Gemini in Workspace - training on brand tone of voice and use cases
Apologies if this is a newbie-level question, but please bear with me. The business I work for, specifically t...
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
Vertex AI Auto ML Image object detect model taking longer than usual
I have started 5 Auto ML image object detection model training in us-central1 location yesterday and specified...
Vertex AI predictions fail without details about the error
I am a very new Vertex AI user, and I started using it with very basic AutoML regression model. I performed ev...
Gemini advanced not answering HTML code questions
suddenly Gemini advanced is refusing to answer questions and generate HTML code .starting yesterday I was gett...
Vertex AI Auto ML - taking longer than usual
Hi, I am in the process of creating my first training model using Vertex AI and it is to classify images. I ha...
Datastore is not getting indexed
Hi @xavidop The datastore are not being indexed. I tried importing from one agent to other, since I to got to ...
Generate Bearer for HTTP requests
Hi,please, tell me simply how to generate bearer token for HTTP request. (Like api-key in openai) I have chatb...
Speech to text V2 Java Help?
Hi Everyone,I'm tearing my hair out trying to get my first java speech to text transcript going. The code is b...
Vertex Agent Builder: Failed to generate response
i made a agent in my project, but when i try to include the example by "Selection strategy" to auto or always,...
Inaccurate results from Conversation AI
Hello, I'm building a chatbot using Vertex AI conversation and Dialogflow CX. for the chatbox the only datasto...
Gemini Advanced suddenly can't access websites
Hello!For hours I've been changing metadata of my stock music by providing direct links to it. I've took a bre...
Generative Fallback is hallucinating fake products
In my Dialogflow CX, I have a generative fallback with this prompt below. When I ask it about random fake prod...
Can you add custom payload with Generative AI fallback?
After Gen AI fallback is triggered in Dialogflow CX, I want to have a follow up question asked. "If you have a...
How to access multiple cameras for live AI model detection: Challenges and Infrastructure Needs?
I need to access 10 CCTV cameras simultaneously for live video detection purposes. I will deploy a custom AI m...
Inability to Process Images in Gemini model
I've encountered the following issues with Gemini-1.5 fask-preview-0514 and 1.5 pro-preview. While it generall...
Gemini AI API Quota Exceeded
So I'm using Next TS with Vercel AI SDK with Gemini-1.5 Pro Latest, the code works on my local machine but the...
Vertex AI Chat-Bison Model
I have three issues with this Model. 1) examples are confusing. On one hand are documented like it is a mechan...
Not being billed for API calls to gemini pro 1.5?
Hi,I have been building an app and the REST API is sending 4 API calls to gemini 1.5-pro using AI Studio (not ...
Model behind Translation LLM and Adaptive Translation
Can someone clarify what model does Translation LLM and Adaptive translation uses? If there's some source whic...
What is the best way to enhance Gemini model with "few shot" prompting in multimodal setting?
Hello,I am working with the Gemini 1.5 model to extract information from PDF documents and am exploring the "f...
cannot see my gpu instance detail
i tryna to deploy llama3 and this require me to have quota on l4gpu, but when i wanna to request i see that i ...
dialogflow - telephony integration- response time
Hello thereI have used telephony for voice call bot, and while talking on the phone, it takes more than 3-5 se...
Gemini 1.5 flash | API Response shows placeholder for image
I am using gemini 1.5 flash and gemini 1.5 pro models via API. I get the following response where I get a plac...
Vertex AI search on unstructured data
Hi,I built a Vertex AI search app on unstructured data (imported a JSONL file with data in it) and I'm getting...
Vertex AI Search API
So I have been reading about Vertex AI Search using the console UI. I created an app with website search capab...
Vertex AI custom model training do not have acces to artifact registry
I wanted to create a custom training in vertex ai.I followed exactly the steps listed in the google courses : ...
"Deadline" error when embedding video using Multimodal Embedding Model
I am currently using Vertex AI's Multimodal Embedding Model (https://cloud.google.com/vertex-ai/generative-ai/...
Issue with structData Not Returned in Search Engine Results
I used Vertex AI App Builder to create the search engine.For the data store, I have selected unstructured data...
Dialogflow using external api's DEADLINE_EXCEEDED
Hello, @xavidop Could you help me with this one?I'm using Dialogflow ES and have integrated a cloud function a...
I would like to localise a Google Maps blueprint using an image (screen-shot) as an input
Hi there,I would to localise a Google Maps blueprint using an image (screen-shot) as an input.One of the tryou...
Articles from Product Experts and Googlers
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.
Untangle the API maze with Apigee API Hub
Mirror mirror on the wall, What do I do with my API sprawl, Where can I see them all, How to make sure they listen to my call, And to ensure their compliance doesn’t fall. API Hub is the one to rule them all!
