Multi-turn conversations

.allstar/binary_artifacts.yaml

@@ -0,0 +1,3 @@
+ignorePaths:
+- generativeai-android-sample/gradle/wrapper/gradle-wrapper.jar
+- gradle/wrapper/gradle-wrapper.jar

.github/workflows/build_release.yml

@@ -20,17 +20,35 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-java@v3
+      - uses: actions/checkout@v4
+      - uses: actions/setup-java@v4
         with:
           distribution: 'temurin'
           java-version: '17'
           cache: gradle
-      - name: Perform a Gradle build
+      - name: Build the generativeai release artifacts
         run: ./gradlew generativeai:publishAllPublicationsToMavenRepository
+
       - name: Upload generated artifacts
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
+
         with:
           name: generative-ai-android
           path: generativeai/m2
           retention-days: 5
+      - name: Build the common release artifacts
+        run: ./gradlew common:publishAllPublicationsToMavenRepository
+      - name: Upload the common artifacts
+        uses: actions/upload-artifact@v2
+        with:
+          name: common-artifacts
+          path: common/m2
+          retention-days: 5
+      - name: Build the release artifacts for all sdks
+        run: ./gradlew publishAllPublicationsToMavenRepository
+      - name: Upload the generated artifacts
+        uses: actions/upload-artifact@v2
+        with:
+          name: release-artifacts
+          path: m2
+          retention-days: 5

.github/workflows/check-code-format.yml

@@ -7,9 +7,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout branch
-        uses: actions/checkout@v3.5.3
+        uses: actions/checkout@v4
       - name: Set up JDK 17
-        uses: actions/setup-java@v3
+        uses: actions/setup-java@v4
         with:
           java-version: 17
           distribution: temurin

.github/workflows/check-licensing.yml

@@ -7,9 +7,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout branch
-        uses: actions/checkout@v3.5.3
+        uses: actions/checkout@v4
       - name: Set up JDK 17
-        uses: actions/setup-java@v3
+        uses: actions/setup-java@v4
         with:
           java-version: 17
           distribution: temurin

.github/workflows/check_for_api_changes.yml

@@ -7,40 +7,46 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout master
-        uses: actions/checkout@v3.5.3
+        uses: actions/checkout@v4
         with:
           ref: ${{ github.base_ref }}
 
       - name: Set up JDK 17
-        uses: actions/setup-java@v3
+        uses: actions/setup-java@v4
         with:
           java-version: 17
           distribution: temurin
           cache: gradle
 
       - name: Generate the api file
         run: |
-          ./gradlew generativeai:exportApi --no-daemon
+          ./gradlew exportApi --no-daemon
 
       - name: Save public.api from master
-        run: mv generativeai/public.api ~/public.api
+        run: |
+          mkdir ~/common/ && \
+          mkdir ~/generativeai/ && \
+          mv generativeai/public.api ~/generativeai/public.api && \
+          mv common/public.api ~/common/public.api
 
       - name: Checkout branch
-        uses: actions/checkout@v3.5.3
+        uses: actions/checkout@v4
 
       - name: Set up JDK 17
-        uses: actions/setup-java@v3
+        uses: actions/setup-java@v4
         with:
           java-version: 17
           distribution: temurin
           cache: gradle
 
       - name: Copy saved api to branch
-        run: mv ~/public.api generativeai/public.api
+        run: |
+          mv ~/generativeai/public.api generativeai/public.api && \
+          mv ~/common/public.api common/public.api
 
       - name: Run api warning task
         run: |
-          ./gradlew generativeai:warnAboutApiChanges --no-daemon
+          ./gradlew warnAboutApiChanges --no-daemon
 
       - name: Add PR Comment
         if: ${{ hashFiles('api_changes.md') != '' }}

.github/workflows/generate_docs.yml

@@ -20,16 +20,16 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-java@v3
+      - uses: actions/checkout@v4
+      - uses: actions/setup-java@v4
         with:
           distribution: 'temurin'
           java-version: '17'
           cache: gradle
       - name: Run dokka
         run: ./gradlew generativeai:dokkaHtml
       - name: Upload generated docs
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           name: google-ai-android
           path: generativeai/build/dokka/html

.github/workflows/unit-tests.yml

@@ -7,9 +7,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout branch
-        uses: actions/checkout@v3.5.3
+        uses: actions/checkout@v4
       - name: Set up JDK 17
-        uses: actions/setup-java@v3
+        uses: actions/setup-java@v4
         with:
           java-version: 17
           distribution: temurin

.github/workflows/warn-version-bump.yml

@@ -0,0 +1,48 @@
+name: Warn Version Bump
+
+on: pull_request
+
+jobs:
+  warn-version-bump:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout target branch
+        uses: actions/[email protected]
+        with:
+          ref: ${{ github.base_ref }}
+
+      - name: Set up JDK 17
+        uses: actions/setup-java@v3
+        with:
+          java-version: 17
+          distribution: temurin
+          cache: gradle
+
+      - name: Generate the api file
+        run: |
+          ./gradlew exportApi --no-daemon
+
+      - name: Save public.api from target branch
+        run: |
+          mkdir ~/common/ && \
+          mkdir ~/generativeai/ && \
+          mv generativeai/public.api ~/generativeai/public.api && \
+          mv common/public.api ~/common/public.api
+
+      - name: Checkout branch
+        uses: actions/[email protected]
+
+      - name: Set up JDK 17
+        uses: actions/setup-java@v3
+        with:
+          java-version: 17
+          distribution: temurin
+          cache: gradle
+
+      - name: Copy saved api to branch
+        run: |
+          mv ~/generativeai/public.api generativeai/public.api && \
+          mv ~/common/public.api common/public.api
+      - name: Run API versioning check
+        run: |
+          if ! test -d .changes || git diff --quiet ${{ github.event.pull_request.base.sha }}..HEAD .changes ; then ./gradlew warnVersionBump ; else exit 0 ; fi

DEVELOPING.md

@@ -15,15 +15,15 @@ hooks, run the following command at the root of your repo directory:
 
 To locally publish the m2 repo:
 
-`./gradlew generativeai:publishToMavenLocal`
+`./gradlew publishToMavenLocal`
 
 To generate a releasable m2 repo:
 
-`./gradlew generativeai:publishAllPublicationsToMavenRepository`
+`./gradlew publishAllPublicationsToMavenRepository`
 
-The m2 repo will be in `generativeai/m2`.
+The m2 repo will be in `/m2`.
 
-To generate Dokka:
+To generate Dokka for the generativeai project:
 
 `./gradlew generativeai:dokkaHtml`
 
@@ -60,6 +60,20 @@ change
 Both of these commands should generate a new file under the `.changes` directory with your message
 and impact.
 
+Note though, that this will naturally create release notes for *all* projects. If you only want
+to generate a change for the `generativeai` project, then prefix your message with the project name:
 
-To learn more, read the section on our changelog plugin in our [plugin readme](./plugins/README.md).
+```bash
+change generativeai "hello world!"
+```
 
+You can also do it for other projects as well, just supply the project name:
+
+```bash
+change common "hello world!"
+```
+
+Although, this does *not* support creating empty changes. You'll have to make that change manually,
+if that's what you want.
+
+To learn more, read the section on our changelog plugin in our [plugin readme](./plugins/README.md).

README.md

@@ -1,60 +1,66 @@
 # Google AI SDK for Android
 
-The Google AI client SDK for Android enables developers to use Google's state-of-the-art generative AI models (like Gemini) to build AI-powered features and applications. This SDK supports use cases like:
-- Generate text from text-only input
-- Generate text from text-and-images input (multimodal)
-- Build multi-turn conversations (chat)
+The Google AI Android SDK is the easiest way for Android developers to build with the Gemini API. The Gemini API gives you access to Gemini [models](https://ai.google.dev/models/gemini) created by [Google DeepMind](https://deepmind.google/technologies/gemini/#introduction). Gemini models are built from the ground up to be multimodal, so you can reason seamlessly across text, images, and code.
 
-For example, with just a few lines of code, you can access Gemini's multimodal capabilities to generate text from text-and-image input:
-
-```kotlin
-val generativeModel = GenerativeModel(
-    modelName = "gemini-1.0-pro-vision-latest",
-    apiKey = BuildConfig.apiKey
-)
-
-val cookieImage: Bitmap = // ...
-val inputContent = content() {
-  image(cookieImage)
-  text("Does this look store-bought or homemade?")
-}
-
-val response = generativeModel.generateContent(inputContent)
-print(response.text)
-```
+> [!CAUTION]
+> **The Google AI SDK for Android is recommended for prototyping only.** If you plan to enable billing, we strongly recommend that you use a backend SDK to access the Google AI Gemini API. You risk
+> potentially exposing your API key to malicious actors if you embed your API key directly in your Android app or fetch it remotely at runtime.
 
 > [!NOTE]
 > If you want to access Gemini on-device (Gemini Nano), check out the [Google AI Edge SDK for Android](https://ai.google.dev/tutorials/android_aicore), which is enabled via Android AICore.
 
-## Try out the sample Android app
+## Get started with the Gemini API
 
 This repository contains a sample app demonstrating how the SDK can access and utilize the Gemini model for various use cases.
 
-To try out the sample app you can directly import the project from Android Studio 
+To try out the sample app you can directly import the project from Android Studio
 via **File > New > Import Sample** and searching for *Generative AI Sample* or follow these steps below:
 
-1.  Check out this repository.\
+1. Go to [Google AI Studio](https://aistudio.google.com/).
+2. Login with your Google account.
+3. [Create](https://aistudio.google.com/app/apikey) an API key. Note that in Europe the free tier is not available.
+4. Check out this repository.\
 `git clone https://github.com/google/generative-ai-android`
+5. Open and build the sample app in the `generativeai-android-sample` folder of this repo.
+6. Paste your API key into the `apiKey` property in the `local.properties` file.
+7. Run the app
+5. For detailed instructions, try the
+[Android SDK tutorial](https://ai.google.dev/tutorials/android_quickstart) on [ai.google.dev](https://ai.google.dev).
+
+## Usage example
 
-1.  [Obtain an API key](https://makersuite.google.com/app/apikey) to use with the Google AI SDKs.
+1. Add the dependency `implementation("com.google.ai.client.generativeai:generativeai:<version>"`) to your Android project.
 
-1.  Open and build the sample app in the `generativeai-android-sample` folder of this repo. 
+2. Initialize the model
 
-1.  Paste your API key into the `apiKey` property in the `local.properties` file.
+```kotlin
+val generativeModel = GenerativeModel(
+    modelName = "gemini-1.5-pro-latest",
+    apiKey = BuildConfig.apiKey
+)
+```
 
-1.  Run the app.
+3. Run a prompt.
 
-## Installation and usage
+```kotlin
+val cookieImage: Bitmap = // ...
+val inputContent = content() {
+  image(cookieImage)
+  text("Does this look store-bought or homemade?")
+}
 
-Add the dependency `implementation("com.google.ai.client.generativeai:generativeai:<version>"`) to your Android project.
+val response = generativeModel.generateContent(inputContent)
+print(response.text)
+```
 
 For detailed instructions, you can find a [quickstart](https://ai.google.dev/tutorials/android_quickstart) for the Google AI client SDK for Android in the Google documentation.
 
 This quickstart describes how to add your API key and the SDK's dependency to your app, initialize the model, and then call the API to access the model. It also describes some additional use cases and features, like streaming, counting tokens, and controlling responses.
+
 ## Documentation
 
-Find complete documentation for the Google AI SDKs and the Gemini model in the Google documentation:\
-https://ai.google.dev/docs
+See the [Gemini API Cookbook](https://github.com/google-gemini/gemini-api-cookbook/) or [ai.google.dev](https://ai.google.dev) for complete documentation.
+
 ## Contributing
 
 See [Contributing](https://github.com/google/generative-ai-android/blob/main/CONTRIBUTING.md) for more information on contributing to the Google AI client SDK for Android.