Generative AI overview

This document describes the generative artificial intelligence (AI) features that BigQuery ML supports. These features let you perform AI tasks in BigQuery ML by using pre-trained Vertex AI models and built-in BigQuery ML models.

Supported tasks include the following:

You access a Vertex AI model to perform one of these functions by creating a remote model in BigQuery ML that represents the Vertex AI model's endpoint. Once you have created a remote model over the Vertex AI model that you want to use, you access that model's capabilities by running a BigQuery ML function against the remote model.

This approach lets you use the capabilities of these Vertex AI models in SQL queries to analyze BigQuery data.

Workflow

You can use remote models over Vertex AI models and remote models over Cloud AI services together with BigQuery ML functions in order to accomplish complex data analysis and generative AI tasks.

The following diagram shows some typical workflows where you might use these capabilities together:

Diagram showing common workflows for remote models that use Vertex AI models or Cloud AI services.

Generate text

Text generation is a form of generative AI in which text is generated based on either a prompt or on analysis of data. You can perform text generation using both text and multimodal data.

Some common use cases for text generation are as follows:

  • Generating creative content.
  • Generating code.
  • Generating chat or email responses.
  • Brainstorming, such as suggesting avenues for future products or services.
  • Content personalization, such as product suggestions.
  • Classifying data by applying one or more labels to the content to sort it into categories.
  • Identifying the key sentiments expressed in the content.
  • Summarizing the key ideas or impressions conveyed by the content.
  • Identifying one or more prominent entities in text or visual data.
  • Translating the content of text or audio data to a different language.
  • Generating text that matches the verbal content in audio data.
  • Captioning or performing Q&A on visual data.

Data enrichment is a common next step after text generation, in which you enrich insights from the initial analysis by combining them with additional data. For example, you might analyze images of home furnishings to generate text for a design_type column, so that the furnishings SKU has an associated description, such as mid-century modern or farmhouse.

Supported models

To perform generative AI tasks, you can use remote models in BigQuery ML to reference to models deployed to or hosted in Vertex AI. You can create the following types of remote models:

Using text generation models

After you create a remote model, you can use the ML.GENERATE_TEXT function to interact with that model:

  • For remote models based on Gemini models, you can do the following:

    • Use the ML.GENERATE_TEXT function to generate text from a prompt that you specify in a query or pull from a column in a standard table. When you specify the prompt in a query, you can reference the following types of table columns in the prompt:

    • Use the ML.GENERATE_TEXT function to analyze text, image, audio, video, or PDF content from an object table with a prompt that you provide as a function argument.

  • For all other types of remote models, you can use the ML.GENERATE_TEXT function with a prompt that you provide in a query or from a column in a standard table.

Use the following topics to try text generation in BigQuery ML:

Grounding and safety attributes

You can use grounding and safety attributes when you use Gemini models with the ML.GENERATE_TEXT function, provided that you are using a standard table for input. Grounding lets the Gemini model use additional information from the internet to generate more specific and factual responses. Safety attributes let the Gemini model filter the responses it returns based on the attributes you specify.

Supervised tuning

When you create a remote model that references any of the following models, you can optionally choose to configure supervised tuning at the same time:

  • gemini-2.5-pro
  • gemini-2.5-flash-lite
  • gemini-2.0-flash-001
  • gemini-2.0-flash-lite-001

All inference occurs in Vertex AI. The results are stored in BigQuery.

Vertex AI Provisioned Throughput

For supported Gemini models, you can use Vertex AI Provisioned Throughput with the ML.GENERATE_TEXT function to provide consistent high throughput for requests. For more information, see Use Vertex AI Provisioned Throughput.

Generate structured data

Structured data generation is very similar to text generation, except you can additionally format the response from the model by specifying a SQL schema.

To generate structured data, create a remote model over any of the generally available or preview Gemini models. You can then use the AI.GENERATE_TABLE function to interact with that model. To try creating structured data, see Generate structured data by using the AI.GENERATE_TABLE function.

You can specify safety attributes when you use Gemini models with the AI.GENERATE_TABLE function in order to filter the model's responses.

Generate values of a specific type by row

You can use scalar generative AI functions with Gemini models to analyze data in BigQuery standard tables. Data includes both text data and unstructured data from columns that contain ObjectRef values. For each row in the table, these functions generate output containing a specific type.

The following AI functions are available:

When you use the AI.GENERATE function with supported Gemini models, you can use Vertex AI Provisioned Throughput to provide consistent high throughput for requests. For more information, see Use Vertex AI Provisioned Throughput.

Generate embeddings

An embedding is a high-dimensional numerical vector that represents a given entity, like a piece of text or an audio file. Generating embeddings lets you capture the semantics of your data in a way that makes it easier to reason about and compare the data.

Some common use cases for embedding generation are as follows:

  • Using retrieval-augmented generation (RAG) to augment model responses to user queries by referencing additional data from a trusted source. RAG provides better factual accuracy and response consistency, and also provides access to data that is newer than the model's training data.
  • Performing multimodal search. For example, using text input to search images.
  • Performing semantic search to find similar items for recommendations, substitution, and record deduplication.
  • Creating embeddings to use with a k-means model for clustering.

Supported models

The following models are supported:

For a smaller, lightweight text embedding, try using a pretrained TensorFlow model, such as NNLM, SWIVEL, or BERT.

Using embedding generation models

After you create the model, you can use the ML.GENERATE_EMBEDDING function to interact with it. For all types of supported models, ML.GENERATE_EMBEDDING works with structured data in standard tables. For multimodal embedding models, ML.GENERATE_EMBEDDING also works with visual content from either standard table columns that contain ObjectRef values, or from object tables.

For remote models, all inference occurs in Vertex AI. For other model types, all inference occurs in BigQuery. The results are stored in BigQuery.

Use the following topics to try text generation in BigQuery ML:

Forecasting

Forecasting is a technique that lets you analyze historical time series data in order to make an informed prediction about future trends. You can use BigQuery ML's built-in TimesFM time series model (Preview) to perform forecasting without having to create your own model. The built-in TimesFM model works with the AI.FORECAST function to generate forecasts based on your data.

Locations

Supported locations for text generation and embedding models vary based on the model type and version that you use. For more information, see Locations. Unlike other generative AI models, location support doesn't apply to the built-in TimesFM time series model. The TimesFM model is available in all BigQuery supported regions.

Pricing

You are charged for the compute resources that you use to run queries against models. Remote models make calls to Vertex AI models, so queries against remote models also incur charges from Vertex AI.

For more information, see BigQuery ML pricing.

What's next