ML.PREDICT

Related topics

• ML.PREDICT is part of BigQuery ML From the official documentation: “BigQuery ML supports prediction functionalities through the [`ML.PREDICT` function](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-predict), with the following models:”
• ML.PREDICT works with remote model From the official documentation: “After you create a remote model, you can use it with the [`ML.PREDICT` function](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-predict) to get predictions from the custom model deployed to Agent Platform.”
• ML.PREDICT is part of Spanner From the official documentation: “To verify the model was registered correctly, query it with the [ML.PREDICT](/spanner/docs/reference/standard-sql/ml-functions#mlpredict) function.”
• BigQuery is an alternative to Cloud Storage From the official documentation: “The `import_result_sink` must be a Cloud Storage path or a BigQuery table.”
• BigQuery works with Cloud Storage From the official documentation: “Sample to load Avro data from Cloud Storage into a new BigQuery table”
• BigQuery works with Spanner From the official documentation: “Federated analytics seamlessly combine data from Spanner and other sources in BigQuery.”
• BigQuery ML works with Cloud Storage From the official documentation: “You can export BigQuery ML models to Cloud Storage, and use them for online prediction, or edit them in Python.”
• BigQuery works with Gemini Enterprise Agent Platform From the official documentation: “The BigQuery dataset stores all versions for the associated Gemini Enterprise Agent Platform dataset.”
• Cloud resource connection works with Cloud Storage From the official documentation: “Cloud resource connection lets BigQuery access Cloud Storage object data and metadata using its own service account.”
• Cloud resource connection works with Gemini Enterprise Agent Platform From the official documentation: “BigQuery uses a [Cloud resource connection](/bigquery/docs/create-cloud-resource-connection) to interact with the Gemini Enterprise Agent Platform endpoint.”
• Cloud Storage works with Gemini Enterprise Agent Platform From the official documentation: “When you perform custom training, Agent Platform usually loads your data from Cloud Storage.”
• remote model is part of BigQuery ML From the official documentation: “- Create a BigQuery ML remote model.”
• Agent Platform works with BigQuery ML From the official documentation: “Learn how to use BigQuery ML for training with Gemini Enterprise Agent Platform.”
• Agent Platform works with Cloud Storage From the official documentation: “Load the model's `state_dict` object into Cloud Storage by using a Agent Platform custom job:”
• Agent Platform works with Spanner From the official documentation: “If both the Spanner database and the Agent Platform endpoint are in the same project, then no additional setup is required.”
• BigQuery works with Cloud resource connection From the official documentation: “After you create the training dataset, you establish a connection to link BigQuery and external sources.”
• BigQuery works with CREATE MODEL From the official documentation: “This document describes the `CREATE MODEL` statement for importing [TensorFlow Lite](https://ai.google.dev/edge/litert) models into BigQuery by using SQL.”
• BigQuery ML works with Gemini Enterprise Agent Platform From the official documentation: “You can also access Agent Platform models by using BigQuery ML.”
• Cloud resource connection is part of BigQuery From the official documentation: “A Cloud resource connection in BigQuery lets you connect BigQuery to other Google Cloud services and external storage by using a dedicated service account with delegated access.”
• Cloud resource connection works with Spanner From the official documentation: “A Cloud resource connection associated with a service account is used to connect to the Spanner.”
• CREATE MODEL depends on Cloud Storage From the official documentation: “The following steps show you how to import the sample ONNX model from Cloud Storage by using a [`CREATE MODEL`](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-onnx) statement.”
• CREATE MODEL configures remote model From the official documentation: “Use the [`CREATE MODEL`](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-remote-model) statement to create a remote model that represents a hosted Agent Platform model:”
• remote model depends on Gemini Enterprise Agent Platform From the official documentation: “Create a remote model that represents a hosted Agent Platform model:”
• Agent Platform works with BigQuery From the official documentation: “BigQuery and Agent Platform are tightly integrated, letting you access and analyze your data directly within the Agent Platform platform.”
• BigQuery works with BigQuery ML From the official documentation: “BigQuery ML lets you build and operationalize machine learning (ML) models over data in BigQuery by using SQL.”
• BigQuery depends on Cloud resource connection From the official documentation: “BigQuery uses a [Cloud resource connection](/bigquery/docs/create-cloud-resource-connection) to interact with the Cloud AI service.”
• BigQuery depends on Cloud Storage From the official documentation: “BigQuery relies on Cloud Storage for staging file data and supports reading from and writing to several other sources and Google Cloud services.”
• BigQuery works with remote model From the official documentation: “The function uses a BigQuery ML [remote model](/bigquery/docs/reference/standard-sql/bigqueryml-syntax-create-remote-model-service) to connect BigQuery to the Cloud Natural Language API.”
• BigQuery ML is part of BigQuery From the official documentation: “BigQuery ML models are stored in BigQuery datasets, similar to tables and views.”
• BigQuery ML depends on Cloud Storage From the official documentation: “BigQuery ML imports the model from Cloud Storage by using the credentials of the user who runs the `CREATE MODEL` statement.”
• BigQuery ML is an alternative to Gemini Enterprise Agent Platform From the official documentation: “You can use [BigQuery ML](/bigquery/docs/bqml-introduction) or [Agent Platform development tools](/gemini-enterprise-agent-platform/machine-learning/general/developer-tools-overview) to develop, train, and evaluate ML models.”
• Cloud resource connection depends on Cloud Storage From the official documentation: “- `CONNECTION_ID`: A `STRING` value that contains a [Cloud resource connection](/bigquery/docs/create-cloud-resource-connection) that the service can use to access the objects in Cloud Storage, in the format `location.connection_id`.”
• Cloud resource connection works with remote model From the official documentation: “Create a [Cloud resource connection](/bigquery/docs/create-cloud-resource-connection) for the remote model to use, and get the connection's service account.”
• Cloud Storage works with Spanner From the official documentation: “Move Spanner databases to and from Avro or CSV files stored in Cloud Storage.”
• CREATE MODEL is part of Spanner From the official documentation: “To register this model in a Spanner database, [execute](/spanner/docs/schema-updates) the following DDL [statement](/spanner/docs/reference/standard-sql/data-definition-language#create_model): ```sql CREATE MODEL TextBison INPUT (prompt STRING(MAX)) OUTPUT (content STRING(MAX))…”
• Gemini Enterprise Agent Platform depends on Cloud Storage From the official documentation: “Certain tasks in Agent Platform require that you use additional Google Cloud products besides Agent Platform. For example, in most cases, you must use Cloud Storage and Artifact Registry when you create a custom training pipeline.”
• Gemini Enterprise Agent Platform works with remote model From the official documentation: “Create a remote model that represents a hosted Agent Platform `gemini-3.5-flash-lite` model:”
• Gemini Enterprise Agent Platform works with Spanner From the official documentation: “MODEL DDL statements and ML functions in Spanner invoke Gemini Enterprise Agent Platform endpoints and can fail due to various reasons:”