I'm quite proud of my "chunker" for my custom RAG, which has some elegant recursive mechanisms based on tiktok...
CX integration with Google Phone Gateway for Hindi
Created a Google Phone Gateway with a bi-lingual CX agent that has English and Hindi as languages. Phone Gatew...
cloud billing support free trier
please This action couldn’t be completed. Try again later. [OR_BACR2_34] this errors trouble me for months if ...
Journey / Chirp HD TTS is very slow to respond... ~ 4,000ms. Not a production ready API from google.
So, for a single sentence I'm getting latencies of nearly 3,000ms... Is this normal? I've noticed Google quali...
Voces no disponibles
Llevo muchos meses trabajando con una voz tipo Neural en español (Estados unidos) neural 2. Todas las voces qu...
Trying to connect DialogFlow CX with agents created in dialogflow cx directly and not in the Agent B
Hey,i am experiencing an issue when attempting to connect my Dialogflow CX agent with Soul Machines. The probl...
Vertex AI Feature Store - Unable to Fetch Historical Feature Values
I'm trying to retrieve historical feature values from Vertex AI Feature Store following the documentation. I'm...
How to delete a data point in Vertex AI vector search
https://cloud.google.com/vertex-ai/docs/vector-search/setup/format-structure?hl=enAccording to the documentati...
Clarification on How response_schema Injects JSON Schema in the prompt.
Hi everyone,I'm currently fine-tuning gemini for structured output and have hit a snag regarding consistency b...
False Positive Block for 'Thank You' in Dialogflow CX
I'm working with Dialogflow CX to build a conversational agent, and I've run into an issue where the system bl...
Play audio on Google Phone Gateway
I have implemented a page fulfillment and a webhook on that fulfillment that does text to speech generation. A...
Image editing failed - Vertex AI Vision
Error Message: Image editing failed with the following error: You have chosen the 'Allow (Adults only)' option...
User location is not supported for the API use
I've been using Gemini Models from my Cloud Run function deployed to us-central1 for weeks. This morning I wok...
Dialogflow CX - Escalation to Human Agent Fails in Custom Playbook
I am using Dialogflow CX with Twilio for call handling. In the default playbook, transitioning to the escalati...
Issue with NL2SQL Query Generation for Category-Based Search in BigQuery
Hi everyone,I’m building a chatbot that generates SQL queries using an NL2SQL function to retrieve data from B...
Gemini Pro and Flash 002 suddenly shorter context window
Hello,I can no longer use the Vertex AI API for Gemini models with long context, this is the error I get:run w...
Articles from Product Experts and Googlers
Deeper Insights with knowledge engine & dataset-level metadata in BQ
In my previous blog From Data to Metadata: Unlocking Insights with Gen AI in BigQuery, we explored how BigQuery's “Insights” feature can automatically generate metadata for your tables and columns helping to uncover hidden patterns and trends within your data. We are now taking it a step further with metadata and insights generation at the dataset level. This new capability not only describes the dataset but also provides an interactive entity relationship map that visually reveals connections between different entities.
A developer's guide for building with Anthropic’s Claude 4 models on Vertex AI
We recently announced the general availability of two new models from the latest generation of Anthropic’s Claude model family on Vertex AI: Claude Opus 4 and Claude Sonnet 4. In this blog, we’ll guide you through building with the new Claude 4 models on Vertex AI.
Introducing DeepSeek R1 Model-as-a-service on Vertex AI Model Garden
Deploying Deepseek-R1-0528, a 671B parameters model, typically necessitates at least 8x H200 GPUs for a single API request. Such extensive resources are not accessible to everyone.To make Deepseek R1 more accessible to developers, we're excited to announce that DeepSeek R1 is now available as a fully managed API on Vertex AI in Preview.
