Add multi-image prompt snippets

google-gemini · Jul 11, 2024 · 2cfa965 · 2cfa965
1 parent 07f9cf5
commit 2cfa965
Showing 1 changed file with 127 additions and 57 deletions.
diff --git a/samples/TextGeneration.swift b/samples/TextGeneration.swift
@@ -21,76 +21,146 @@ import XCTest
 // section in the Gemini API quickstart:
 // https://ai.google.dev/gemini-api/docs/quickstart?lang=swift#set-up-api-key
 
-@available(iOS 15.0, macOS 11.0, macCatalyst 15.0, *)
-final class TextGeneration: XCTestCase {
-  override func setUpWithError() throws {
-    try XCTSkipIf(APIKey.default.isEmpty, "`\(APIKey.apiKeyEnvVar)` environment variable not set.")
-  }
-
-  func testTextOnlyPrompt() async throws {
-    // [START text_gen_text_only_prompt]
-    let generativeModel =
-      GenerativeModel(
-        // Specify a Gemini model appropriate for your use case
-        name: "gemini-1.5-flash",
-        // Access your API key from your on-demand resource .plist file (see "Set up your API key"
-        // above)
-        apiKey: APIKey.default
+#if canImport(UIKit)
+  @available(iOS 15.0, macCatalyst 15.0, *)
+  final class TextGeneration: XCTestCase {
+    override func setUpWithError() throws {
+      try XCTSkipIf(
+        APIKey.default.isEmpty,
+        "`\(APIKey.apiKeyEnvVar)` environment variable not set."
       )
+    }
 
-    let prompt = "Write a story about a magic backpack."
-    let response = try await generativeModel.generateContent(prompt)
-    if let text = response.text {
-      print(text)
+    func testTextOnlyPrompt() async throws {
+      // [START text_gen_text_only_prompt]
+      let generativeModel =
+        GenerativeModel(
+          // Specify a Gemini model appropriate for your use case
+          name: "gemini-1.5-flash",
+          // Access your API key from your on-demand resource .plist file (see "Set up your API key"
+          // above)
+          apiKey: APIKey.default
+        )
+
+      let prompt = "Write a story about a magic backpack."
+      let response = try await generativeModel.generateContent(prompt)
+      if let text = response.text {
+        print(text)
+      }
+      // [END text_gen_text_only_prompt]
     }
-    // [END text_gen_text_only_prompt]
-  }
 
-  func testTextOnlyPromptStreaming() async throws {
-    // [START text_gen_text_only_prompt_streaming]
-    let generativeModel =
-      GenerativeModel(
-        // Specify a Gemini model appropriate for your use case
-        name: "gemini-1.5-flash",
-        // Access your API key from your on-demand resource .plist file (see "Set up your API key"
-        // above)
-        apiKey: APIKey.default
-      )
+    func testTextOnlyPromptStreaming() async throws {
+      // [START text_gen_text_only_prompt_streaming]
+      let generativeModel =
+        GenerativeModel(
+          // Specify a Gemini model appropriate for your use case
+          name: "gemini-1.5-flash",
+          // Access your API key from your on-demand resource .plist file (see "Set up your API key"
+          // above)
+          apiKey: APIKey.default
+        )
 
-    let prompt = "Write a story about a magic backpack."
-    // Use streaming with text-only input
-    for try await response in generativeModel.generateContentStream(prompt) {
+      let prompt = "Write a story about a magic backpack."
+      // Use streaming with text-only input
+      for try await response in generativeModel.generateContentStream(prompt) {
+        if let text = response.text {
+          print(text)
+        }
+      }
+      // [END text_gen_text_only_prompt_streaming]
+    }
+
+    func testMultimodalOneImagePrompt() async throws {
+      // [START text_gen_multimodal_one_image_prompt]
+      let generativeModel =
+        GenerativeModel(
+          // Specify a Gemini model appropriate for your use case
+          name: "gemini-1.5-flash",
+          // Access your API key from your on-demand resource .plist file (see "Set up your API key"
+          // above)
+          apiKey: APIKey.default
+        )
+
+      guard let image = UIImage(systemName: "cloud.sun") else { fatalError() }
+
+      let prompt = "What's in this picture?"
+
+      let response = try await generativeModel.generateContent(image, prompt)
       if let text = response.text {
         print(text)
       }
+      // [END text_gen_multimodal_one_image_prompt]
     }
-    // [END text_gen_text_only_prompt_streaming]
-  }
 
-  func testMultimodalOneImagePrompt() async throws {
-    // [START text_gen_multimodal_one_image_prompt]
-    let generativeModel =
-      GenerativeModel(
-        // Specify a Gemini model appropriate for your use case
-        name: "gemini-1.5-flash",
-        // Access your API key from your on-demand resource .plist file (see "Set up your API key"
-        // above)
-        apiKey: APIKey.default
-      )
+    func testMultimodalOneImagePromptStreaming() async throws {
+      // [START text_gen_multimodal_one_image_prompt_streaming]
+      let generativeModel =
+        GenerativeModel(
+          // Specify a Gemini model appropriate for your use case
+          name: "gemini-1.5-flash",
+          // Access your API key from your on-demand resource .plist file (see "Set up your API key"
+          // above)
+          apiKey: APIKey.default
+        )
 
-    #if canImport(UIKit)
       guard let image = UIImage(systemName: "cloud.sun") else { fatalError() }
-    #elseif canImport(AppKit)
-      guard let image = NSImage(systemSymbolName: "cloud.sun", accessibilityDescription: nil)
-      else { fatalError() }
-    #endif
 
-    let prompt = "What's in this picture?"
+      let prompt = "What's in this picture?"
+
+      for try await response in generativeModel.generateContentStream(image, prompt) {
+        if let text = response.text {
+          print(text)
+        }
+      }
+      // [END text_gen_multimodal_one_image_prompt_streaming]
+    }
+
+    func testMultimodalMultiImagePrompt() async throws {
+      // [START text_gen_multimodal_multi_image_prompt]
+      let generativeModel =
+        GenerativeModel(
+          // Specify a Gemini model appropriate for your use case
+          name: "gemini-1.5-flash",
+          // Access your API key from your on-demand resource .plist file (see "Set up your API key"
+          // above)
+          apiKey: APIKey.default
+        )
+
+      guard let image1 = UIImage(systemName: "cloud.sun") else { fatalError() }
+      guard let image2 = UIImage(systemName: "cloud.heavyrain") else { fatalError() }
+
+      let prompt = "What's the difference between these pictures?"
+
+      let response = try await generativeModel.generateContent(image1, image2, prompt)
+      if let text = response.text {
+        print(text)
+      }
+      // [END text_gen_multimodal_multi_image_prompt]
+    }
 
-    let response = try await generativeModel.generateContent(image, prompt)
-    if let text = response.text {
-      print(text)
+    func testMultimodalMultiImagePromptStreaming() async throws {
+      // [START text_gen_multimodal_multi_image_prompt_streaming]
+      let generativeModel =
+        GenerativeModel(
+          // Specify a Gemini model appropriate for your use case
+          name: "gemini-1.5-flash",
+          // Access your API key from your on-demand resource .plist file (see "Set up your API key"
+          // above)
+          apiKey: APIKey.default
+        )
+
+      guard let image1 = UIImage(systemName: "cloud.sun") else { fatalError() }
+      guard let image2 = UIImage(systemName: "cloud.heavyrain") else { fatalError() }
+
+      let prompt = "What's the difference between these pictures?"
+
+      for try await response in generativeModel.generateContentStream(image1, image2, prompt) {
+        if let text = response.text {
+          print(text)
+        }
+      }
+      // [END text_gen_multimodal_multi_image_prompt_streaming]
     }
-    // [END text_gen_multimodal_one_image_prompt]
   }
-}
+#endif // canImport(UIKit)