Generating content

model = genai.GenerativeModel("gemini-1.5-flash")
response = model.generate_content("Write a story about a magic backpack.")
print(response.text)
text_generation.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });

const prompt = "Write a story about a magic backpack.";

const result = await model.generateContent(prompt);
console.log(result.response.text());
text_generation.js

model := client.GenerativeModel("gemini-1.5-flash")
resp, err := model.GenerateContent(ctx, genai.Text("Write a story about a magic backpack."))
if err != nil {
	log.Fatal(err)
}

printResponse(resp)
docs-snippets_test.go

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[{"text": "Write a story about a magic backpack."}]
        }]
       }' 2> /dev/null
text_generation.sh

val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey)

val prompt = "Write a story about a magic backpack."
val response = generativeModel.generateContent(prompt)
print(response.text)
text_generation.kt

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)
}
TextGeneration.swift

// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
final model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
);
final prompt = 'Write a story about a magic backpack.';

final response = await model.generateContent([Content.text(prompt)]);
print(response.text);
text_generation.dart

// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey);
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

Content content =
    new Content.Builder().addText("Write a story about a magic backpack.").build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

ListenableFuture<GenerateContentResponse> response = model.generateContent(content);
Futures.addCallback(
    response,
    new FutureCallback<GenerateContentResponse>() {
      @Override
      public void onSuccess(GenerateContentResponse result) {
        String resultText = result.getText();
        System.out.println(resultText);
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }
    },
    executor);
text_generation.java

import PIL.Image

model = genai.GenerativeModel("gemini-1.5-flash")
organ = PIL.Image.open(media / "organ.jpg")
response = model.generate_content(["Tell me about this instrument", organ])
print(response.text)
text_generation.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });

function fileToGenerativePart(path, mimeType) {
  return {
    inlineData: {
      data: Buffer.from(fs.readFileSync(path)).toString("base64"),
      mimeType,
    },
  };
}

const prompt = "Describe how this product might be manufactured.";
// Note: The only accepted mime types are some image types, image/*.
const imagePart = fileToGenerativePart(
  `${mediaPath}/jetpack.jpg`,
  "image/jpeg",
);

const result = await model.generateContent([prompt, imagePart]);
console.log(result.response.text());
text_generation.js

model := client.GenerativeModel("gemini-1.5-flash")

imgData, err := os.ReadFile(filepath.Join(testDataDir, "organ.jpg"))
if err != nil {
	log.Fatal(err)
}

resp, err := model.GenerateContent(ctx,
	genai.Text("Tell me about this instrument"),
	genai.ImageData("jpeg", imgData))
if err != nil {
	log.Fatal(err)
}

printResponse(resp)
docs-snippets_test.go

# Use a temporary file to hold the base64 encoded image data
TEMP_B64=$(mktemp)
trap 'rm -f "$TEMP_B64"' EXIT
base64 $B64FLAGS $IMG_PATH > "$TEMP_B64"

# Use a temporary file to hold the JSON payload
TEMP_JSON=$(mktemp)
trap 'rm -f "$TEMP_JSON"' EXIT

cat > "$TEMP_JSON" << EOF
{
  "contents": [{
    "parts":[
      {"text": "Tell me about this instrument"},
      {
        "inline_data": {
          "mime_type":"image/jpeg",
          "data": "$(cat "$TEMP_B64")"
        }
      }
    ]
  }]
}
EOF

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d "@$TEMP_JSON" 2> /dev/null
text_generation.sh

val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey)

val image: Bitmap = BitmapFactory.decodeResource(context.resources, R.drawable.image)
val inputContent = content {
  image(image)
  text("What's in this picture?")
}

val response = generativeModel.generateContent(inputContent)
print(response.text)
text_generation.kt

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)
}
TextGeneration.swift

// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
final model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
);

Future<DataPart> fileToPart(String mimeType, String path) async {
  return DataPart(mimeType, await File(path).readAsBytes());
}

final prompt = 'Describe how this product might be manufactured.';
final image = await fileToPart('image/jpeg', 'resources/jetpack.jpg');

final response = await model.generateContent([
  Content.multi([TextPart(prompt), image])
]);
print(response.text);
text_generation.dart

// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey);
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

Bitmap image = BitmapFactory.decodeResource(context.getResources(), R.drawable.image);

Content content =
    new Content.Builder()
        .addText("What's different between these pictures?")
        .addImage(image)
        .build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

ListenableFuture<GenerateContentResponse> response = model.generateContent(content);
Futures.addCallback(
    response,
    new FutureCallback<GenerateContentResponse>() {
      @Override
      public void onSuccess(GenerateContentResponse result) {
        String resultText = result.getText();
        System.out.println(resultText);
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }
    },
    executor);
text_generation.java

model = genai.GenerativeModel("gemini-1.5-flash")
sample_audio = genai.upload_file(media / "sample.mp3")
response = model.generate_content(["Give me a summary of this audio file.", sample_audio])
print(response.text)
text_generation.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });

function fileToGenerativePart(path, mimeType) {
  return {
    inlineData: {
      data: Buffer.from(fs.readFileSync(path)).toString("base64"),
      mimeType,
    },
  };
}

const prompt = "Give me a summary of this audio file.";
// Note: The only accepted mime types are some image types, image/*.
const audioPart = fileToGenerativePart(
  `${mediaPath}/samplesmall.mp3`,
  "audio/mp3",
);

const result = await model.generateContent([prompt, audioPart]);
console.log(result.response.text());
text_generation.js

# Use File API to upload audio data to API request.
MIME_TYPE=$(file -b --mime-type "${AUDIO_PATH}")
NUM_BYTES=$(wc -c < "${AUDIO_PATH}")
DISPLAY_NAME=AUDIO

tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D upload-header.tmp \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${AUDIO_PATH}" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Please describe this file."},
          {"file_data":{"mime_type": "audio/mpeg", "file_uri": '$file_uri'}}]
        }]
       }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json
text_generation.sh

import time

# Video clip (CC BY 3.0) from https://peach.blender.org/download/
myfile = genai.upload_file(media / "Big_Buck_Bunny.mp4")
print(f"{myfile=}")

# Videos need to be processed before you can use them.
while myfile.state.name == "PROCESSING":
    print("processing video...")
    time.sleep(5)
    myfile = genai.get_file(myfile.name)

model = genai.GenerativeModel("gemini-1.5-flash")
response = model.generate_content([myfile, "Describe this video clip"])
print(f"{response.text=}")
text_generation.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
// import { GoogleAIFileManager, FileState } from "@google/generative-ai/server";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });

const fileManager = new GoogleAIFileManager(process.env.API_KEY);

const uploadResult = await fileManager.uploadFile(
  `${mediaPath}/Big_Buck_Bunny.mp4`,
  { mimeType: "video/mp4" },
);

let file = await fileManager.getFile(uploadResult.file.name);
while (file.state === FileState.PROCESSING) {
  process.stdout.write(".");
  // Sleep for 10 seconds
  await new Promise((resolve) => setTimeout(resolve, 10_000));
  // Fetch the file from the API again
  file = await fileManager.getFile(uploadResult.file.name);
}

if (file.state === FileState.FAILED) {
  throw new Error("Video processing failed.");
}

const prompt = "Describe this video clip";
const videoPart = {
  fileData: {
    fileUri: uploadResult.file.uri,
    mimeType: uploadResult.file.mimeType,
  },
};

const result = await model.generateContent([prompt, videoPart]);
console.log(result.response.text());
text_generation.js

model := client.GenerativeModel("gemini-1.5-flash")

file, err := client.UploadFileFromPath(ctx, filepath.Join(testDataDir, "earth.mp4"), nil)
if err != nil {
	log.Fatal(err)
}
defer client.DeleteFile(ctx, file.Name)

// Videos need to be processed before you can use them.
for file.State == genai.FileStateProcessing {
	log.Printf("processing %s", file.Name)
	time.Sleep(5 * time.Second)
	var err error
	if file, err = client.GetFile(ctx, file.Name); err != nil {
		log.Fatal(err)
	}
}
if file.State != genai.FileStateActive {
	log.Fatalf("uploaded file has state %s, not active", file.State)
}

resp, err := model.GenerateContent(ctx,
	genai.Text("Describe this video clip"),
	genai.FileData{URI: file.URI})
if err != nil {
	log.Fatal(err)
}

printResponse(resp)
docs-snippets_test.go

# Use File API to upload audio data to API request.
MIME_TYPE=$(file -b --mime-type "${VIDEO_PATH}")
NUM_BYTES=$(wc -c < "${VIDEO_PATH}")
DISPLAY_NAME=VIDEO

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D "${tmp_header_file}" \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${VIDEO_PATH}" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

state=$(jq ".file.state" file_info.json)
echo state=$state

name=$(jq ".file.name" file_info.json)
echo name=$name

while [[ "($state)" = *"PROCESSING"* ]];
do
  echo "Processing video..."
  sleep 5
  # Get the file of interest to check state
  curl https://generativelanguage.googleapis.com/v1beta/files/$name > file_info.json
  state=$(jq ".file.state" file_info.json)
done

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Transcribe the audio from this video, giving timestamps for salient events in the video. Also provide visual descriptions."},
          {"file_data":{"mime_type": "video/mp4", "file_uri": '$file_uri'}}]
        }]
       }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json
text_generation.sh

model = genai.GenerativeModel("gemini-1.5-flash")
sample_pdf = genai.upload_file(media / "test.pdf")
response = model.generate_content(["Give me a summary of this document:", sample_pdf])
print(f"{response.text=}")
text_generation.py

MIME_TYPE=$(file -b --mime-type "${PDF_PATH}")
NUM_BYTES=$(wc -c < "${PDF_PATH}")
DISPLAY_NAME=TEXT


echo $MIME_TYPE
tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D upload-header.tmp \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${PDF_PATH}" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

# Now generate content using that file
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Can you add a few more lines to this poem?"},
          {"file_data":{"mime_type": "application/pdf", "file_uri": '$file_uri'}}]
        }]
       }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json
text_generation.sh

model = genai.GenerativeModel("gemini-1.5-flash")
chat = model.start_chat(
    history=[
        {"role": "user", "parts": "Hello"},
        {"role": "model", "parts": "Great to meet you. What would you like to know?"},
    ]
)
response = chat.send_message("I have 2 dogs in my house.")
print(response.text)
response = chat.send_message("How many paws are in my house?")
print(response.text)
chat.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });
const chat = model.startChat({
  history: [
    {
      role: "user",
      parts: [{ text: "Hello" }],
    },
    {
      role: "model",
      parts: [{ text: "Great to meet you. What would you like to know?" }],
    },
  ],
});
let result = await chat.sendMessage("I have 2 dogs in my house.");
console.log(result.response.text());
result = await chat.sendMessage("How many paws are in my house?");
console.log(result.response.text());
chat.js

model := client.GenerativeModel("gemini-1.5-flash")
cs := model.StartChat()

cs.History = []*genai.Content{
	{
		Parts: []genai.Part{
			genai.Text("Hello, I have 2 dogs in my house."),
		},
		Role: "user",
	},
	{
		Parts: []genai.Part{
			genai.Text("Great to meet you. What would you like to know?"),
		},
		Role: "model",
	},
}

res, err := cs.SendMessage(ctx, genai.Text("How many paws are in my house?"))
if err != nil {
	log.Fatal(err)
}
printResponse(res)
docs-snippets_test.go

curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [
        {"role":"user",
         "parts":[{
           "text": "Hello"}]},
        {"role": "model",
         "parts":[{
           "text": "Great to meet you. What would you like to know?"}]},
        {"role":"user",
         "parts":[{
           "text": "I have two dogs in my house. How many paws are in my house?"}]},
      ]
    }' 2> /dev/null | grep "text"
chat.sh

val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey)

val chat =
    generativeModel.startChat(
        history =
            listOf(
                content(role = "user") { text("Hello, I have 2 dogs in my house.") },
                content(role = "model") {
                  text("Great to meet you. What would you like to know?")
                }))

val response = chat.sendMessage("How many paws are in my house?")
print(response.text)
chat.kt

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
  )

// Optionally specify existing chat history
let history = [
  ModelContent(role: "user", parts: "Hello, I have 2 dogs in my house."),
  ModelContent(role: "model", parts: "Great to meet you. What would you like to know?"),
]

// Initialize the chat with optional chat history
let chat = generativeModel.startChat(history: history)

// To generate text output, call sendMessage and pass in the message
let response = try await chat.sendMessage("How many paws are in my house?")
if let text = response.text {
  print(text)
}
ChatSnippets.swift

// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
final model = GenerativeModel(
  model: 'gemini-1.5-flash',
  apiKey: apiKey,
);
final chat = model.startChat(history: [
  Content.text('hello'),
  Content.model([TextPart('Great to meet you. What would you like to know?')])
]);
var response =
    await chat.sendMessage(Content.text('I have 2 dogs in my house.'));
print(response.text);
response =
    await chat.sendMessage(Content.text('How many paws are in my house?'));
print(response.text);
chat.dart

// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey);
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

// (optional) Create previous chat history for context
Content.Builder userContentBuilder = new Content.Builder();
userContentBuilder.setRole("user");
userContentBuilder.addText("Hello, I have 2 dogs in my house.");
Content userContent = userContentBuilder.build();

Content.Builder modelContentBuilder = new Content.Builder();
modelContentBuilder.setRole("model");
modelContentBuilder.addText("Great to meet you. What would you like to know?");
Content modelContent = userContentBuilder.build();

List<Content> history = Arrays.asList(userContent, modelContent);

// Initialize the chat
ChatFutures chat = model.startChat(history);

// Create a new user message
Content.Builder userMessageBuilder = new Content.Builder();
userMessageBuilder.setRole("user");
userMessageBuilder.addText("How many paws are in my house?");
Content userMessage = userMessageBuilder.build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

// Send the message
ListenableFuture<GenerateContentResponse> response = chat.sendMessage(userMessage);

Futures.addCallback(
    response,
    new FutureCallback<GenerateContentResponse>() {
      @Override
      public void onSuccess(GenerateContentResponse result) {
        String resultText = result.getText();
        System.out.println(resultText);
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }
    },
    executor);
chat.java

document = genai.upload_file(path=media / "a11.txt")
model_name = "gemini-1.5-flash-001"
cache = genai.caching.CachedContent.create(
    model=model_name,
    system_instruction="You are an expert analyzing transcripts.",
    contents=[document],
)
print(cache)

model = genai.GenerativeModel.from_cached_content(cache)
response = model.generate_content("Please summarize this transcript")
print(response.text)
cache.py

// Make sure to include these imports:
// import { GoogleAICacheManager, GoogleAIFileManager } from "@google/generative-ai/server";
// import { GoogleGenerativeAI } from "@google/generative-ai";
const cacheManager = new GoogleAICacheManager(process.env.API_KEY);
const fileManager = new GoogleAIFileManager(process.env.API_KEY);

const uploadResult = await fileManager.uploadFile(`${mediaPath}/a11.txt`, {
  mimeType: "text/plain",
});

const cacheResult = await cacheManager.create({
  model: "models/gemini-1.5-flash-001",
  contents: [
    {
      role: "user",
      parts: [
        {
          fileData: {
            fileUri: uploadResult.file.uri,
            mimeType: uploadResult.file.mimeType,
          },
        },
      ],
    },
  ],
});

console.log(cacheResult);

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModelFromCachedContent(cacheResult);
const result = await model.generateContent(
  "Please summarize this transcript.",
);
console.log(result.response.text());
cache.js

model = genai.GenerativeModel(model_name="tunedModels/my-increment-model")
result = model.generate_content("III")
print(result.text)  # "IV"
tuned_models.py

import typing_extensions as typing

class Recipe(typing.TypedDict):
    recipe_name: str
    ingredients: list[str]

model = genai.GenerativeModel("gemini-1.5-pro-latest")
result = model.generate_content(
    "List a few popular cookie recipes.",
    generation_config=genai.GenerationConfig(
        response_mime_type="application/json", response_schema=list[Recipe]
    ),
)
print(result)
controlled_generation.py

// Make sure to include these imports:
// import { GoogleGenerativeAI, SchemaType } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.API_KEY);

const schema = {
  description: "List of recipes",
  type: SchemaType.ARRAY,
  items: {
    type: SchemaType.OBJECT,
    properties: {
      recipeName: {
        type: SchemaType.STRING,
        description: "Name of the recipe",
        nullable: false,
      },
    },
    required: ["recipeName"],
  },
};

const model = genAI.getGenerativeModel({
  model: "gemini-1.5-pro",
  generationConfig: {
    responseMimeType: "application/json",
    responseSchema: schema,
  },
});

const result = await model.generateContent(
  "List a few popular cookie recipes.",
);
console.log(result.response.text());
controlled_generation.js

model := client.GenerativeModel("gemini-1.5-pro-latest")
// Ask the model to respond with JSON.
model.ResponseMIMEType = "application/json"
// Specify the schema.
model.ResponseSchema = &genai.Schema{
	Type:  genai.TypeArray,
	Items: &genai.Schema{Type: genai.TypeString},
}
resp, err := model.GenerateContent(ctx, genai.Text("List a few popular cookie recipes using this JSON schema."))
if err != nil {
	log.Fatal(err)
}
for _, part := range resp.Candidates[0].Content.Parts {
	if txt, ok := part.(genai.Text); ok {
		var recipes []string
		if err := json.Unmarshal([]byte(txt), &recipes); err != nil {
			log.Fatal(err)
		}
		fmt.Println(recipes)
	}
}
docs-snippets_test.go

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "contents": [{
      "parts":[
        {"text": "List 5 popular cookie recipes"}
        ]
    }],
    "generationConfig": {
        "response_mime_type": "application/json",
        "response_schema": {
          "type": "ARRAY",
          "items": {
            "type": "OBJECT",
            "properties": {
              "recipe_name": {"type":"STRING"},
            }
          }
        }
    }
}' 2> /dev/null | head
controlled_generation.sh

val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-pro",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey,
        generationConfig = generationConfig {
            responseMimeType = "application/json"
            responseSchema = Schema(
                name = "recipes",
                description = "List of recipes",
                type = FunctionType.ARRAY,
                items = Schema(
                    name = "recipe",
                    description = "A recipe",
                    type = FunctionType.OBJECT,
                    properties = mapOf(
                        "recipeName" to Schema(
                            name = "recipeName",
                            description = "Name of the recipe",
                            type = FunctionType.STRING,
                            nullable = false
                        ),
                    ),
                    required = listOf("recipeName")
                ),
            )
        })

val prompt = "List a few popular cookie recipes."
val response = generativeModel.generateContent(prompt)
print(response.text)
controlled_generation.kt

let jsonSchema = Schema(
  type: .array,
  description: "List of recipes",
  items: Schema(
    type: .object,
    properties: [
      "recipeName": Schema(type: .string, description: "Name of the recipe", nullable: false),
    ],
    requiredProperties: ["recipeName"]
  )
)

let generativeModel = GenerativeModel(
  // Specify a model that supports controlled generation like Gemini 1.5 Pro
  name: "gemini-1.5-pro",
  // Access your API key from your on-demand resource .plist file (see "Set up your API key"
  // above)
  apiKey: APIKey.default,
  generationConfig: GenerationConfig(
    responseMIMEType: "application/json",
    responseSchema: jsonSchema
  )
)

let prompt = "List a few popular cookie recipes."
let response = try await generativeModel.generateContent(prompt)
if let text = response.text {
  print(text)
}
ControlledGeneration.swift

// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
final schema = Schema.array(
    description: 'List of recipes',
    items: Schema.object(properties: {
      'recipeName':
          Schema.string(description: 'Name of the recipe.', nullable: false)
    }, requiredProperties: [
      'recipeName'
    ]));

final model = GenerativeModel(
    model: 'gemini-1.5-pro',
    apiKey: apiKey,
    generationConfig: GenerationConfig(
        responseMimeType: 'application/json', responseSchema: schema));

final prompt = 'List a few popular cookie recipes.';
final response = await model.generateContent([Content.text(prompt)]);
print(response.text);
controlled_generation.dart

Schema<List<String>> schema =
    new Schema(
        /* name */ "recipes",
        /* description */ "List of recipes",
        /* format */ null,
        /* nullable */ false,
        /* list */ null,
        /* properties */ null,
        /* required */ null,
        /* items */ new Schema(
            /* name */ "recipe",
            /* description */ "A recipe",
            /* format */ null,
            /* nullable */ false,
            /* list */ null,
            /* properties */ Map.of(
                "recipeName",
                new Schema(
                    /* name */ "recipeName",
                    /* description */ "Name of the recipe",
                    /* format */ null,
                    /* nullable */ false,
                    /* list */ null,
                    /* properties */ null,
                    /* required */ null,
                    /* items */ null,
                    /* type */ FunctionType.STRING)),
            /* required */ null,
            /* items */ null,
            /* type */ FunctionType.OBJECT),
        /* type */ FunctionType.ARRAY);

GenerationConfig.Builder configBuilder = new GenerationConfig.Builder();
configBuilder.responseMimeType = "application/json";
configBuilder.responseSchema = schema;

GenerationConfig generationConfig = configBuilder.build();

// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-pro",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey,
        /* generationConfig */ generationConfig);
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

Content content = new Content.Builder().addText("List a few popular cookie recipes.").build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

ListenableFuture<GenerateContentResponse> response = model.generateContent(content);
Futures.addCallback(
    response,
    new FutureCallback<GenerateContentResponse>() {
      @Override
      public void onSuccess(GenerateContentResponse result) {
        String resultText = result.getText();
        System.out.println(resultText);
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }
    },
    executor);
controlled_generation.java

model = genai.GenerativeModel(model_name="gemini-1.5-flash", tools="code_execution")
response = model.generate_content(
    (
        "What is the sum of the first 50 prime numbers? "
        "Generate and run code for the calculation, and make sure you get all 50."
    )
)

# Each `part` either contains `text`, `executable_code` or an `execution_result`
for part in response.candidates[0].content.parts:
    print(part, "\n")

print("-" * 80)
# The `.text` accessor joins the parts into a markdown compatible text representation.
print("\n\n", response.text)
code_execution.py

val model = GenerativeModel(
    // Specify a Gemini model appropriate for your use case
    modelName = "gemini-1.5-pro",
    // Access your API key as a Build Configuration variable (see "Set up your API key" above)
    apiKey = BuildConfig.apiKey,
    tools = listOf(Tool.CODE_EXECUTION)
)

val response = model.generateContent("What is the sum of the first 50 prime numbers?")

// Each `part` either contains `text`, `executable_code` or an `execution_result`
println(response.candidates[0].content.parts.joinToString("\n"))

// Alternatively, you can use the `text` accessor which joins the parts into a markdown compatible
// text representation
println(response.text)
code_execution.kt

// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
        new GenerativeModel(
                /* modelName */ "gemini-1.5-pro",
                // Access your API key as a Build Configuration variable (see "Set up your API key"
                // above)
                /* apiKey */ BuildConfig.apiKey,
                /* generationConfig */ null,
                /* safetySettings */ null,
                /* requestOptions */ new RequestOptions(),
                /* tools */ Collections.singletonList(Tool.CODE_EXECUTION));
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

Content inputContent =
        new Content.Builder().addText("What is the sum of the first 50 prime numbers?").build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

ListenableFuture<GenerateContentResponse> response = model.generateContent(inputContent);
Futures.addCallback(
        response,
        new FutureCallback<GenerateContentResponse>() {
            @Override
            public void onSuccess(GenerateContentResponse result) {
                // Each `part` either contains `text`, `executable_code` or an
                // `execution_result`
                Candidate candidate = result.getCandidates().get(0);
                for (Part part : candidate.getContent().getParts()) {
                    System.out.println(part);
                }

                // Alternatively, you can use the `text` accessor which joins the parts into a
                // markdown compatible text representation
                String resultText = result.getText();
                System.out.println(resultText);
            }

            @Override
            public void onFailure(Throwable t) {
                t.printStackTrace();
            }
        },
        executor);
code_execution.java

def add(a: float, b: float):
    """returns a + b."""
    return a + b

def subtract(a: float, b: float):
    """returns a - b."""
    return a - b

def multiply(a: float, b: float):
    """returns a * b."""
    return a * b

def divide(a: float, b: float):
    """returns a / b."""
    return a / b

model = genai.GenerativeModel(
    model_name="gemini-1.5-flash", tools=[add, subtract, multiply, divide]
)
chat = model.start_chat(enable_automatic_function_calling=True)
response = chat.send_message(
    "I have 57 cats, each owns 44 mittens, how many mittens is that in total?"
)
print(response.text)
function_calling.py

// Make sure to include these imports:
// import { GoogleGenerativeAI } from "@google/generative-ai";
async function setLightValues(brightness, colorTemperature) {
  // This mock API returns the requested lighting values
  return {
    brightness,
    colorTemperature,
  };
}

const controlLightFunctionDeclaration = {
  name: "controlLight",
  parameters: {
    type: "OBJECT",
    description: "Set the brightness and color temperature of a room light.",
    properties: {
      brightness: {
        type: "NUMBER",
        description:
          "Light level from 0 to 100. Zero is off and 100 is full brightness.",
      },
      colorTemperature: {
        type: "STRING",
        description:
          "Color temperature of the light fixture which can be `daylight`, `cool` or `warm`.",
      },
    },
    required: ["brightness", "colorTemperature"],
  },
};

// Executable function code. Put it in a map keyed by the function name
// so that you can call it once you get the name string from the model.
const functions = {
  controlLight: ({ brightness, colorTemperature }) => {
    return setLightValues(brightness, colorTemperature);
  },
};

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({
  model: "gemini-1.5-flash",
  tools: { functionDeclarations: [controlLightFunctionDeclaration] },
});
const chat = model.startChat();
const prompt = "Dim the lights so the room feels cozy and warm.";

// Send the message to the model.
const result = await chat.sendMessage(prompt);

// For simplicity, this uses the first function call found.
const call = result.response.functionCalls()[0];

if (call) {
  // Call the executable function named in the function call
  // with the arguments specified in the function call and
  // let it call the hypothetical API.
  const apiResponse = await functions[call.name](call.args);

  // Send the API response back to the model so it can generate
  // a text response that can be displayed to the user.
  const result2 = await chat.sendMessage([
    {
      functionResponse: {
        name: "controlLight",
        response: apiResponse,
      },
    },
  ]);

  // Log the text response.
  console.log(result2.response.text());
}
function_calling.js

cat > tools.json << EOF
{
  "function_declarations": [
    {
      "name": "enable_lights",
      "description": "Turn on the lighting system.",
      "parameters": { "type": "object" }
    },
    {
      "name": "set_light_color",
      "description": "Set the light color. Lights must be enabled for this to work.",
      "parameters": {
        "type": "object",
        "properties": {
          "rgb_hex": {
            "type": "string",
            "description": "The light color as a 6-digit hex string, e.g. ff0000 for red."
          }
        },
        "required": [
          "rgb_hex"
        ]
      }
    },
    {
      "name": "stop_lights",
      "description": "Turn off the lighting system.",
      "parameters": { "type": "object" }
    }
  ]
} 
EOF

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro-latest:generateContent?key=$GOOGLE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d @<(echo '
  {
    "system_instruction": {
      "parts": {
        "text": "You are a helpful lighting system bot. You can turn lights on and off, and you can set the color. Do not perform any other tasks."
      }
    },
    "tools": ['$(source "$tools")'],

    "tool_config": {
      "function_calling_config": {"mode": "none"}
    },

    "contents": {
      "role": "user",
      "parts": {
        "text": "What can you do?"
      }
    }
  }
') 2>/dev/null |sed -n '/"content"/,/"finishReason"/p'
function_calling.sh

fun multiply(a: Double, b: Double) = a * b

val multiplyDefinition = defineFunction(
    name = "multiply",
    description = "returns the product of the provided numbers.",
    parameters = listOf(
    Schema.double("a", "First number"),
    Schema.double("b", "Second number")
    )
)

val usableFunctions = listOf(multiplyDefinition)

val generativeModel =
    GenerativeModel(
        // Specify a Gemini model appropriate for your use case
        modelName = "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key" above)
        apiKey = BuildConfig.apiKey,
        // List the functions definitions you want to make available to the model
        tools = listOf(Tool(usableFunctions))
    )

val chat = generativeModel.startChat()
val prompt = "I have 57 cats, each owns 44 mittens, how many mittens is that in total?"

// Send the message to the generative model
var response = chat.sendMessage(prompt)

// Check if the model responded with a function call
response.functionCalls.first { it.name == "multiply" }.apply {
    val a: String by args
    val b: String by args

    val result = JSONObject(mapOf("result" to multiply(a.toDouble(), b.toDouble())))
    response = chat.sendMessage(
        content(role = "function") {
            part(FunctionResponsePart("multiply", result))
        }
    )
}

// Whenever the model responds with text, show it in the UI
response.text?.let { modelResponse ->
    println(modelResponse)
}
function_calling.kt

// Calls a hypothetical API to control a light bulb and returns the values that were set.
func controlLight(brightness: Double, colorTemperature: String) -> JSONObject {
  return ["brightness": .number(brightness), "colorTemperature": .string(colorTemperature)]
}

let generativeModel =
  GenerativeModel(
    // Use a model that supports function calling, like a Gemini 1.5 model
    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,
    tools: [Tool(functionDeclarations: [
      FunctionDeclaration(
        name: "controlLight",
        description: "Set the brightness and color temperature of a room light.",
        parameters: [
          "brightness": Schema(
            type: .number,
            format: "double",
            description: "Light level from 0 to 100. Zero is off and 100 is full brightness."
          ),
          "colorTemperature": Schema(
            type: .string,
            format: "enum",
            description: "Color temperature of the light fixture.",
            enumValues: ["daylight", "cool", "warm"]
          ),
        ],
        requiredParameters: ["brightness", "colorTemperature"]
      ),
    ])]
  )

let chat = generativeModel.startChat()

let prompt = "Dim the lights so the room feels cozy and warm."

// Send the message to the model.
let response1 = try await chat.sendMessage(prompt)

// Check if the model responded with a function call.
// For simplicity, this sample uses the first function call found.
guard let functionCall = response1.functionCalls.first else {
  fatalError("Model did not respond with a function call.")
}
// Print an error if the returned function was not declared
guard functionCall.name == "controlLight" else {
  fatalError("Unexpected function called: \(functionCall.name)")
}
// Verify that the names and types of the parameters match the declaration
guard case let .number(brightness) = functionCall.args["brightness"] else {
  fatalError("Missing argument: brightness")
}
guard case let .string(colorTemperature) = functionCall.args["colorTemperature"] else {
  fatalError("Missing argument: colorTemperature")
}

// Call the executable function named in the FunctionCall with the arguments specified in the
// FunctionCall and let it call the hypothetical API.
let apiResponse = controlLight(brightness: brightness, colorTemperature: colorTemperature)

// Send the API response back to the model so it can generate a text response that can be
// displayed to the user.
let response2 = try await chat.sendMessage([ModelContent(
  role: "function",
  parts: [.functionResponse(FunctionResponse(name: "controlLight", response: apiResponse))]
)])

if let text = response2.text {
  print(text)
}
FunctionCalling.swift

// Make sure to include this import:
// import 'package:google_generative_ai/google_generative_ai.dart';
Map<String, Object?> setLightValues(Map<String, Object?> args) {
  return args;
}

final controlLightFunction = FunctionDeclaration(
    'controlLight',
    'Set the brightness and color temperature of a room light.',
    Schema.object(properties: {
      'brightness': Schema.number(
          description:
              'Light level from 0 to 100. Zero is off and 100 is full brightness.',
          nullable: false),
      'colorTemperatur': Schema.string(
          description:
              'Color temperature of the light fixture which can be `daylight`, `cool`, or `warm`',
          nullable: false),
    }));

final functions = {controlLightFunction.name: setLightValues};
FunctionResponse dispatchFunctionCall(FunctionCall call) {
  final function = functions[call.name]!;
  final result = function(call.args);
  return FunctionResponse(call.name, result);
}

final model = GenerativeModel(
  model: 'gemini-1.5-pro',
  apiKey: apiKey,
  tools: [
    Tool(functionDeclarations: [controlLightFunction])
  ],
);

final prompt = 'Dim the lights so the room feels cozy and warm.';
final content = [Content.text(prompt)];
var response = await model.generateContent(content);

List<FunctionCall> functionCalls;
while ((functionCalls = response.functionCalls.toList()).isNotEmpty) {
  var responses = <FunctionResponse>[
    for (final functionCall in functionCalls)
      dispatchFunctionCall(functionCall)
  ];
  content
    ..add(response.candidates.first.content)
    ..add(Content.functionResponses(responses));
  response = await model.generateContent(content);
}
print('Response: ${response.text}');
function_calling.dart

FunctionDeclaration multiplyDefinition =
    defineFunction(
        /* name  */ "multiply",
        /* description */ "returns a * b.",
        /* parameters */ Arrays.asList(
            Schema.numDouble("a", "First parameter"),
            Schema.numDouble("b", "Second parameter")),
        /* required */ Arrays.asList("a", "b"));

Tool tool = new Tool(Arrays.asList(multiplyDefinition), null);

// Specify a Gemini model appropriate for your use case
GenerativeModel gm =
    new GenerativeModel(
        /* modelName */ "gemini-1.5-flash",
        // Access your API key as a Build Configuration variable (see "Set up your API key"
        // above)
        /* apiKey */ BuildConfig.apiKey,
        /* generationConfig (optional) */ null,
        /* safetySettings (optional) */ null,
        /* requestOptions (optional) */ new RequestOptions(),
        /* functionDeclarations (optional) */ Arrays.asList(tool));
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

// Create prompt
Content.Builder userContentBuilder = new Content.Builder();
userContentBuilder.setRole("user");
userContentBuilder.addText(
    "I have 57 cats, each owns 44 mittens, how many mittens is that in total?");
Content userMessage = userContentBuilder.build();

// For illustrative purposes only. You should use an executor that fits your needs.
Executor executor = Executors.newSingleThreadExecutor();

// Initialize the chat
ChatFutures chat = model.startChat();

// Send the message
ListenableFuture<GenerateContentResponse> response = chat.sendMessage(userMessage);

Futures.addCallback(
    response,
    new FutureCallback<GenerateContentResponse>() {
      @Override
      public void onSuccess(GenerateContentResponse result) {
        if (!result.getFunctionCalls().isEmpty()) {
          handleFunctionCall(result);
        }
        if (!result.getText().isEmpty()) {
          System.out.println(result.getText());
        }
      }

      @Override
      public void onFailure(Throwable t) {
        t.printStackTrace();
      }

      private void handleFunctionCall(GenerateContentResponse result) {
        FunctionCallPart multiplyFunctionCallPart =
            result.getFunctionCalls().stream()
                .filter(fun -> fun.getName().equals("multiply"))
                .findFirst()
                .get();
        double a = Double.parseDouble(multiplyFunctionCallPart.getArgs().get("a"));
        double b = Double.parseDouble(multiplyFunctionCallPart.getArgs().get("b"));

        try {
          // `multiply(a, b)` is a regular java function defined in another class
          FunctionResponsePart functionResponsePart =
              new FunctionResponsePart(
                  "multiply", new JSONObject().put("result", multiply(a, b)));

          // Create prompt
          Content.Builder functionCallResponse = new Content.Builder();
          userContentBuilder.setRole("user");
          userContentBuilder.addPart(functionResponsePart);
          Content userMessage = userContentBuilder.build();

          chat.sendMessage(userMessage);
        } catch (JSONException e) {
          throw new RuntimeException(e);
        }
      }
    },
    executor);
function_calling.java