PulseAugur
EN
LIVE 22:31:06

BigQuery ML integrates Vertex AI for text generation, detailing costs

By PulseAugur Editorial · [2 sources] ·

BigQuery ML users can now create remote models that reference Vertex AI endpoints, enabling text generation capabilities directly within BigQuery. This setup involves creating a connection object that acts as an intermediary for authorization, preventing direct IAM roles for analysts. The pricing for these remote model calls is split between BigQuery's data scanning costs and Vertex AI's token processing fees, with Vertex AI costs typically dominating for text generation tasks. AI

IMPACT Enables direct use of generative AI models within data warehousing workflows, potentially streamlining data analysis and application development.

RANK_REASON This describes a technical integration and usage pattern for existing products, not a new product release or significant industry event.

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

BigQuery ML integrates Vertex AI for text generation, detailing costs

COVERAGE [2]

  1. dev.to — LLM tag TIER_1 English(EN) · Multigrid ·

    Creating a Remote Model in BigQuery ML for Text Generation

    <p>The <code>CREATE MODEL</code> statement is one line. Everything that goes wrong happens in the two steps before it, in a connection object and an IAM grant on a service account that BigQuery creates for you and does not mention again.</p> <h2> What a remote model is </h2> <p>A…

  2. dev.to — LLM tag TIER_1 English(EN) · Multigrid ·

    BigQuery ML Pricing for Remote Model Calls

    <p>A generation query in BigQuery is billed twice: once by BigQuery for the bytes it scanned, and once by Vertex AI for the tokens the model processed. The two numbers are not close to each other, and knowing which one dominates changes what you optimise.</p> <h2> Two meters, one…

RELATED ENTITIES

RELATED TOPICS