[TEST PR] Add individual README.md files to each sample #135
Conversation
lethargicpanda
requested review from
JolandaVerhoef,
calren and
ksemenova
as code owners
Summary of ChangesHello @lethargicpanda, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances the AI sample catalog by adding comprehensive documentation for a wide array of new AI-powered features. The additions cover real-time voice interactions, multimodal input processing, advanced video analysis, on-device AI capabilities with Gemini Nano, and creative image generation and editing with Imagen. The overall goal is to provide clearer, more diverse examples of how to integrate and utilize Google's AI models in various applications, making it easier for developers to understand and implement these technologies. Highlights
Ignored Files
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request is a great initiative to improve the project's documentation by adding individual README files for each sample. The new files are well-structured and informative. I've identified a few areas for improvement, mainly concerning link consistency and correctness. There are some broken links, absolute URLs that should be relative, and one link pointing to the wrong API documentation. Addressing these points will enhance the quality and accuracy of the documentation.
|
|
||
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-writing-assistance/src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. | ||
|
|
||
| Here is the key snippet of code that runs the proofreading inference from [`GenAIWritingAssistanceViewModel.kt`](.src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt): |
There was a problem hiding this comment.
This link to the ViewModel is broken due to an extra . at the beginning of the path. Please remove it to fix the link.
| Here is the key snippet of code that runs the proofreading inference from [`GenAIWritingAssistanceViewModel.kt`](.src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt): | |
| Here is the key snippet of code that runs the proofreading inference from [`GenAIWritingAssistanceViewModel.kt`](./src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt): |
| } | ||
| ``` | ||
|
|
||
| Read more about the [Gemini API](https://developer.android.com/ai/gemini) in the Android Documentation. |
There was a problem hiding this comment.
This sample uses the Imagen API to generate the background, not the Gemini API. The link should point to the Imagen documentation for accuracy.
| Read more about the [Gemini API](https://developer.android.com/ai/gemini) in the Android Documentation. | |
| Read more about [Imagen](https://developer.android.com/ai/imagen) in the Android Documentation. |
| } | ||
| ``` | ||
|
|
||
| Read more about [getting started with Gemini](https://developer.android.com/ai/gemini) in the Android Documentation. |
There was a problem hiding this comment.
For consistency with other documentation changes in this pull request (like in gemini-chatbot/README.md), it would be better to use "the Gemini API" as the link text instead of "getting started with Gemini".
| Read more about [getting started with Gemini](https://developer.android.com/ai/gemini) in the Android Documentation. | |
| Read more about [the Gemini API](https://developer.android.com/ai/gemini) in the Android Documentation. |
|
|
||
| ## How it works | ||
|
|
||
| The application uses the ML Kit GenAI Image Description API to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIImageDescriptionViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-image-description/src/main/java/com/android/ai/samples/genai_image_description/GenAIImageDescriptionViewModel.kt) file. An `ImageDescriber` client is initialized. When a user provides an image, it's converted to a bitmap and sent to the `runInference` method, which streams back the generated description. |
There was a problem hiding this comment.
For consistency and portability (e.g., in forks), it's better to use a relative path for the link to the source file instead of an absolute GitHub URL.
| The application uses the ML Kit GenAI Image Description API to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIImageDescriptionViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-image-description/src/main/java/com/android/ai/samples/genai_image_description/GenAIImageDescriptionViewModel.kt) file. An `ImageDescriber` client is initialized. When a user provides an image, it's converted to a bitmap and sent to the `runInference` method, which streams back the generated description. | |
| The application uses the ML Kit GenAI Image Description API to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIImageDescriptionViewModel.kt`](./src/main/java/com/android/ai/samples/genai_image_description/GenAIImageDescriptionViewModel.kt) file. An `ImageDescriber` client is initialized. When a user provides an image, it's converted to a bitmap and sent to the `runInference` method, which streams back the generated description. |
|
|
||
| ## How it works | ||
|
|
||
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-writing-assistance/src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. |
There was a problem hiding this comment.
For consistency and portability, it's better to use a relative path for the link to the source file instead of an absolute GitHub URL.
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-writing-assistance/src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. | |
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](./src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. |
|
|
||
| ## How it works | ||
|
|
||
| The application uses the Firebase AI SDK (see [How to run](../../#how-to-run)) for Android to interact with the `imagen-4.0-ultra-generate-001` and `imagen-3.0-capability-001` models. The core logic is in the [`ImagenEditingDataSource.kt`](https://github.com/android/ai-samples/blob/main/samples/imagen-editing/src/main/java/com/android/ai/samples/imagenediting/data/ImagenEditingDataSource.kt) file. It first generates a base image using the generation model. Then, for editing, it takes the source image, a user-drawn mask, and a text prompt, and sends them to the editing model's `editImage` method to perform inpainting. |
There was a problem hiding this comment.
This link uses an absolute GitHub URL. For consistency with other links in this file and across the project, please use a relative path.
| The application uses the Firebase AI SDK (see [How to run](../../#how-to-run)) for Android to interact with the `imagen-4.0-ultra-generate-001` and `imagen-3.0-capability-001` models. The core logic is in the [`ImagenEditingDataSource.kt`](https://github.com/android/ai-samples/blob/main/samples/imagen-editing/src/main/java/com/android/ai/samples/imagenediting/data/ImagenEditingDataSource.kt) file. It first generates a base image using the generation model. Then, for editing, it takes the source image, a user-drawn mask, and a text prompt, and sends them to the editing model's `editImage` method to perform inpainting. | |
| The application uses the Firebase AI SDK (see [How to run](../../#how-to-run)) for Android to interact with the `imagen-4.0-ultra-generate-001` and `imagen-3.0-capability-001` models. The core logic is in the [`ImagenEditingDataSource.kt`](./src/main/java/com/android/ai/samples/imagenediting/data/ImagenEditingDataSource.kt) file. It first generates a base image using the generation model. Then, for editing, it takes the source image, a user-drawn mask, and a text prompt, and sends them to the editing model's `editImage` method to perform inpainting. |
|
/gemini review |
There was a problem hiding this comment.
Code Review
This pull request is a great addition, adding individual README files for each sample to improve documentation and user guidance. My review focuses on ensuring consistency and correctness in these new files. I've pointed out a few instances of absolute URLs that should be relative for better portability, and a broken link that needs fixing. Additionally, I've included a suggestion to improve code maintainability in one of the Kotlin files by replacing a hardcoded string with a constant.
|
|
||
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-writing-assistance/src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. | ||
|
|
||
| Here is the key snippet of code that runs the proofreading inference from [`GenAIWritingAssistanceViewModel.kt`](.src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt): |
There was a problem hiding this comment.
This relative link to the ViewModel is broken. It's missing a leading ./ which makes the path invalid.
| Here is the key snippet of code that runs the proofreading inference from [`GenAIWritingAssistanceViewModel.kt`](.src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt): | |
| Here is the key snippet of code that runs the proofreading inference from [`GenAIWritingAssistanceViewModel.kt`](./src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt): |
| private val generativeModel by lazy { | ||
| Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel( | ||
| "gemini-2.5-flash", | ||
| "gemini-2.0-flash", |
There was a problem hiding this comment.
For better maintainability and consistency, consider extracting the hardcoded model name "gemini-2.0-flash" into a constant within a companion object. This makes it easier to update the model name in the future and aligns with practices seen elsewhere in the project (e.g., ImagenEditingDataSource.kt).
Example:
private companion object {
private const val GEMINI_MODEL = "gemini-2.0-flash"
}
// ...
generativeModel(
GEMINI_MODEL,
// ...
)|
|
||
| ## How it works | ||
|
|
||
| The application uses the ML Kit GenAI Image Description API to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIImageDescriptionViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-image-description/src/main/java/com/android/ai/samples/genai_image_description/GenAIImageDescriptionViewModel.kt) file. An `ImageDescriber` client is initialized. When a user provides an image, it's converted to a bitmap and sent to the `runInference` method, which streams back the generated description. |
There was a problem hiding this comment.
The link to the ViewModel is an absolute GitHub URL. For consistency with other README files in this repository and to ensure links work correctly in forks, please use a relative path instead.
| The application uses the ML Kit GenAI Image Description API to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIImageDescriptionViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-image-description/src/main/java/com/android/ai/samples/genai_image_description/GenAIImageDescriptionViewModel.kt) file. An `ImageDescriber` client is initialized. When a user provides an image, it's converted to a bitmap and sent to the `runInference` method, which streams back the generated description. | |
| The application uses the ML Kit GenAI Image Description API to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIImageDescriptionViewModel.kt`](./src/main/java/com/android/ai/samples/genai_image_description/GenAIImageDescriptionViewModel.kt) file. An `ImageDescriber` client is initialized. When a user provides an image, it's converted to a bitmap and sent to the `runInference` method, which streams back the generated description. |
|
|
||
| ## How it works | ||
|
|
||
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-writing-assistance/src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. |
There was a problem hiding this comment.
This link to the ViewModel is an absolute GitHub URL. Please use a relative path for consistency and to ensure the link works in forks of this repository.
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-writing-assistance/src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. | |
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](./src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. |
|
|
||
| ## How it works | ||
|
|
||
| The application uses the Firebase AI SDK (see [How to run](../../#how-to-run)) for Android to interact with the `imagen-4.0-ultra-generate-001` and `imagen-3.0-capability-001` models. The core logic is in the [`ImagenEditingDataSource.kt`](https://github.com/android/ai-samples/blob/main/samples/imagen-editing/src/main/java/com/android/ai/samples/imagenediting/data/ImagenEditingDataSource.kt) file. It first generates a base image using the generation model. Then, for editing, it takes the source image, a user-drawn mask, and a text prompt, and sends them to the editing model's `editImage` method to perform inpainting. |
There was a problem hiding this comment.
This link is an absolute GitHub URL. For consistency and robustness, please change it to a relative path.
| The application uses the Firebase AI SDK (see [How to run](../../#how-to-run)) for Android to interact with the `imagen-4.0-ultra-generate-001` and `imagen-3.0-capability-001` models. The core logic is in the [`ImagenEditingDataSource.kt`](https://github.com/android/ai-samples/blob/main/samples/imagen-editing/src/main/java/com/android/ai/samples/imagenediting/data/ImagenEditingDataSource.kt) file. It first generates a base image using the generation model. Then, for editing, it takes the source image, a user-drawn mask, and a text prompt, and sends them to the editing model's `editImage` method to perform inpainting. | |
| The application uses the Firebase AI SDK (see [How to run](../../#how-to-run)) for Android to interact with the `imagen-4.0-ultra-generate-001` and `imagen-3.0-capability-001` models. The core logic is in the [`ImagenEditingDataSource.kt`](./src/main/java/com/android/ai/samples/imagenediting/data/ImagenEditingDataSource.kt) file. It first generates a base image using the generation model. Then, for editing, it takes the source image, a user-drawn mask, and a text prompt, and sends them to the editing model's `editImage` method to perform inpainting. |
|
/gemini review |
There was a problem hiding this comment.
Code Review
This pull request adds individual README.md files to several samples, which is a great improvement for documentation. The changes are mostly good, but I've identified a few areas for improvement. Specifically, there's a potential model name inconsistency in GeminiChatbotViewModel.kt that should be reviewed. Additionally, several of the new README files use absolute GitHub URLs instead of relative paths to link to source files, and one README contains a broken link. Using relative paths would improve consistency and ensure the links work correctly in various environments.
| private val generativeModel by lazy { | ||
| Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel( | ||
| "gemini-2.5-flash", | ||
| "gemini-2.0-flash", |
There was a problem hiding this comment.
The model name has been changed to gemini-2.0-flash, which appears to be a downgrade or a typo, as other samples in this repository use gemini-2.5-flash. Please verify if this change is intentional. If not, it should be updated to maintain consistency and use the intended model version.
| "gemini-2.0-flash", | |
| "gemini-2.5-flash", |
|
|
||
| ## How it works | ||
|
|
||
| The application uses the ML Kit GenAI Image Description API to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIImageDescriptionViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-image-description/src/main/java/com/android/ai/samples/genai_image_description/GenAIImageDescriptionViewModel.kt) file. An `ImageDescriber` client is initialized. When a user provides an image, it's converted to a bitmap and sent to the `runInference` method, which streams back the generated description. |
There was a problem hiding this comment.
The link to GenAIImageDescriptionViewModel.kt is an absolute GitHub URL. For consistency with other README files in the repository and to ensure links work correctly in different environments (like local clones), it's better to use a relative path.
| The application uses the ML Kit GenAI Image Description API to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIImageDescriptionViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-image-description/src/main/java/com/android/ai/samples/genai_image_description/GenAIImageDescriptionViewModel.kt) file. An `ImageDescriber` client is initialized. When a user provides an image, it's converted to a bitmap and sent to the `runInference` method, which streams back the generated description. | |
| The application uses the ML Kit GenAI Image Description API to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIImageDescriptionViewModel.kt`](./src/main/java/com/android/ai/samples/genai_image_description/GenAIImageDescriptionViewModel.kt) file. An `ImageDescriber` client is initialized. When a user provides an image, it's converted to a bitmap and sent to the `runInference` method, which streams back the generated description. |
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-writing-assistance/src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. | ||
|
|
||
| Here is the key snippet of code that runs the proofreading inference from [`GenAIWritingAssistanceViewModel.kt`](.src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt): |
There was a problem hiding this comment.
There are two issues with the links in this section:
- The link on line 15 to
GenAIWritingAssistanceViewModel.ktis an absolute GitHub URL. It should be a relative path for consistency. - The link on line 17 to the same file has a broken relative path (
.src/...instead of./src/...).
Please use a consistent, correct relative path for linking to source files.
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](https://github.com/android/ai-samples/blob/main/samples/genai-writing-assistance/src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. | |
| Here is the key snippet of code that runs the proofreading inference from [`GenAIWritingAssistanceViewModel.kt`](.src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt): | |
| The application uses the ML Kit GenAI Proofreading and Rewriting APIs to interact with the on-device Gemini Nano model. The core logic is in the [`GenAIWritingAssistanceViewModel.kt`](./src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt) file. `Proofreader` and `Rewriter` clients are initialized. When a user provides text, it's passed to either the `runProofreadingInference` or `runRewritingInference` method, which then returns the polished text. | |
| Here is the key snippet of code that runs the proofreading inference from [`GenAIWritingAssistanceViewModel.kt`](./src/main/java/com/android/ai/samples/genai_writing_assistance/GenAIWritingAssistanceViewModel.kt): |
|
|
||
| ## How it works | ||
|
|
||
| The application uses the Firebase AI SDK (see [How to run](../../#how-to-run)) for Android to interact with the `imagen-4.0-ultra-generate-001` and `imagen-3.0-capability-001` models. The core logic is in the [`ImagenEditingDataSource.kt`](https://github.com/android/ai-samples/blob/main/samples/imagen-editing/src/main/java/com/android/ai/samples/imagenediting/data/ImagenEditingDataSource.kt) file. It first generates a base image using the generation model. Then, for editing, it takes the source image, a user-drawn mask, and a text prompt, and sends them to the editing model's `editImage` method to perform inpainting. |
There was a problem hiding this comment.
The link to ImagenEditingDataSource.kt is an absolute GitHub URL. For consistency and to ensure the link works correctly in different environments (like local clones), it's better to use a relative path.
| The application uses the Firebase AI SDK (see [How to run](../../#how-to-run)) for Android to interact with the `imagen-4.0-ultra-generate-001` and `imagen-3.0-capability-001` models. The core logic is in the [`ImagenEditingDataSource.kt`](https://github.com/android/ai-samples/blob/main/samples/imagen-editing/src/main/java/com/android/ai/samples/imagenediting/data/ImagenEditingDataSource.kt) file. It first generates a base image using the generation model. Then, for editing, it takes the source image, a user-drawn mask, and a text prompt, and sends them to the editing model's `editImage` method to perform inpainting. | |
| The application uses the Firebase AI SDK (see [How to run](../../#how-to-run)) for Android to interact with the `imagen-4.0-ultra-generate-001` and `imagen-3.0-capability-001` models. The core logic is in the [`ImagenEditingDataSource.kt`](./src/main/java/com/android/ai/samples/imagenediting/data/ImagenEditingDataSource.kt) file. It first generates a base image using the generation model. Then, for editing, it takes the source image, a user-drawn mask, and a text prompt, and sends them to the editing model's `editImage` method to perform inpainting. |
1 participant
TEST PR