Stack Overflow
Stack Overflow

Questions tagged [google-cloud-vertex-ai]

Usage questions relating to Google Cloud Platform's Vertex AI: https://cloud.google.com/vertex-ai/docs

692 questions
3
votes
4 answers

How can I run Google Cloud's "AI Notebooks" on a schedule automatically?

Notebooks in the Google Cloud Platform has been great for Python development in the cloud, but the last missing piece is just running existing notebooks on a schedule. There's a million different tools (Airflow, Papermill, Google Cloud Jobs, Google…
Ani kumar
  • 153
  • 1
  • 6
3
votes
2 answers

How do I access AIP_STORAGE_URI in Vertex AI?

I uploaded a model with gcloud beta ai models upload --artifact-uri And in the docker I access AIP_STORAGE_URI. I see that AIP_STORAGE_URI is another Google Storage location so I try to download the files using storage.Client() but then it says…
lee
  • 137
  • 1
  • 8
3
votes
2 answers

Severities of all logs on AI Platform are errors

On Google AI Platform, all logs printed on stderr are interpreted as ERROR. Is there any way to print logs as INFO, WARNING, and CRITICAL?
Shuhei Fujiwara
  • 193
  • 1
  • 7
2
votes
0 answers

using vertex ai in custom python script outside AI workbench and collab fails with permission denied

I'm trying to use GCP Vertex AI outside of a GCP managed AI Workbench notebook environment or Google Collab notebook environment. Specifically I am trying to run in an self hosted jupyter notebook environment. Here is my setup and…
netskink
  • 4,033
  • 2
  • 34
  • 46
2
votes
0 answers

Using VertexAI (Google Generative AI) in Golang

I am implementing this curl request in golang for connecting to vertexi generative AI models. I am using the token generated by this command for authentication gcloud auth print-access-token. But the token doesn't last for more than 1…
Sumit Vishwakarma
  • 85
  • 3
  • 7
2
votes
0 answers

On what set(Train, Test & Validation) does the VertexAI AutoML tabular(regression) display the evaluation once the training is completed?

I have used VertexAI AutoML tabular to train a regression model. In the dataset I have provided the TRAIN, VALIDATE & TEST split manually using a column indicating which set the row belongs to. When I train the model, it provides me with the…
Aditya
  • 21
  • 1
2
votes
1 answer

User Managed Notebook Auto Shut Down

I have been researching to find a suitable and scalable functionality accross multiple project to auto-shutdown user managed notebook in Vertex AI to reduce the idle costs. I saw that "official" solution for this feature is only available for…
Pawan Kumar
  • 31
  • 2
2
votes
0 answers

Trying to get my agent_executor for a sql agent in langchain to accept Prompts and Chat History

The langchain, agent_executor, SQLDatabaseToolkit all working but I want to prompt it and keep chat history for follow up questions. For example place a prompt somewhere to push to use table x when asked about storage. It looks like this at the…
user22121082
  • 21
  • 1
2
votes
1 answer

Why would Vertex AI not take the machine type while deploying endpoint for the model?

I am trying to deploy my successfully-imported on Vertex AI. But, while doing so, upon clicking "Done", the machine type is lost. And I am unable to deploy the model. Is someone else facing this too? How can I fix it?
Avantika Banerjee
  • 307
  • 1
  • 17
2
votes
0 answers

How can I [increase the rate limits/ batch requests] for the Google Vertex AI Bison API?

I'm testing out google palm API to recursively summarize a long text, and have since come into rate-limiting issues and therefore some questions to verify on. It seems that the number of requests made to the bison API is 60/min (this seems quite…
Dion Neo
  • 21
  • 2
2
votes
0 answers

Request-Response Logging Not Working on Vertex AI Endpoints

I'm having trouble with request-response logging on Vertex AI endpoints. Previously, with AI Platform endpoints, I was able to enable request-response logging via gcloud, which would then store the request-response data in a chosen BigQuery table.…
carl du Plessis
  • 29
  • 2
2
votes
2 answers

Vertex AI - Deployed Model Prediction is Different From Prediction in Evaluation Results

I have trained a multi-label text classification model using AutoML. I then deployed the model and attempted testing some of the inputs that we presented in the evaluation tab of the model registry. The problem I am having is that the predicted…
mattbrockwhg
  • 21
  • 1
2
votes
1 answer

Vertex AI Pipeline quota aiplatform.googleapis.com/restricted_image_training_tpu_v3_pod

I'm getting started with creating a tuned model. I've got my training data in a .jsonl file, uploaded to a bucket, everything checks out. I've run the tuning 3 times and every time it fails on step…
santeko
  • 360
  • 5
  • 10
2
votes
1 answer

Vertex AI Pipelines. Batch Prediction 'Error state: 5.'

I have been trying to run a Vertex AI pipeline using Kubeflow Pipelines and the google-cloud-pipeline-components library. The pipeline is entirely custom container components with the exception of the batch predictions. The code for my pipeline is…
AndrewJaeyoung
  • 368
  • 3
  • 10
2
votes
1 answer

Call Vertex AI Endpoint with Node.js - Error: 3 INVALID_ARGUMENT: Failed to parse input instances

I am calling a customized model (Two Towers for retrieval) in Vertex AI endpoint with Node.js with the following code: const axios = require('axios'); const { GoogleAuth } = require('google-auth-library'); const project = '1234567'; const…
razimbres
  • 4,715
  • 5
  • 23
  • 50
1 2 3
…
45 46