Application Integration Roadmap: The Future Ahead (March 19-20) - Global Sessions
Hi AI/ML Community, I'm excited to invite you to our Application Integration Roadmap: The Future Ahead session...
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
Bard isn't supported for this account
I'm continually encountering an issue where I'm told "Bard isn't supported for this account", even though I wa...
how often do I need to call gcloud auth login?
I am a FE engineer working on a new company from the ground up. The "backend" world is completely foreign to m...
Dialogflow CX - continue conversation of abandoned user
I'm testing dialogflow cx to service chatbot.Is it possible to remember and continue previous conversation of ...
Regarding GCP Cloud Vision and Functions
I have a simple setup where a GCP Function gets triggered when a pdf is uploaded to a bucket. Once the file is...
Where are Dialogflow ES/CX audio files stored?
This page indicates that Dialogflow ES audio recording are stored somewhere once enabled, but I can't find whe...
Can the Google Translate API v2 be used in the frontend?
Hello? By any chance, can the Google Translate API v2 be used in the frontend?Initially, I thought the Google ...
Datasets best practices
I am new to ML and VertexAI. I have some questions about an app I am building that requires image classificati...
What is the difference between vertexai.preview.language_models and google-generativeai?
as asked in the title what is the difference between these two python packages? how can I get my hands on PaLM...
AutoML Translation: again one of 22 requests finishes with timeout
Again we meet some problems with AutoML Translation API Trained 22 custom models for translation from EN to t...
Bard API
Hello, I am student currently working on a chatbot project and I would love to use the Bard API, please can so...
English to German translation issue in html for Chrome
Hello,This is the very first message for me here, sorry if some rules are not followed precisely. So our users...
Vertex AI create pipeline file content error
Have been trying to build a pipeline using several generic examples. Python created the following yaml file, b...
GCP function deploy
The error message you received indicates that there was a bad syntax in the request you sent to the server. Th...
Training phrases are not returned via python API
I am trying to get an overview of the training phrases per intent from Dialogflow in python. However, for ever...
Error while deploying hugging pytorch model (ROBERTA) to Vertex AI
Hello I am new to the vertex AI. I have created a binary classfication model using hugging face Pytorch model ...
Agent struggles to get a car registration number/postcode over voice
I'm struggling to get my Dialogflow CX agent to understand user's car registration number (e.g. GV15YGH + lot ...
Submit Job But Never Ran
I am trying to test a bash script on the cloud, but when I submit it, it repeatedly switch between SCHEDULE an...
building a custom jupyter notebook container that supports python 3.10
the off the shelf notebooks only support python 3.7. This doesn't work for us as many of the libraries we use ...
Quota 'GPUS_ALL_REGIONS' exceeded. Limit: 0.0 globally.
Hi,I have notebook like thisWhen trying to start is I get error "Quota 'GPUS_ALL_REGIONS' exceeded. Limit: 0.0...
Language was support with machine translation engine and not supported any more or got error 400
- Last time we work well when choose Arabic Iraq to deal with Kurdish Sorani on google machine engine, but now...
Google Bard API
Hello, I know that there's the PaLM-2 API. My question is if there will ever be a BARD API. So a model with th...
I want to build bard tools
Hello Google I'm one of the first 40 approved plugin developers at gpt and am currently in talks with 5 Fortu...
Vertex AI custom training job never finished
Hi, I am trying to implement custom model training on Vertex AI.I pushed custom training job to Vertex AI and ...
Unable to deploy model to endpoint
Hi,I am trying to deploy a simple model on an endpoint in order to start making predictions.I followed these s...
Document Ai to csv document
Hi,I am using Document AI to extract data from a pdf file. However, the result is a json file. What can I do t...
Google Cloud Vision API reports (x,) in boundingBox when (x,y) is expected
I have this piece of response where (x,y) information for 4-points of the bounding box is expected but you'll ...
Invoice parser "invents" non-existing string for supplier_name normalized value
While processing a dummy invoice taken from the internet, I have found that invoice parser returns normalized ...
How to implement custom evaluation jobs (with custom metrics for custom learning tasks) in Vertex AI
From what I can see in GCP's official docs: https://cloud.google.com/vertex-ai/docs/evaluation/introductionEva...
Document AI OCR problem and IssueTracker no reply
Hi,I have submitted reports on IssueTracker about Document AI OCR recognition errors, but the report has not b...
Console Speech to text - transcription
When I give a 45 second mp3 file to the transcription program, this program generates only 15 seconds of trans...
Articles from Product Experts and Googlers
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!
Next-Gen Data Pipelines: Airflow 3 Arrives on Google Cloud Composer
We are thrilled to announce that Google is the first hyperscaler to provide selected customers with access to Apache Airflow 3 on our fully managed Cloud Composer 3 service. Discover how powerful new features like DAG Versioning, a modern React-based UI, and scheduler-managed backfills can help you innovate faster and more reliably.
