translation of images via API
Im using an older API script thats meant to translate images. This feature is available on the web browser, ho...
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
Dialogflow CX - DTMF on intents
I have Google Dialogflow CX integrated with the Cisco contact center. I like to use utterances and also DTMF o...
Retrieve Status of Model Deployment to endpoint
I'm building out a service that can deploy a Vertex AI model to an Endpoint. Using the VertexAI Java SDK, is t...
speaking_rate has no effect for Journey Voice in Text-To-Speech
Hi there. I've been exploring the various voices offered by Google Text-To-Speech, specifically various speeds...
Dialogflow CX Recognizing Voice Input But Not Moving On
I created a parameter to collect email addresses for a voice bot. While it seems to be collecting the user's i...
Text-bison fails at handling JSON output
I am giving a series of prompts to the model in batch predictions and they are constantly failing with this cr...
AutoML, Batch predictions
Hi! I made my predictions and it said 'succeeded' without any errors, but the problem is that it added another...
Choosing a vector database
I am building a RAG architecture for an AI Agent and want to store my data in the form of vectors in a relatio...
Problems with calling Gemini API from Vertex training job
I am trying to run Vertex training job which contains calls to Gemini API (GenerativeModel -> generate_content...
Create a data store in DialogFlow CX supplied by a website with basic authentication
HelloI am trying to create a Data Store in DialogFlow CX fed with a website authenticated with username and pa...
Multliple data store sources
I am curious, if you have more than 1 source for datastore, which type is hit first. Secondly, are you able to...
Is it possible to run a Document AI instance in a local container?
Hi everybody, I'm looking for a local solution (ideally using docker) to run some data extraction from some fi...
Vertex AI Builder Third-party data source
Hello,According to the Vertex AI Builder documentation the Connect a third-party data source feature should be...
vertex ai vision product recognizer
Hello experts.I am guiding a customer who is testing the Vertex AI vision product recognizer for the first tim...
Gemini API [400 Bad Request] - Array fields breaks function calling
Using the node.js SDK: @Google/generative-ai@0.14.0This function declaration worked well one day or two days a...
Using "task_type" with Gecko embeddings on Vertex Ai-- BigQuery table as input
Hi,as documented here , to use bigquery table as input, the text's column name should be "content",But I don't...
query use of gemini api
Dear community, I am working on a very simple chatbot for my high school students, I have been able to use it,...
Video Intelligence API : Discrepancy in Label Detection API Results Compared to "Try Now" Feature
I wrote a Python code to analyze a video stored in my Google Cloud Storage using the Google Cloud Video Intell...
Gemini Grounding Not Working Properly?
Hi I keep enabling Gemini Grounding to be enabled on Gemini 1.5 Flash, yet I am not receiving Grounded base an...
How to retrive transcript of virtual agent and customer in dialogflowcx?
I have two questions?1. How to retrieve transcript of virtual agent and customer in dialogflowcx? After the vi...
issue: Call Vertex agent via API
we need to call our Vertex agent via API from a 3rd party application: Zoho Cliq, we code a customized command...
Regarding the cost calculation of Fine tuning for Gemini 1.0 Pro
Currently, in Google's documentation, Fine Tuning for Gemini is in preview status, so testing Fine Tuning is f...
Dialogflow cx : True condition routes triggered instead of routes having intent
Hi guys,I am having an issue in dialogflow cx , In one of my pages I have a few routes which are intent trigge...
website on Gen AI (Vertex)
I am experiencing an issue with adding a website on Gen AI (Vertex). The indexing process completes successful...
Gemini 1.5 parallel function calls
Hi everybody!I've been reading the documents and samples regarding the new feature of Gemini 1.5 models for pa...
Difference in response: Dialogflow CX and when the same bot hosted in webpage
The data store from each page is being used to generate responses using a state machine. However, the same que...
Dialogflow CX Generator Outputs Parameter Name Instead of Text
I'm encountering a strange bug with Dialogflow CX generator (gemini-1.0-pro-001). Sometimes, when I use the ge...
gemini-1.5-pro-001 is not 2M context window. Is it fake?
Current Token: 1,576,564 tokensI use this file for testing, is the 2M context window in vertex-ai is fake?driv...
input as text to llm and need response as audio stream from Gemini
I want to feed text to the LLM say Gemini Pro, and the response needs to be streamed to the FrondEnd or say mo...
Gemini API Costing
We are planning to use the Gemini API for our development and just want to ask that if we enable Gemini API th...
Articles from Product Experts and Googlers
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.
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!
