Dialogflow CX, how to store a user query on a page and use it as input on the next page?
Hi,On Dialogflow CX, using the end-user query, I want to go on a new page, and from this new page I want to lo...
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
Text to Speech "Journey" Voice Bitrate Quality Issue on API
Hello,I've noticed the "Journey" voices, when called through the API, have much worse bitrate quality than the...
Vertex AI - Support for XLXS files
The mime types supported by the VertexAI seems to be limited as opposed to AICloud. The Vertex AI API claims t...
I am using Document AI lending bank statement parser, but have limit to 9 pages instead of 30 pages
Hello, i need a help i am using the Document AI api for bank statement parse, but i have some limit that i can...
Google vertex AI support is terrible
I usually don't post things like this but I have been trying to work with Google support for Vertex AI for a w...
I have available quotas GPU but my pipelines are failing due to error: code=RESOURCE_EXHAUSTED
I got Quotas avaialbe in my region with 1 value on the GPU (NVIDIA_TESLA_P100) but it return this error:om.goo...
Significant Drop in Accuracy and Coherence of Urdu Transcriptions Using Google Cloud's Chirp v2 API
I have been using the Google Cloud Speech-to-Text service with the Chirp v2 API for the Urdu language for quit...
Cannot see third party data sources when creating a connector for Vertex AI
I am following the instructions on this page to connect my Confluence instance with Vertex AI. Connect a third...
VertexAI AI Agent API
Hi,i created a VertexAI AI Agent from the agent builder. What i'm trying to do now is call this Agent from a n...
Search requests per day per project quota in Vertex AI Search
We need to set up a request quota for Search requests per day per project in Vertex AI Search. The available q...
Vision AI Available in Qatar region?
My company has a Qatar client who requires facial recogntion. They do not want their data or images leaving Qa...
How to disable custom payload that restates Q/A on data store response with dialogflow
When I ask a question that gives a data store response, the bot outputs a custom payload that restates the qu...
Fine-tuning Gemini Model with x2 images and text as input
Hi there,I'm trying to create a fine tuned Gemini model where the process takes 2 images and text as input, an...
how to view JSON transcript in human-readable format
I have created a text transcript from an audio file using the Speech-to-Text API in the cloud console. Probabl...
Model is showing response along with the instructions given in function return
We are building a chatbot using gemini-1.5-flash-001, specifically for logistics and to get the correct output...
Dialogflow CX Data Store Invalid Value Error
We used to be able to organize FAQ data into Structured Data in CX using BQ where we used SQL to generate and ...
Google Cloud Translation - Does Documents translation consumes characters?
My simply question is if Document Translation charges per page and per characters at same time.I translated tw...
Not able to use vertex ai on cpanel
Hello,So I have used vertex ai multimodel embedding on my local windows machine it works perfect I just want t...
Quota not listed in Vertex AI pipelines?
Hi everyone I have a step in vertex ai pipelines that looks like this: transcribe_task = transcribe_audios(aud...
Agent Builder data store with Google Drive: the whole Drive!?
I have created a Search app in Agent Builder and would like to connect it to a specific Google Drive where use...
Tuning Gemini Model through VertexAI Studio - JSONL file format help
Hello, all,I have been trying to tune a Gemini model through google cloud console using VertexAI Studio. The t...
Tuning Gemini Model through VertexAI Studio - JSONL file format help
Hello, all,I have been trying to tune a Gemini model through google cloud console using VertexAI Studio. The t...
How to specify region in Gemini API request?
Hello,I'm currently using the Gemini API to generate content for my app. I'm trying to specify the region in t...
Custom ID on context caching vertex ai
Hi, community.I'm trying to create a cached content in Vertex AI. I want to provide a custom ID to the endpoin...
user is not allowlisted
Image generation failed with the following error: Project or the user is not allowlisted to turn off child det...
Issue with google Speech To Text API
I am working with a python script that is made from the code below that is provided in the google documentatio...
Fetch image/video from cloud bucket and send it+prompt to Gemini vision in Go
Hello helloI am trying to get an image from my cloud bucket and send it + a user prompt to gemini vision. I ma...
Gemini Model 1.5 flash
We are using gemini model 1.5 flash for our logistics related queries in which we are only using it for functi...
Assistance Required for Estimating Hosting and Deployment Costs for Fine-Tuning Gemini 1.0 Pro
Hello Google Cloud Community,I am fine-tuning Gemini 1.0 Pro on a small dataset of approximately 5-10 MB and n...
Request for Fix: Misinterpretation of Enter Key during IME Input in df-messenger.js
Dear All, I hope you are all doing well. I am currently using df-messenger.js for a project and would like to ...
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.
