Document AI - Contract Parser
Hey guys,Anyone know the story behind the deprecation of the Contract Parser, a specialized Document AI parser...
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
Summarize and get response from data store
Hi,I have a HR support chatbot, it answer questions using Data Store.If user input more than 256 characters I ...
Checkbox extraction using Google Vertex LLM
Hi Team,My use case: I want to extract handwritten content from pdf along with some checkbox data using Google...
Clarification on Training Restriction Clause in GCP Terms
Hi,I’ve been reviewing the Service-Specific Terms for Google Cloud Platform (GCP), particularly section 17: Tr...
Why is Google Cloud's Generative Model quota not respected by the API?
I am using a fine tuned model of gemini-1.5-flash to process large amounts of data (worth noting same issue ha...
DialogFlow and SoulMachines
I have setup a DialogFlow CX Conversational Agent and it says it will integrate with SoulMachines to create a ...
Possible unauthorized access and "shadowing" on my Google account via RTC
Hi everyone,I'm experiencing some strange issues with my Google account and I'm hoping someone can help. I'm c...
Out of SLA in 179 days
Does anyone know what this status means in the AutoML model?
Has anyone configured the preview data connectors for Confluence or Jira?
I was allowed-listed access to the Agent Builder datastore connectors for Jira and Confluence. I'm trying to w...
How to manage after timed out ?
Hi,When take any action after session timeout in Google Dialogflow CX it responses "Unknown".How can I handle ...
When will the new Conversational Agents console be stable?
Hello all,I've been doing some prototyping work with new consolidated Conversational Agents console.There are ...
Permissions or method to use Generative Language API
Hi, we are new to Google Cloud and want to make use of the Generative Language API in our application. The app...
Document AI Language
Hi Team,Is there any way to give language hint while sending processing request to a custom processor through ...
Dialogflow returns an empty list of conversations
Dialogflow returns an empty list of conversations, without responses, however there are conversations in the a...
Repeated "Internal Error" in Vertex AI Batch Prediction - Seeking Assistance
I recently trained a model with AutoML in Vertex AI to predict future ticket sales on the basis of past data f...
Gemini 1.5 pro latest REST API and system instructions
Hello,I use the Gemini REST API (https://ai.google.dev/gemini-api/docs/get-started/tutorial?lang=rest) but wit...
How to upload data to datastore in agent builder in GCP from google storage bucket
I am working on the development of a chatbot using agent builder in vertex ai in google cloud platform. I have...
Deploy AI in GC
I implemented an AI prediction model(GRU) and by running the code, the prediction result will show in Google S...
How do I enable Speaker Id on a free account
I've created a trial GCP account and enabled DialogFlow CX. I am trying to access Speaker ID but this seems im...
What exactly is the confidence score? Is it the confidence score of the text or the entity-value
I am using form parser currently from DocAI processors. Can you give me more clarity on whether the confidence...
How to Remove Default Messages in CCAI Web Chat SDK
I am currently working with the CCAI Web SDK and have encountered a situation where the default system message...
Gemini multiple API keys use for load balancing
Hi,Great forum, a big thank you to all those that make it possible,I am developing a chatbot app using Gemini ...
Dialogflow CX - Voice bot takes too long to response
I have a voice Bot integrated with the Cisco Webex contact center. This BOT is used for collecting customers' ...
How to correctly reference a dataframe in a Gemini Pro data summary prompt in a Vertex AI notebook
I'm running a prompt using Gemini Pro to analyze a dataset that includes entity sentiment analysis datapoints ...
Dialogflow voice input too sensitive
I would like to request help with the voice integration feature. I am currently building an agent for a busine...
Error Loading Vertex AI Prompt - Tracking Number: c8560245403438355
I'm encountering an error while loading a Vertex AI prompt in the Google Cloud Console. The error message is: ...
Need Urgent Help with Google OAuth Setup for App - Issues with App Blocked by Google
Hello everyone,I’m reaching out because I’m stuck and running out of time to resolve an issue with our Google ...
Outdated Gemini Pro image pricing? By tile, or by image?
I'm trying to understand the pricing for image inputs to Gemini Pro, which seems to be contradictory.On this p...
AutoML Translation models response time
Hi,We have several AutoML Translation models and we are facing timeout issues when the first translation reque...
Need Gemini LLM Ouput to be more grammatically tuned !!
Issue details: We are using Gemini Flash 002 for doing image and video analysis and predict content details. T...
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!
