With ML Kit's GenAI Prompt API, you can send natural language requests on-device to Gemini Nano . GenAI Prompt API accepts either a text input or a combined image and text input, and emits text output.
You can use GenAI Prompt API for a variety of use cases, including the following:
| Use case |
Example |
| Image understanding |
Analyzing photos for classification, such as "pets", "food", or "travel". |
| Short translations |
Translating short messages between a delivery driver and customer. |
| Guided summarization |
Summarizing reviews of a restaurant based on a user's specific interest. |
| Entity extraction |
Extracting important details about an upcoming event from an email thread. |
| Content generation inspiration |
Suggesting prompts for a journal entry. |
| Intelligent document scanning |
Extracting and categorizing items from a receipt image. |
| Text classification |
Classifying customer reviews into a positive, neutral, or negative category. |
Prompt API versus feature-specific APIs
The existing ML Kit GenAI APIs support the Summarization , Proofreading , Rewriting , and Image Description use cases, which Prompt API also supports. The following table outlines the benefits of each:
Consideration
Prompt API
Feature-specific APIs
Integration effort
High.
Requires more effort to implement, due to prompt engineering and quality assurance.
Low.
Requires less effort, as these APIs are already fine-tuned for specific use cases. No need to work directly with the LLM.
Flexibility
More flexibility, as you can custom engineer the prompt.
Less flexibility. Each API has fixed fine-tuning and a built-in prompt that has the following characteristics:
- Summarizations can only be in 1-3 bullet points.
- Image description is generic and short.
- Rewriting supports only predefined styles.
As a general rule, use Prompt API when you need more customization and flexibility, and use the feature-specific APIs for standard tasks that don't require complex logic.
