Is there any API for quotas and limits management in Google cloud Document AI?
Is there any API available for getting information about quotas and limitation in Document AI?.
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
EEException: Vertex AI prediction error: XLA compilation disabled
I deployed my trained custom model to Vertex AI and used the GEE API to call the model for predicting images o...
Is Adaptive LLM Google translation and Gemini pro 1.0 already GA or is it still in pre-GA?
Hi,There was an info two weeks ago in the release notes that Gemini Pro and Adaptive LLM is GA and not in pre-...
For Speech-to-Text, how long can API's streaming session remain open after inactivity period?
In Google Cloud Speech-to-Text:When no audio data (including silent audio) is being sent, the Google Cloud Spe...
Matching Engine shows restricts=None when finding nearest neighbors
I have a matching engine set up on a VPC. I can upload and query datapoints, but I'm trying to store metadata ...
Pipeline run failed: The replica workerpool0-0 exited with a non-zero status of 13.
I'm trying to fine-tune the chat-bison@002 model with my own JSONL dataset. And I'm receiving this error: "The...
PaLM 2 token_counts Result
Hi all,I need help to understand the result of count_tokens method in Vertex AI Python SDK from vertexai.previ...
Dialogflow CX Generators Response Parameters
I'm creating a chatbot in Dialogflow CX. On one page I'm using a generator to produce a response. I would like...
Understanding problem: MLKit Bird Classifier
I tested the vision-quickstart app and am interested in bird classification. There I get results as shown in t...
Speech-to-Text V2 API documentation
In list of supported languages model "long" available for Kazakh language (kk-kz) but in reality it's not work...
Dialogflow CX Messenger feedback forms - other supported languages?
Hi,When you enable feedback, the form used to give feedback is in English. Are other languages supported? I ha...
Vertex Workbench Instance SSH - Unable to login as a non-OSLogin user
Hi,I'm currently assessing Vertex AI User-managed Notebooks vs. the new Vertex AI Workbench Instances. In cont...
Error while creating Vertex AI Dataset
Hello everyone,I would like to solve the following problem with the Google Cloud, but I keep getting only erro...
Text-to-Music Generation
*Posting a use case from my client* I'm interested in developing a text-to-music generation system WITH lyric ...
Where do I find jupyterlab code using SSH into a dataproc cluster
I have managed to ssh into dataproc cluster, but cannot find the folder that contains my python codeHelp me pl...
Best practice for training on very large documents
I am creating a chatbot using Dialogflow-Cx. A few of the documents in my datastore are very large, with a few...
Very recent problem with STT in Java
I am working on a Java application which includes speech to text recognition technology based on Google Cloud ...
Gemini Pro Vision -- Inconsistent 400 Response for identical prompts
I've recently run across a strange issue when using the Gemini Pro Vision API. I've been running the same prom...
Missing Permissions and cannot create a custom role
Hi,I am trying to allow a user in my project to have sufficient permissions to be able to build custom models ...
Trying to pass OCR results to Gemini
I have both my python scripts independently working. One that converts pdf to text and another that gets a res...
Can't increase quotas for Vertex content generation?
I currently have a limit of 5 on aiplatform.googleapis.com/generate_content_requests_per_minute_per_project_pe...
Vertex AI Auto ML - error during prediction - Some bounding boxes were not valid
I created a custom dataset, trained the model and deployed the endpoint. While testing the endpoint with a tes...
Can we trigger a vertex AI pipeline using github trigger?
I have created a vertex AI pipeline using KFP in workbench and it is working fine. Can I use the same code to ...
Document AI
Hello team,I want to set up Document AI (OCR processor) for parsing a single PDF document from an input bucket...
Error using models/chat-bison-001 with text in portuguese
I'm testing an application with node.js, using the library @Google-ai/generativelanguage with the models/chat-...
Chirp model stopped working
we were using chirp model last week and it was working fine.this week, it stopped making any transcripts at al...
documentAI Labeling OCR issues: text select vs. bounding box
I need some help with best practices for labeling a PDF in DocAI. Based on my details, which option is best, o...
Parsing error when uploading JSONL files to a dataset
Hi,I have been trying out the Vertex AI tool for the past couple of days. I am doing a pretty basic test with ...
How can I get access to Gemini 1.0 Ultra?
How can I get access to Gemini 1.0 Ultra allowlist?I saw that you need to register on their allowlist?
Vertex search not retrieving all relevant records
Hi Everyone,We have vertex search app with half million records, But when we search any search term its return...
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.
