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
Looking for Suggestions: Best Approach for Chatbot and Content Creation Use Cases
I'm evaluating options for two related use cases and would appreciate any insights or recommendations:Chatbot ...
How to specify the Reference Id for each prompts requests in gemini batch
I have gone through the documentations https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/batch-...
429 error on Vertex after only a few requests per minute with relatively small token sizes
I'm using Vertex API in us-central1. I get this error after 3 or 4 requests per minute.What's strange is nothi...
Programmatically import documents into a dataset using DocumentServiceClient.ImportDocuments
I am trying to import documents into a dataset using DocumentServiceClient.ImportDocuments(). There are many e...
AI Application (previously Agent Builder) Agent deployment
Hello, I have developed a conversational agent with AI Application that is grounded on a website. It responds ...
Is the “experimental Google mdoel” available for free after GA?
"Experimental Google models" can be used for free on Vertex AI. However, even after a model that was under exp...
Is the model part of the container in the script
I was looking into the code# Set docker and quantization for AWQ quantized models VLLM_DOCKER_URI = "us-docker...
Vector Search The message limit size
I work with Google Vector Search and faced the issue when trying to upload a datapoint:400 The message size is...
Vertex AI AgentBuilder blank response via console and DialogFlow
Hey,I have some agents developed in Vertex AI AgentBuilder, new agents and some old ones, and I use their inte...
What is the Rate Limit for the Chirp TTS Model?
Hi all,I'm looking at using the Chirp TTS model for a telephone IVR, including real time conversion to read ba...
Semua produk Google translate
https://cloud.google.com/recommender/docs/recommendation-hub/find-recommnedation-hub?hl=id#before_you_begin
Pricing of Google AI Studio
HiI am very confused about the price of Google AI Studio.I intend the prompt online: I want just use the promp...
Pricing - Vertex hosted tuned model
Hello,I am trying to figure out the cost of using a fine-tuned version of Gemini-flash-2.0. I believe all the ...
Google Ai Studio - Always returns error "An internal error has occurred", does not generate text
Whenever I try to use https://aistudio.google.com/ and chat with it, I get this error message and it does not ...
ePHI and Gemini
We would like to use Gemini (in GCP via Vertex) to analyze data that may contain ePHI. We're HIPAA certified a...
Ai And ML is wide lavel boom the market you reach the
Help us the most important work to
Chirp3 HD Voices don't support markup field in long audio synthesis
I'm trying to put some pauses in my synthesized text-to-speech audio. Since it seems as though the Chirp3 HD v...
Which Python Library for Chat App in AI Applications (Agent Builder)
Hi GCP community,I've been trying to create the Chat App (screenshot 1) and attach an existing datastore (scre...
quota error using text model
Hi there !I'm running into the following quota issue when performing predictions with Vertex AI's text models:...
Gemini Batch API Performance Issue - Slow Processing
Hello,I am using Gemini batch api through the python SDK. I have created around 5000 jsonl batches, each conta...
Prefer a specific phone in answers by bot
Hallo,we have added our website and a faq file to our storage as source for the bot.All works fine but on the ...
while doing the text or doc translation can we feed a standard dictionary?
while doing the text or doc translation can we feed a standard dictionary?like below into the translation serv...
Internal Error Occurred: CustomContainerTrainingJob
Hello, I'm trying to run a CustomContainerTrainingJob with the Python SDK on g2-standard-24 machines with 2 NV...
No Module Named bq_stats
I'm using the new instances of the vertex notebooks. When attempting to run the scheduled jobs I get this mess...
Constant 429 Errors with gemini-2.0-flash-thinking-exp-01-21 API on Vertex AI
Hi everyone,I'm encountering consistent 429 errors (rate limit exceeded) when using the Vertex AI gemini-2.0-f...
Empty Response from projects.locations.dataStores.conversations.list Despite Valid Setup
The projects.locations.dataStores.conversations.list method returns a 200 response but no conversations. My se...
[Vertex AI + Service Account] Could not refresh access token - persistent 403 error
Hi everyone,I’m working on a Node.js backend that connects to Vertex AI (gemini-pro) using a service account w...
text-multilingual-embedding-002 - deprecation policy
hiwe are using multi-lingual text embedding for similarity search and clustering.I see that once in a while, e...
Getting an error: "Unsupported client message: go/debugproto" and "go/debugstr" - Bidi API
We are using the Gemini Vertex AI API (Bi-directional API), it was working fine but from the last 2 hours we h...
Error 429 when using Vertex AI API, even though my usage is below quota
I just started implementing claude-3-7-sonnet@20250219 for my app, already getting 429 errors in my developmen...
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.
