Stay organized with collections Save and categorize content based on your preferences.
Task-specific solutions overviewThis document describes the artificial intelligence (AI) features that BigQuery ML supports. These features let you develop task-specific solutions in BigQuery ML by using Cloud AI APIs. Supported tasks include the following:
You access a Cloud AI API to perform one of these functions by creating a remote model in BigQuery ML that represents the API endpoint. Once you have created a remote model over the AI resource that you want to use, you access that resource's capabilities by running a BigQuery ML function against the remote model.
This approach lets you use the capabilities of the underlying API without having to know Python or develop familiarity with API.
WorkflowYou 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:
Natural language processingYou can use natural language processing to perform tasks such as classification and sentiment analysis on your data. For example, you could analyze product feedback to estimate whether customers like a particular product.
To perform natural language tasks, you can create a reference to the Cloud Natural Language API by creating a remote model and specifying CLOUD_AI_NATURAL_LANGUAGE_V1 for the REMOTE_SERVICE_TYPE value. You can then use the ML.UNDERSTAND_TEXT function to interact with that service. ML.UNDERSTAND_TEXT works with data in standard tables. All inference occurs in Vertex AI. The results are stored in BigQuery.
To learn more, try understanding text with the ML.UNDERSTAND_TEXT function.
You can use machine translation to translate text data into other languages. For example, translating customer feedback from an unfamiliar language into a familiar one.
To perform machine translation tasks, you can create a reference to the Cloud Translation API by creating a remote model and specifying CLOUD_AI_TRANSLATE_V3 for the REMOTE_SERVICE_TYPE value. You can then use the ML.TRANSLATE function to interact with that service. ML.TRANSLATE works with data in standard tables. All inference occurs in Vertex AI. The results are stored in BigQuery.
To learn more, try translating text with the ML.TRANSLATE function.
You can use audio transcription to transcribe audio files into written text. For example, transcribing a voicemail recording into a text message.
To perform audio transcription tasks, you can create a reference to the Speech-to-Text API by creating a remote model and specifying CLOUD_AI_SPEECH_TO_TEXT_V2 for the REMOTE_SERVICE_TYPE value. You can optionally specify a recognizer to use to process the audio content. You can then use the ML.TRANSCRIBE function to transcribe audio files. ML.TRANSCRIBE works with audio files in object tables. All inference occurs in Vertex AI. The results are stored in BigQuery.
To learn more, try transcribing audio files with the ML.TRANSCRIBE function.
You can use document processing to extract insights from unstructured documents. For example, extracting relevant information from invoice files so it can be input into accounting software.
To perform document processing tasks, you can create a reference to the Document AI API by creating a remote model, specifying CLOUD_AI_DOCUMENT_V1 for the REMOTE_SERVICE_TYPE value, and specifying a processor to use to process the document content. You can then use the ML.PROCESS_DOCUMENT function to process documents. ML.PROCESS_DOCUMENT works on documents in object tables. All inference occurs in Vertex AI. The results are stored in BigQuery.
To learn more, try processing documents with the ML.PROCESS_DOCUMENT function.
You can use computer vision to perform image analysis tasks. For example, you could analyze images to detect whether they contain faces, or to generate labels describing the objects in the image.
To perform computer vision tasks, you can create a reference to the Cloud Vision API by creating a remote model and specifying CLOUD_AI_VISION_V1 for the REMOTE_SERVICE_TYPE value. You can then use the ML.ANNOTATE_IMAGE function to annotate images by using that service. ML.ANNOTATE_IMAGE works with data in object tables. All inference occurs in Vertex AI. The results are stored in BigQuery.
To learn more, try annotating object table images with the ML.ANNOTATE_IMAGE function.
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2025-08-07 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07 UTC."],[[["BigQuery ML supports AI features via Cloud AI APIs, enabling task-specific solutions like natural language processing, machine translation, audio transcription, document processing, and computer vision."],["You can access Cloud AI API functionalities by creating a remote model in BigQuery ML, which represents the API endpoint, and then use BigQuery ML functions against the remote model."],["This system allows you to utilize the capabilities of the underlying AI APIs without requiring expertise in Python or detailed API familiarity."],["Remote models over Vertex AI and Cloud AI services can be combined with BigQuery ML functions to perform complex data analysis and generative AI tasks."],["The inference for each of the processes (natural language processing, machine translation, audio transcription, document processing and computer vision) occurs in Vertex AI and the results are stored in BigQuery."]]],[]]
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4