Vertex Search Widget Error: sites.google.com refused to connect
Vertex Search Widget Imbedded to a Google site is getting this error "sites.google.com refused to connect" whe...
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
Translation AI - Exclude language for translation
Hi. I'm very new to this, so please bear with me if I'm asking stupid questions. I am using Freshchat, and thi...
Confusing Documentation in Dialogflow CX
Hello,I am trying to understand the evaluation order of a parameter form filling of a particular page. Accordi...
Document AI setup question
Hi - I'm looking for guidance on setting up the parser correctly.I have created field and parent fields. The p...
GeminiAI, Generate function comments, Code getting modified, No comments for big files
Program is run for the whole repo in a while loop with suitable sleep of 30 seconds after every 10 requests. F...
boost control for Vertex AI Conversation with Data Store limitations?
Hi, I'm developing a Conversation agent using a Data Store. I have a mix of web content and unstructured conte...
Cloud Retail categories
Hi community,Recently, I implemented a search model in cloud retail using apparel data. In the categories opti...
ML Pipeline parameter_values does not work well.
I am currently running an ML pipeline on Vertex AI and it is not working as expected, so I am asking this ques...
Dialogflow CX Knowledgebase in a bucket and links displayed inside chatbot
Hello,I've created a Dialogflow CX chatbot that feeds out of HTML files stored in a GCS bucket and answers que...
serverStreamingPredict doesn't accept request object properly
I'm trying to use `serverStreamingPredict` with `text-bison@001` and its always saying prompt is missing in th...
Bard extensions - When can we develop our own?
Hi! I'm a developer who already develops Chrome extensions, and work with AI/ML at my current job.I'd love to ...
Quota exceeded while training a simple fraud detection model
I am trying to train a simple model using tabular data in bigquery-public-data.ml_datasets.ulb_fraud_detection...
Issue about timeout in Speech to text Long model v2
Hi Google Team, I have an issue with the timeout in the long-run requests. I use the input file as 1hr 30 mins...
DialogFlow doesn't answer bases on Knowledge base
I have Vertex AI with an unestructure data knowledge (pdfs) and when I ask questions, it answer random things ...
"Search and Conversion" searching a German PDF: Bad results/specifying languages?
We want to add a "AI-supported search feature" to our application, where the users ask questions in natural la...
About “Cloud Speech-to-Text”
Hope someone can help me understand what is the difference between the APIs of v1 and v2 of the “Cloud Speech-...
[PHP] Error setPaths FieldMask on batchProcessDocuments for DocumentAI
Hello,I’m using Document AI with the invoice_parser and I am trying to implement a FieldMask on my GcsOutputCo...
EOF error when loading data for Vertex Search and Conversation
I'm getting an EOF error when creating a data store for my Vertex AI Search and Conversation app. I create the...
How to use "openMinChat()" function in dialogflow cx messenger?
Hi chatbot developers, Can you please help me to use openMinChat() function with an small example or resource?...
Issues with CPU and Memory Request Allocation in Vertex AI Pipelines
Hello,I am facing challenges with resource allocation for a Kubeflow Pipeline component deployed on Google Clo...
Vertex AI- train model from checkpoint?
Hi,I'm looking to use Vertex AI for an entity extraction use case where we have a small amount of training dat...
Vision AI and Vertex AI
Hello, I have a project in Python that is using Vision AI and as I can see Vision AI will be removed in march ...
How To Run Queries Against Your Custom Vertex AI Model?
I have a set of images I labeled during the creation of my "Image object Detection" dataset.After training the...
Giving Gemini Access to the Internet
Hey everybody! First post in the google cloud community. Anyways I wanted to know if anyone knew how to connec...
Dialogflow CX charges
Hi everyone,I still don't quite understand how Dialogflow CX charges for its usage. I need to know if the usag...
In Google dialogflow cx on the basis of phrases agent not redirected to page
Hello,I am new here as dialogflow cx user. I configured the flow, pages, intent and entity,and once I started ...
When is gemini-pro-vision moving out of pre-GA?
> Vertex AI Gemini API is a Preview offeringI have it noted from earlier page versions that the move from pre-...
Error -83104 when using speech to text
I am trying to transcribe a long mp3 file (45 mins long). Here are the details of my configuration.When using ...
Gemini Pro Vertex AI Chat Prompt Requests Getting Blocked
So, I am trying to build a chatbot for which I am using gemini pro's chat prompt to keep the context intact. H...
Why does Sentiment return different magnitude and score results from the online demo?
I have added the API for Sentiment to my project and when I run "Yes appointment confirmed" I get a magnitude ...
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.
