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...
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 : 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...
Is anyone aware of third party that is offering any LLMs trained on the insurance domain(s)?
I've been asked to explore what's available in the marketplace for LLM options where foundation models are bei...
Dialogflow CX response after conversation is idile
hi @xavidop I would like to know if there is a way using DialogFlow CX to get the chatbot to send a follow up ...
How can I efficiently deploy a machine learning model using Google Cloud AI Platform?
To efficiently deploy a machine learning model on Google Cloud AI Platform:1. Train: Use AI Platform Training ...
GCP & AI Managing Quotas/Rate limits - What am I missing
I've been trying to transition from OpenAI/AWS to Gemini/GCP for a project and I am extremely frustrated. I ca...
DialogflowCX - escalate conversation after 30 seconds of no user input
Hello, At point of the conversation, after we´ve prompt the user to imput a comment, we need to escalate the c...
Error 499 - The operation was cancelled on STTv2, one in 10 times
Hello,After updating to v2 of the Speech to Text python API, I get error 499 - The operation was cancelled eve...
BigQuery Studio Partition and Clustering recommendations not working
I checked my table, it is pretty big but there are no recommendations, is it possible for me to know why the r...
Building a Business
Hi folks: I’m an entrepreneur and founder. My company is a digital technology startup. Currently, we are proto...
DialogFlow intents with different contexts having same training phrases
Hi, From the DialogFlow best practice pack, I understand that generally intents should not have similar traini...
Dialogflow CX to Bigquery in GCP
I've set up a BigQuery table with columns representing various intents used in Dialogflow CX, each stored as i...
Google Vertex support scope for models and troubleshooting
Hi, I'm looking for more information on the scope of coverage for AI models in Google Vertex. What if there is...
Continuing chats with uploaded file
Hi! I'm using the Gemini Python SDK to transcribe a long audio file. My system prompt includes instructions fo...
text-bison@001 IAM_PERMISSION_DENIED
Hello,I am currently facing an issue with calling the text-bison@001 API in my App Engine deployment. While th...
AI and big data in stock market analysis
Hello Guys !I'm writing my master thesis. It is about usage of AI and Big data to analyse stock market data. I...
Emmanuel Katto Uganda : How long does it take for Google to verify my account?
Hello everyone,I'm Emmanuel Katto from Uganda, I have a question about Google account verification: Does anyon...
Secret Manager and vertex AI permission issue with service account
HI All,I am using vertex ai and secret manager. I am able to create the client and access the secret when i ru...
Bug with Max Predictions in AutoML Batch Predictions (image object detection)
I am not able to get the batch prediction API for an AutoML image object detection request to recognize a "max...
Agent Builder and tool Query
Hi,I have recently started using the Agent builder and setup the tool. The tool has 3 data stores, one is webs...
Difference between Vertex AI search & conversation vs Vertex Palm API
Is there documentation that compares Vertex AI search & conversation with Vertex AI Palm or Palm2 API? What ar...
Dialogflow CX - Extracting & Comparing Confidence Scores for Multi-Intent Matching
Hello, I'm developing a chat agent in Dialogflow CX and I want it to handle ambiguous inputs effectively. Spec...
Dialogflow CX Match Confidence goes over 1.0
Hi,I'm using DialogFlow CX and I have noticed (since few days) that the match confidence value has changed. Un...
Articles from Product Experts and Googlers
Protect your LLM applications with Google Cloud Services
Generative AI offers immense power, but with it comes significant risk. This article discuss how to protect your LLM applications from prompt injection, data leakage, and other threats using a multi-layered security approach with Google Cloud services like Natural Language API, Model Armor, and vector databases.
Evaluating success in a multi-agent system: Why trajectory assessment and handoffs matters
Your AI agents are only as good as their ability to collaborate. As we move from single agents using tools to multi-agent ecosystems, our methods for evaluating success must evolve. Learn why trajectory and handoffs matter more than ever.
Media CDN flexible origin shielding: Reducing origin load, latency, and improving viewer experience
Discover how Media CDN's new flexible origin shielding enhances content delivery! Learn how to reduce origin load, optimize latency, and improve viewer experience by precisely controlling your shield locations.
