Gemini for AutoML text users
AutoML Text is deprecated.This page provides comparisons between AutoML Textand Gemini to help AutoML text users understand how to useGemini.
Check the tables that apply to your use case, andreview the changes that are likely to impact your workflow.
General usage
These differences are applicable to all Gemini users.
| Operation | AutoML text | Gemini |
|---|---|---|
| Training data formats | You can use CSV or JSON Lines files, except for text entity extraction, to include inline text snippets or to reference documents that are of typeTXT. Entity extraction supports only JSON Lines files. | You can only use JSON Line files. Each line in the file should represent asingle training example. You can download asample dataset for fine-tuning Gemini models. Files should be stored in Cloud Storage. |
| Dataset annotation | Annotations are grouped together as anAnnotationSet object. You can use different annotation sets with the same dataset. | Dataset annotations are not applicable with Gemini. |
| Dataset import | You specify ML use values in an optional column for CSV, in the same row as the data; or as a tag in JSON Lines in the same JSON object as the data. If you don't specify ML use values, your data is split automatically for training, testing, and validation. For sentiment analysis, CSV files must include the sentiment max value in the last column of each row. | You need to have two separate JSONL files, one for training and one for validation. The validation file is optional. The validation file should have 10-256 examples. |
| Storage costs | When you create a dataset, your data is loaded into Cloud Storage in your project. You are charged for this storage.Learn more. | When you create a dataset, your data is loaded into Cloud Storage in your project. You are charged for this storage.Learn more |
| Data labeling | You provide labeling instructions by using a URL. Annotations are part of theDataset object and can't be manipulated by using the API. | Data labeling is not applicable with Gemini. |
| Model deployment | You create anEndpoint object, which provides resources for serving online inferences. You then deploy the model to the endpoint. To request inferences, you call thepredict() method. | After fine-tuning Gemini, the model is stored inVertex AI Model Registry, and an Endpoint is automatically created. Online inferences from the tuned modelcan be requested using the Python SDK, REST API, or the console. You request inferences by first fetching the tuned endpoint and then using thegenerate_content() method. |
| Using project number or project ID | Bothproject-number andproject-id work in Vertex AI. | Gemini usesproject-id. |
| Confidence scores | AutoML text supports confidence scores. | Gemini doesn't support confidence scores. |
API users
For detailed information about the API, see theVertex AI Generative AI Tuning API reference documentation.
| Operation or entity | AutoML text | Gemini |
|---|---|---|
| Model Creation | You create aTrainingPipeline object, which returns a training job. | You create aSupervised Fine Tuning job which returns the tuning job. |
| Using the client library | There are different API clients for each API resource. | You can create a Supervised Fine-tuning Job for Gemini using the Python SDK, REST API or the Console. |
| Requesting inferences | You request inferences by calling thepredict() method on the Endpoint resource. | You request inferences by first fetching the tuned endpoint and then using thegenerate_content method. |
| Online inference endpoint | In the following, replaceREGION with the region that your inference model is in.REGION-aiplatform.googleapis.com. For example:us-central1-aiplatform.googleapis.com | In the following, replaceTUNING_JOB_REGION with the region where your tuning job runs.TUNING_JOB_REGION-aiplatform.googleapis.com. For example:us-central1-aiplatform.googleapis.com |
| Schema and definition files | Some request and response fields are defined in schema and definition files. Data formats are defined using predefined schema files. This enables flexibility for the API and data formats. | Therequest body,model parameters, andresponse body are the same as with the untuned Gemini models. Seesample requests. |
| Hostname | aiplatform.googleapis.com | aiplatform.googleapis.com |
| Regional hostname | Required. For example:us-central1-aiplatform.googleapis.com | Required. For example:us-central1-aiplatform.googleapis.com |
What's next
To get started with tuning, seeModel tuning for Gemini text models
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2025-12-15 UTC.