Chinese is not displayed in the language selection
Chinese doesn't appear in the text-to-speech language selection. How do I create a Chinese voice?
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
LLM Evaluation
Hi All,How can we validated the playbook produced outputs? I created a playbook with tools in agent builder an...
Attempting to create a scheduled job for User Managed Notebooks
Hi, I'm trying to create a scheduled job for User Managed notebooks. I click the calendar looking icon here:An...
Change Endpoint of VertexAI SFT Job
Hello,A while ago, I created a Supervised Fine-Tuning Job on VertexAI, using this guide: https://cloud.google....
"ValueError(\nValueError: Unknown model publishers/google/models/gemini-1.5-pro-001
Hello Google Cloud Community, I'm using gemini-1.5-pro-001 for some classification pipelines using vertexai an...
Discrepancies in Gemini-1.5 Quotas and Understanding Dynamic Shared Quotas (DSQ)
Hi, I have some questions regarding the quota limitations for Gemini-1.5-flash and Gemini-1.5-pro in the Tokyo...
Request for troubleshooting assistance with AutoML pipeline
I am trying to complete an intro to ML course for Product Managers offered online by Duke University. I believ...
Dialogflow CX reload page loads always new welcome text
We have added the chatbot to our website. Chat window opens, the welcome text appears.But every time you reloa...
Batch prediction support for tuned Gemini models
I am trying to do batch prediction using a fine-tuned Gemini (gemini-1.5-flash-002) in Vertex AI. I am followi...
For Blended search, datastore spec with boost spec says Invalid
Hello There, We are been actively using Vertex ai Agent builder search and recently we started looking into bl...
Vertex RAG get document content by id
I can use `rag.get_file` to retrieve the file:```pythonrag_file = rag.get_file(rag_files[0].name)rag_file```Ou...
Internal error encountered.. while starting a fine tuning job.
When I was trying to start a fine-tuning job on a foundation model on generative ai studio. Got this error: in...
Vertex AI custom job training pipeline unable to query bigquery
I have a python script (some of the values are changed). It works in a vertex ai workbench. It works as a dock...
Grounding with Google Search- Detailed Costing
I am looking to understand the costs involved in Gemini API when using Grounding with Google search featureAcc...
ways to use fine tuned model
Hi @alessiasacchi, There is no option available in dialog flow cx for directly use a fine-tuned LLM model (usi...
Vertex AI RAG Engine - "Failed to search for project" Error (HTTP 500) - Possible Service Outage
I'm experiencing an issue with Vertex AI RAG Engine that appears to be a backend service problem rather than a...
Bugs in ML Notebooks?
Do you use Jupyter Notebooks to develop data science or machine learning pipelines? Have you encountered chall...
Unable to register Stream within Vertex AI Vision
I am trying to learn more about Vertex AI Vision. So, I followed the Quickstart instructions for building an a...
Vertex AI search Summarization
I'm facing issues in summarization results. The search will give results with all matching html/pdf documents ...
Journey voices deteriorated significantly (stopped respecting periods)
there's been some update that has made journey voices effectively unusable. The demos on the site and the actu...
How to sync/update Vector DB Vertex AI Search (used as RAG) in a agent?
Using Firestore Genkit (Node.js) and GCP Vortex AI, Vortex AI Search (the datastore), and GCP Cloud storage I ...
There are already 3 running ImportRagFiles operations in this project. The max limit is 3.
Hello!I'm new to vertex and I'm trying to import files from my gcs to Vertex AI RAG using a python SDKFor some...
Error 429 when using Vertex AI API, even though my usage is far below quota
Hi, I'm very frequently getting Error 429 when using Vertex AI API, even though my usage is far below quota fo...
Hyperparameters for GenAI
Hello! I hope someone can shed some light on an issue i'm having.I am having an issue with consistency when sw...
Got Missing required permissions: storage.objects.get
I'm trying to import data as csv file from Google Cloud Storage (creating DataStore)then got an error -> Missi...
How do I rename a documentai Processor?
Hi, my team manages an ever-growing set of custom processors. We didn't pay much attention to how we named the...
Model Armour for Agent Builder
Hi All,I created a playbook in agent builder and I would like to use model armour concept.How to achieve this?...
AI/ML at Google Cloud Next '24!
Answer this question in the comments to earn a special badge: If you could give your younger self one piece of...
Bug - Online prediction requests per base model per minute per region per base_model set to 0!
For the claude 3.5 sonnet model, the Online prediction requests per base model per minute per region per base_...
Data security in dialogFlow CX generator
I have created a chatbot using dialogflow CX and before returning the response to customers i'm using generato...
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.
