Ground Model Responses Error
I've been playing recently with very high level grounding of model responses in a datastore by creating a sear...
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
integrate salesforce con GCP
i need tho know how can i integrate or where can in. find the developer settings in ccai portal?
Model Overfitting
Hi All!I was recently making my own AI/ML project with GCP products and heard about over-fitting! As a result,...
Connecting button from payload to the form page
Hi @xavidop, i have created this custom payload in the default start page of the default welcome intent. Now, ...
How to improve Document AI model that detects O as zero
HiI’m training a model that detects a value that is a mix of letters and number. It is struggling to different...
Vertex API Multimodal Embedding can be blocked if too much request?
Hi, I am currently using Multimodal Embedding for image and I need it fast. So I create process that loop and ...
Vertex AI cannot access cloud storage
I am trying to set up my first fine-tuning with vertex ai. I am unable to load my data in a cloud storage buck...
Deploying reranker models on Vertex AI with text-embedding-inference
Currently Vertex AI supports deploying embedding models like BGE and GTE using HuggingFace text-embedding-infe...
Disable ADC and Pass bearer token in headers for search gRCP call
Hi,How do I disable ADC, not look at application_default_credentials file and pass bearer token in headers for...
Filter generic search for structured or unstructured data - Vertex AI Search
Hello,I have some problems with using https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v...
TTS Receiving ERROR: Failed to write to GCS URI: gs://${bucketName}/output20.wav
Hi everyone,I came across a error on Google Text to Speech long audio synthesis that i can't solve. hope you c...
Multi-Modal Chatbot
Hi, I was working on a chatbot quite recently, and I have tried to incorporate image and video processing with...
I receive a large number of emails about Gemini API project has been reinstated every day
I encountered the same problem, could you help me solve it?https://www.googlecloudcommunity.com/gc/AI-ML/Stop-...
Inquiry About Payment Method for Gemini
I am currently using the Gemini API key created through the Google Cloud Project. I would like to know if the ...
Error when prompting gemini API with links directly instead of file manager API
GoogleGenerativeAIFetchError: [GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googl...
Improving response times on Gemini API
Hello everyone, so I've been using Microsoft's Semantic Kernel to develop a RAG pipeline for some time and mak...
How can I fine-tune a pre-trained BERT model using Google Cloud AI Platform?
I am working on a natural language processing project and I need to fine-tune a pre-trained BERT (Bidirectiona...
df-messenger.js upload file to Bucket
Hi everyone, I'm currently working through this (URL Removed by Staff) on uploading files to a Google Cloud St...
Inconsistent Responses from PDF Bot Using text-bison-001
I have developed the question and answering system based on the PDF bot using the "model named text-bison-001"...
Tuning the model
when dataset uploaded , but when tried to tune the model, says this "Row: 0. Missing required `contents` or `m...
Recommendation Engine takes too long to prepare
Hi, I am trying to create a recommendation engine using Vertex AI Agent Builder. I followed the "Get started w...
Start chat with context
model = GenerativeModel("gemini-1.0-pro", generation_config={"temperature": 0}, tools=[retail_tool]) context =...
Dialog Flow ES cannot save intents
Hi I am trying to edit my dialogflow ES agent. whenever I try to add new text responses and save it I get a ne...
Vertex AI Vector Search support text2vector?
Hello everyone,I'm currently exploring Vertex AI Vector Search and I'm particularly interested in its capabili...
'Environments' button under 'Manage' disappeared
Hi all, As of this morning the 'Environments' button has disappeared so I cannot adjust the test- and producti...
How to make sure the agent answers only based on the data from the tool
I'm developing a Vertex AI agent using the agent builder to answer user questions about investment products. T...
VertexAI Document Reader for PDF
My goal is to be able to process large amounts of technical data sheets and extract the material properties wi...
PipelineJob using a dedicated service account
When I submit my pipelinejob (submit) job = PipelineJob(...)job.submit( service_account='') I get the followin...
Training pipeline failed with error message: Train set should contain all labels.
Hi Team, I just started evaluating Google Vertex using my sandbox . I m building a basic classification pipeli...
image processing not working with Gemini API. text working fine
I have been using the Gemini API for image processing in my flutter application. It was working fine until rec...
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.
