Agent Builder Data Store Capabilities (Semantic & Multilingual Search)
Hi ,I'm working on a multilingual chatbot using Vertex AI Agent Builder and its Search data store feature.Does...
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
How to update the existed unstructured data to add metadata
Hi, I have unstructured data in the AI Application storage, now I want to add some metadata or structured data...
NLP v2
When will Google Cloud NLP scheduled to be taken out of Beta? I've read that the process usually takes 6 month...
Gemini Pro Quota Exceeded
Hi Community,I am getting a quota exhaustion message: "quota exceeded for aiplatform.googleapis.com/online_pre...
Gemini API: suddenly getting "User location is not supported for the API use" (Finland)
Started getting "User location is not supported for the API use" when trying to use the gemini-2.5-pro-exp-03-...
Vertex AI Agent
Hello,I'm currently testing Google Vertex AI Agent Builder to create a chatbot. I’ve built a chatbot using my ...
Incomprehensible Vertex AI API usage fee
A few days ago, I wanted to apply AI technology to an app I created, so I changed Google's Vertex AI API to 'E...
Unable to Schedule Vertex AI Workbench notebooks using a custom container
Hi! I would like to schedule notebook execution using a custom container with a custom default kernel and a cu...
Error: "Project '12345' is not allowed to use Publisher model"
During the "Compare Model Performance using the Generative AI Evaluation Service: Challenge Lab" I am running ...
Project 'fif-chatbot' Not Allowed to Use Vertex AI Foundational Models (e.g., gemini-1.0-pro-001) De
Hello,I am trying to create a chatbot.I am trying to call Vertex AI foundation models (Gemini) from Cloud Run ...
Integrating Gemini API in our SAAS platform
We are building a Gen-AI first learning, hybrid training and assessment platform. We would like to integrate G...
429 errors on Imagen, Gemini 2.5 and sonnet 3.7
I am testing a platform that I developed using Anthropic's offerings. We decided to go single cloud and I made...
Vertex AI Agent Builder completeQuery API returning empty array suggestions
Hi, I'm trying to use the datastores.completeQuery method for Vertex AI Agent Builder but I'm not receiving an...
update AutoscalingMetricSpec for online prediction
I want to update the autoscaling metric such that new replicas are triggered based on the volume of incoming p...
Text classification on-premise
Hello,We are seeking a Document AI on-premise solution to classify and extract information from unstructured t...
Need Assistance: `discoveryengine.assistants.update` not listed in IAM
Hey Guys,I am currently working with generative AI-based agents (previously known as Vertex AI Agents, which ...
Vertex AI Pipelines cannot compile kfp components
We started observe build failures for components built with KFP's `@component` notation.> @component(> package...
Quota stuck at 0 for Claude 3.5 Haiku
I'm trying to use Claude 3.5 Haiku on Vertex AI for a research project at my university. When I try to send an...
Need Clarification: Dialogflow vs DiscoveryEngine API : AI Applications(i.e Agent builder)
Hey Guys,I am currently exploring conversational agents in AI applications and have developed agents that I am...
safety filter for imagen are way to harsh
Hi dear google team,i am building an app which makes comics images and would love to use imagen 3.But the safe...
dialogflow-cx
For some reason, my flow performs worse than my playbook.my playbook answers the questions right but the memor...
Internal error occurred while fine-tuning gemini flash 2.0 model.
I have started the fine-tuning for the gemini flash 2.0 model. After running it for around 8 hours, I got the ...
document AI extract invoice data and feed into google sheets
Hi.I am a small business owner. I wish to use "document AI workbench" to extract information from supplier inv...
Google TTS Long form synthesis working sporadically
Hi, I'm Cas, new to using Google Cloud, Google APIs, and Python (I know, a good idea to try and figure it all ...
Structured data stores not visible to Conversational Agents' tools
Hi allThese are my steps:Create a Vertex AI Coversational Agent in the global region.Create a Tool.Set type to...
AI Model Deployment on Google Cloud – Getting Error in Vertex AI
Hello everyone,I'm trying to deploy an AI model using Vertex AI on Google Cloud.But I'm getting an error that ...
Error when connecting to llama3.1
While I try to connect to llama3.1 with langchain (VertexModelGardenLlama), I am getting this error "error": {...
Vertex gemini-2.0-flash -- since 2nd of April strong quality decrease
Hi,Since 2nd of April we see a strong quality decrease on gemini-2.0-flash. We haven't changed our code base n...
Google Cloud Sales Team India does not respond
Hello,I am trying to upgrade my quota limit for Vertex api's, for the underlying Gemini models, by contacting ...
Trouble authenticating to Vertex AI Gemini from n8n using Service Account (n8n Cloud user)
Hi,I'm trying to call the Google Vertex AI Gemini API (e.g., gemini-1.5-pro or gemini-1.0-pro-vision-latest) f...
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.
