튜토리얼: Gemini API 시작하기


ai.google.dev에서 보기 Google Colab에서 실행 GitHub에서 소스 보기

Gemini API를 빠르게 사용해 보고 싶다면 curl 명령어를 사용하여 REST API에서 메서드를 호출합니다. 여기에 나오는 예시는 튜토리얼에서 각 API 메서드에 대한 호출을 보여줍니다.

Colab 는 Python 코드를 사용하여 환경 변수를 설정하고 이미지를 표시하지만, REST API를 사용하기 위해 Colab이 필요하지 않습니다. 운영 중인 모든 운영 체제를 curl 예를 보유하고 있는 경우 수정 없이 Colab 외부에서 액세스할 수 있습니다. 다음 섹션에 설명된 대로 API_KEY가 설정됩니다.

curl 명령어마다 적용 가능한 모델 이름과 API를 지정해야 합니다. 키를 누릅니다.

API 키 설정

Gemini API를 사용하려면 API 키가 필요합니다. 아직 키가 없다면 Google AI Studio에서 키를 만듭니다.

API 키 가져오기

Colab에서 'recommended' 아래의 보안 비밀 관리자에 키를 추가하세요. 왼쪽 패널에 표시됩니다. 이름을 GOOGLE_API_KEY로 지정합니다. 그런 다음 이를 환경 변수로 추가하여 curl 호출에서 키를 전달할 수 있습니다.

터미널에서 GOOGLE_API_KEY="Your API Key"를 실행하면 됩니다.

import os
from google.colab import userdata

os.environ['GOOGLE_API_KEY'] = userdata.get('GOOGLE_API_KEY')

Gemini 및 Content 기반 API

텍스트 전용 입력

generateContent 메서드 사용 모델을 사용하여 응답을 생성합니다 입력 값이 텍스트만 포함된 경우 Gemini 1.5 모델 또는 Gemini 1.0 Pro 모델을 사용합니다.

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
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "In the quaint town of Willow Creek, nestled amidst rolling hills and whispering willows, there lived an ordinary boy named Ethan. Ethan's life took an extraordinary turn the day he stumbled upon an enigmatic backpack hidden in the depths of his attic.\n\nCuriosity ignited within Ethan as he lifted the worn leather straps and unzipped its mysterious contents. Inside lay a shimmering array of vibrant objects and peculiar trinkets. There was a glowing orb that pulsated with an ethereal glow, a feather that seemed to have a life of its own, and a small, enigmatic key.\n\nAs Ethan explored each item, he realized they possessed astonishing abilities. The orb illuminated his path, casting a warm glow in the darkest of nights. The feather granted him the power of flight, allowing him to soar through the skies with newfound freedom. And the key opened a portal to a hidden world, a realm of endless wonder.\n\nArmed with his magical backpack, Ethan embarked on countless adventures. He flew over the towering mountains of Willow Creek, exploring their hidden secrets. He navigated the treacherous depths of the Enchanted Forest, where he encountered mythical creatures and ancient spirits. And he ventured into distant, unknown lands, uncovering lost civilizations and forgotten treasures.\n\nWith each adventure, Ethan's knowledge and abilities grew. He learned to harness the power of his backpack wisely, using its magic to help others and protect the world from evil forces. The backpack became an extension of himself, a symbol of hope and wonder in the face of adversity.\n\nAs the years went by, Ethan's reputation as the boy with the magic backpack spread far and wide. People from all walks of life came to him, seeking his guidance and protection. And Ethan never hesitated to lend a helping hand, using his extraordinary abilities to make the world a better place.\n\nIn the end, the magic backpack became more than just a collection of objects. It was a representation of Ethan's unwavering spirit, his boundless imagination, and his unwavering belief in the power of dreams. And as long as Ethan carried it with him, the magic of Willow Creek would live on, illuminating the darkest corners of the world with hope, wonder, and the limitless possibilities that resided within the heart of a child."
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0,
      "safetyRatings": [
        {
          "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability": "NEGLIGIBLE"
        },
        {
          "category": "HARM_CATEGORY_HATE_SPEECH",
          "probability": "NEGLIGIBLE"
        },
        {
          "category": "HARM_CATEGORY_HARASSMENT",
          "probability": "NEGLIGIBLE"
        },
        {
          "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability": "NEGLIGIBLE"
        }
      ]
    }
  ],
  "promptFeedback": {
    "safetyRatings": [
      {
        "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_HATE_SPEECH",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_HARASSMENT",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
        "probability": "NEGLIGIBLE"
      }
    ]
  }
}

텍스트 및 이미지 입력

Gemini는 멀티모달 입력을 처리할 수 있는 다양한 모델을 제공합니다. (Gemini 1.5 모델)을 사용하여 두 텍스트를 모두 입력할 수 있습니다. 살펴보겠습니다 이 프롬프트의 이미지 요구사항을 참고하세요.

프롬프트 입력에 텍스트와 이미지가 모두 포함된 경우 Gemini 1.5 모델을 사용하세요.

다음 스니펫은 요청을 빌드하고 REST API로 전송하는 데 도움이 됩니다.

curl -o image.jpg https://storage.googleapis.com/generativeai-downloads/images/scones.jpg
% Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100  385k  100  385k    0     0  2053k      0 --:--:-- --:--:-- --:--:-- 2050k
import PIL.Image

img = PIL.Image.open("image.jpg")
img.resize((512, int(img.height*512/img.width)))

png

echo '{
  "contents":[
    {
      "parts":[
        {"text": "What is this picture?"},
        {
          "inline_data": {
            "mime_type":"image/jpeg",
            "data": "'$(base64 -w0 image.jpg)'"
          }
        }
      ]
    }
  ]
}' > request.json
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=${GOOGLE_API_KEY} \
        -H 'Content-Type: application/json' \
        -d @request.json 2> /dev/null | grep "text"
"text": " The picture shows a table with a white tablecloth. On the table are two cups of coffee, a bowl of blueberries, and a plate of scones. There are also some flowers on the table."

멀티턴 대화 (채팅)

Gemini를 사용하면 여러 차례에 걸쳐 자유 형식의 대화를 구축할 수 있습니다.

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": "Write the first line of a story about a magic backpack."}]},
        {"role": "model",
         "parts":[{
           "text": "In the bustling city of Meadow brook, lived a young girl named Sophie. She was a bright and curious soul with an imaginative mind."}]},
        {"role": "user",
         "parts":[{
           "text": "Can you set it in a quiet village in 1600s France?"}]},
      ]
    }' 2> /dev/null | grep "text"
"text": "In the quaint village of Fleur-de-Lys, nestled amidst the rolling hills of 17th century France, lived a young maiden named Antoinette. She possessed a heart brimming with curiosity and a spirit as vibrant as the wildflowers that bloomed in the meadows.\n\nOne sunny morn, as Antoinette strolled through the cobblestone streets, her gaze fell upon a peculiar sight—a weathered leather backpack resting atop a mossy stone bench. Intrigued, she cautiously approached the bag, her fingers tracing the intricate carvings etched into its surface. As her fingertips grazed the worn leather, a surge of warmth coursed through her body, and the backpack began to emit a soft, ethereal glow."

구성

모델로 보내는 모든 프롬프트에는 모델이 응답을 생성하는 방식을 제어하는 매개변수 값이 포함되어 있습니다. 모델은 서로 다른 매개변수 값에 대해 서로 다른 결과를 생성할 수 있습니다. 모델 매개변수에 대해 자세히 알아보세요.

또한 안전 설정을 사용하여 유해한 것으로 간주될 수 있는 대답을 받을 가능성을 조정할 수도 있습니다. 기본적으로 안전 설정은 모든 측정기준에서 중간 또는 높은 수준의 안전하지 않은 콘텐츠를 차단합니다. 안전 설정에 대해 자세히 알아보세요.

다음 예는 generateContent 메서드를 사용하여 지도 가장자리에 패딩을 추가할 수 있습니다.

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."}
            ]
        }],
        "safetySettings": [
            {
                "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
                "threshold": "BLOCK_ONLY_HIGH"
            }
        ],
        "generationConfig": {
            "stopSequences": [
                "Title"
            ],
            "temperature": 1.0,
            "maxOutputTokens": 800,
            "topP": 0.8,
            "topK": 10
        }
    }'  2> /dev/null | grep "text"
"text": "Once upon a time, in a small town nestled at the foot of a majestic mountain range, lived a young girl named Lily. Lily was a bright and curious child who loved to explore the world around her. One day, while playing in the forest near her home, she stumbled upon a hidden cave. Intrigued, she stepped inside, and to her amazement, she discovered a dusty old backpack lying in a corner.\n\nCuriosity piqued, Lily reached out and picked up the backpack. As soon as her fingers brushed against the worn leather, she felt a strange tingling sensation coursing through her body. Suddenly, the backpack began to glow, emitting a soft, ethereal light that filled the cave.\n\nWith wide-eyed wonder, Lily opened the backpack to find it filled with an assortment of magical objects. There was a compass that always pointed to the nearest adventure, a magnifying glass that could reveal hidden secrets, a telescope that allowed her to see distant lands, and a book that contained the knowledge of the universe.\n\nOverjoyed with her discovery, Lily took the magic backpack home and began using its contents to explore the world in ways she had never imagined. She followed the compass to discover hidden treasures, used the magnifying glass to uncover the secrets of nature, gazed through the telescope to witness the wonders of the cosmos, and delved into the book to learn about the mysteries of the universe.\n\nAs Lily's adventures continued, she realized that the magic backpack was more than just a collection of enchanted items. It was a symbol of her own limitless potential and the power of her imagination. It taught her that with curiosity, courage, and a touch of magic, anything was possible.\n\nNews of Lily's magical backpack spread throughout the town, and soon, children from all around came to her, eager to learn about its wonders. Lily welcomed them with open arms, sharing her stories and inspiring them to embark on their own adventures.\n\nAnd so, the magic backpack became a beacon of hope and wonder, reminding everyone that the world is full of hidden treasures waiting to be discovered, if only one has the courage to step into the unknown."

스트림 생성 콘텐츠

generateContent 메서드는 전체 생성 프로세스가 완료된 후 응답을 반환합니다. 전체 결과를 기다리지 않고 대신 streamGenerateContent를 사용하여 부분 결과를 반환하면 상호작용을 더 빠르게 할 수 있습니다.

!curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent?alt=sse&key=${GOOGLE_API_KEY}" \
        -H 'Content-Type: application/json' \
        --no-buffer \
        -d '{ "contents":[{"parts":[{"text": "Write long a story about a magic backpack."}]}]}' \
        2> /dev/null
data: {"candidates": [{"content": {"parts": [{"text": "In the quaint little town of Willow Creek, nestled among rolling hills and whispering willows"}],"role": "model"},"finishReason": "STOP","index": 0,"safetyRatings": [{"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HATE_SPEECH","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HARASSMENT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_DANGEROUS_CONTENT","probability": "NEGLIGIBLE"}]}],"promptFeedback": {"safetyRatings": [{"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HATE_SPEECH","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HARASSMENT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_DANGEROUS_CONTENT","probability": "NEGLIGIBLE"}]} }

data: {"candidates": [{"content": {"parts": [{"text": ", there existed an extraordinary backpack that possessed an astonishing secret. Its unassuming canvas exterior and worn leather straps held a hidden realm brimming with wonder and endless possibilities."}],"role": "model"},"finishReason": "STOP","index": 0,"safetyRatings": [{"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HATE_SPEECH","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HARASSMENT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_DANGEROUS_CONTENT","probability": "NEGLIGIBLE"}]}]}

data: {"candidates": [{"content": {"parts": [{"text": "\n\nYoung Oliver, a curious and imaginative boy, stumbled upon this magical backpack in the dusty attic of his grandmother's house. Intrigued by its enigmatic aura, he unzipped it cautiously, revealing a seemingly ordinary interior. But as his fingers brushed against the lining, an ethereal glow emanated from within.\n\n"}],"role": "model"},"finishReason": "STOP","index": 0,"safetyRatings": [{"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HATE_SPEECH","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HARASSMENT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_DANGEROUS_CONTENT","probability": "NEGLIGIBLE"}]}]}

data: {"candidates": [{"content": {"parts": [{"text": "With a gasp of surprise, Oliver watched as the backpack transformed before his very eyes. Its fabric shimmered and flowed like liquid silver, morphing into a portal that connected him to a hidden dimension. Step by step, he ventured into this enchanted realm, his heart pounding with a mixture of trepidation and exhilaration.\n\nThe backpack's interior was a vast and wondrous labyrinth filled with towering bookshelves, bubbling potions, and ethereal artifacts. Each turn offered a new discovery: a self-playing piano, a talking mirror that whispered ancient wisdom, and a compass that pointed to the furthest reaches of the imagination.\n\nOliver soon realized"}],"role": "model"},"finishReason": "STOP","index": 0,"safetyRatings": [{"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HATE_SPEECH","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HARASSMENT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_DANGEROUS_CONTENT","probability": "NEGLIGIBLE"}]}]}

data: {"candidates": [{"content": {"parts": [{"text": " that this backpack was no mere container but a sentient being, capable of aiding him in his quests and expanding his horizons. It granted him the gift of tongues, allowing him to speak with animals and creatures from distant lands. It gifted him a quill that wrote stories that danced off the page, bringing his wildest dreams to life.\n\nTogether, Oliver and the backpack embarked on extraordinary adventures. They soared through the skies on the back of a majestic griffon, traversed treacherous terrains with the aid of a shape-shifting fox, and solved mysteries that had long baffled the wisest minds in Willow Creek.\n\nAs the days turned into weeks, Oliver's imagination flourished beyond measure. He painted vibrant landscapes with words, composed symphonies that echoed through the hidden realm, and invented gadgets that defied the laws of physics. The backpack became an extension of his boundless creativity, nurturing his wonder and fueling his aspirations.\n\nNews of Oliver's extraordinary backpack spread throughout the town and beyond. People flocked from far and wide to witness its marvels. Scholars sought its wisdom, artists sought its inspiration, and children dreamed of experiencing its boundless adventures.\n\nHowever, not all who approached the backpack with pure intentions. One fateful day, a greedy sorcerer named Maldred attempted to seize its power for himself. But"}],"role": "model"},"finishReason": "STOP","index": 0,"safetyRatings": [{"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HATE_SPEECH","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HARASSMENT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_DANGEROUS_CONTENT","probability": "NEGLIGIBLE"}]}]}

data: {"candidates": [{"content": {"parts": [{"text": " the backpack, sensing his malevolent nature, resisted his grasp and summoned a legion of fantastical creatures to its defense.\n\nIn a fierce battle that shook the very fabric of the hidden realm, Oliver and the backpack allied with brave heroes and wise wizards to defeat Maldred and his wicked forces. The town of Willow Creek was forever grateful, and the backpack became a symbol of hope and imagination for all who knew of its existence.\n\nAs the years passed, Oliver grew into a wise and compassionate leader, using the magic backpack to spread joy, inspire creativity, and unlock the potential of those around him. The hidden realm within its depths became a sanctuary for dreamers, inventors, and anyone who dared to embrace the wonders of the unknown.\n\nAnd so, the tale of the magic backpack was passed down through generations, a timeless testament to the power of imagination and the boundless possibilities that lie when wonder and curiosity ignite the human spirit."}],"role": "model"},"finishReason": "STOP","index": 0,"safetyRatings": [{"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HATE_SPEECH","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_HARASSMENT","probability": "NEGLIGIBLE"},{"category": "HARM_CATEGORY_DANGEROUS_CONTENT","probability": "NEGLIGIBLE"}]}]}

토큰 수 계산

긴 프롬프트를 사용할 때는 모델에 콘텐츠를 전송하기 전에 토큰을 계산하는 것이 유용할 수 있습니다.

curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:countTokens?key=$GOOGLE_API_KEY \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[{
          "text": "Write a story about a magic backpack."}]}]}' > response.json
% Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed

  0     0    0     0    0     0      0      0 --:--:-- --:--:-- --:--:--     0
100   127    0    23  100   104    105    477 --:--:-- --:--:-- --:--:--   585
cat response.json
{
  "totalTokens": 8
}

임베딩

임베딩은 배열에서 정보를 부동 소수점 숫자 목록으로 표현하는 데 사용되는 기법입니다. Gemini를 사용하면 텍스트 (단어, 문장, 텍스트 블록)를 벡터화된 형식으로 표현할 수 있어 임베딩을 더 쉽게 비교하고 대조할 수 있습니다. 예를 들어 주제나 감정이 비슷한 두 텍스트에는 비슷한 임베딩이 있어야 하며, 이는 코사인 유사성과 같은 수학적 비교 기법을 통해 식별할 수 있습니다.

embedding-001 모델을 embedContents 또는 batchEmbedContents와 함께 사용합니다.

curl https://generativelanguage.googleapis.com/v1beta/models/embedding-001:embedContent?key=$GOOGLE_API_KEY \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
        "model": "models/embedding-001",
        "content": {
        "parts":[{
          "text": "Write a story about a magic backpack."}]} }' 2> /dev/null | head
{
  "embedding": {
    "values": [
      0.008624583,
      -0.030451821,
      -0.042496547,
      -0.029230341,
      0.05486475,
      0.006694871,
      0.004025645,
curl https://generativelanguage.googleapis.com/v1beta/models/embedding-001:batchEmbedContents?key=$GOOGLE_API_KEY \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "requests": [{
        "model": "models/embedding-001",
        "content": {
        "parts":[{
          "text": "Write a story about a magic backpack."}]} }]}' 2> /dev/null | head
{
  "embeddings": [
    {
      "values": [
        0.008624583,
        -0.030451821,
        -0.042496547,
        -0.029230341,
        0.05486475,
        0.006694871,

모델 정보

모델 가져오기

모델의 URL에 GET를 지정하면 API가 get 메서드를 사용하여 버전, 표시 이름, 입력 토큰 한도 등 모델에 대한 정보를 반환합니다.

curl https://generativelanguage.googleapis.com/v1beta/models/gemini-pro?key=$GOOGLE_API_KEY
{
  "name": "models/gemini-pro",
  "version": "001",
  "displayName": "Gemini Pro",
  "description": "The best model for scaling across a wide range of tasks",
  "inputTokenLimit": 30720,
  "outputTokenLimit": 2048,
  "supportedGenerationMethods": [
    "generateContent",
    "countTokens"
  ],
  "temperature": 0.9,
  "topP": 1,
  "topK": 1
}

모델 나열

models 디렉터리를 GET하면 이는 list 메서드를 사용하여 Gemini 및 PaLM 제품군 모델을 비롯해 API를 통해 사용 가능한 모든 모델을 나열합니다.

curl https://generativelanguage.googleapis.com/v1beta/models?key=$GOOGLE_API_KEY
{
  "models": [
    {
      "name": "models/chat-bison-001",
      "version": "001",
      "displayName": "Chat Bison",
      "description": "Chat-optimized generative language model.",
      "inputTokenLimit": 4096,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateMessage",
        "countMessageTokens"
      ],
      "temperature": 0.25,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/text-bison-001",
      "version": "001",
      "displayName": "Text Bison",
      "description": "Model targeted for text generation.",
      "inputTokenLimit": 8196,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateText",
        "countTextTokens",
        "createTunedTextModel"
      ],
      "temperature": 0.7,
      "topP": 0.95,
      "topK": 40
    },
    {
      "name": "models/embedding-gecko-001",
      "version": "001",
      "displayName": "Embedding Gecko",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 1024,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedText",
        "countTextTokens"
      ]
    },
    {
      "name": "models/embedding-gecko-002",
      "version": "002",
      "displayName": "Embedding Gecko 002",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 2048,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedText",
        "countTextTokens"
      ]
    },
    {
      "name": "models/gemini-pro",
      "version": "001",
      "displayName": "Gemini Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 1
    },
    {
      "name": "models/gemini-pro",
      "version": "001",
      "displayName": "Gemini 1.0 Pro",
      "description": "The best model for scaling across a wide range of tasks",
      "inputTokenLimit": 12288,
      "outputTokenLimit": 4096,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.4,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/gemini-ultra",
      "version": "001",
      "displayName": "Gemini Ultra",
      "description": "The most capable model for highly complex tasks",
      "inputTokenLimit": 30720,
      "outputTokenLimit": 2048,
      "supportedGenerationMethods": [
        "generateContent",
        "countTokens"
      ],
      "temperature": 0.9,
      "topP": 1,
      "topK": 32
    },
    {
      "name": "models/embedding-001",
      "version": "001",
      "displayName": "Embedding 001",
      "description": "Obtain a distributed representation of a text.",
      "inputTokenLimit": 2048,
      "outputTokenLimit": 1,
      "supportedGenerationMethods": [
        "embedContent",
        "countTextTokens"
      ]
    },
    {
      "name": "models/aqa",
      "version": "001",
      "displayName": "Model that performs Attributed Question Answering.",
      "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
      "inputTokenLimit": 7168,
      "outputTokenLimit": 1024,
      "supportedGenerationMethods": [
        "generateAnswer"
      ],
      "temperature": 0.2,
      "topP": 1,
      "topK": 40
    }
  ]
}