آموزش: با Gemini API شروع کنید


مشاهده در ai.google.dev در Google Colab اجرا شود مشاهده منبع در GitHub

اگر می‌خواهید به سرعت Gemini API را امتحان کنید، می‌توانید از دستورات curl برای فراخوانی متدها در REST API استفاده کنید. مثال‌های موجود در این آموزش، فراخوانی‌های هر روش API را نشان می‌دهند.

Colab از کد پایتون برای تنظیم یک متغیر محیطی و نمایش تصویر استفاده می کند، اما برای کار با REST API نیازی به Colab ندارید. تا زمانی که API_KEY همانطور که در بخش بعدی توضیح داده شده تنظیم کرده باشید، باید بتوانید تمام نمونه های curl را در خارج از Colab، بدون تغییر اجرا کنید.

برای هر دستور curl ، باید نام مدل قابل اجرا و کلید API خود را مشخص کنید.

کلید API خود را تنظیم کنید

برای استفاده از Gemini API، به یک کلید API نیاز دارید. اگر قبلاً یکی ندارید، یک کلید در Google AI Studio ایجاد کنید.

یک کلید API دریافت کنید

در Colab، کلید را به مدیر مخفی زیر "🔑" در پانل سمت چپ اضافه کنید. نام GOOGLE_API_KEY را به آن بدهید. سپس می‌توانید آن را به‌عنوان یک متغیر محیطی برای ارسال کلید در فراخوانی خود اضافه کنید.

در ترمینال، فقط می‌توانید GOOGLE_API_KEY="Your API Key" را اجرا کنید.

import os
from google.colab import userdata

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

Gemini و APIهای مبتنی بر Content

ورودی فقط متن

از متد generateContent برای ایجاد پاسخ از مدل داده شده با پیام ورودی استفاده کنید. اگر ورودی فقط حاوی متن است، از مدل Gemini 1.5 یا مدل Gemini 1.0 Pro استفاده کنید.

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"
      }
    ]
  }
}

ورودی متن و تصویر

Gemini مدل‌های مختلفی را ارائه می‌کند که می‌توانند ورودی چندوجهی را مدیریت کنند (مدل‌های Gemini 1.5) تا بتوانید متن و عکس را وارد کنید. حتماً شرایط مورد نیاز تصویر را برای درخواست‌ها مرور کنید.

هنگامی که ورودی سریع شامل متن و تصویر است، از مدل Gemini 1.5 استفاده کنید.

قطعه‌های زیر به شما کمک می‌کنند تا یک درخواست بسازید و آن را به REST API ارسال کنید.

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."

مکالمات چند نوبتی (چت)

با استفاده از Gemini، می توانید مکالمات آزاد را در چندین نوبت ایجاد کنید.

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."

پیکربندی

هر اعلانی که به مدل ارسال می کنید شامل مقادیر پارامتری است که نحوه تولید پاسخ مدل را کنترل می کند. مدل می تواند نتایج متفاوتی را برای مقادیر پارامترهای مختلف ایجاد کند. درباره پارامترهای مدل بیشتر بدانید.

همچنین، می‌توانید از تنظیمات ایمنی برای تنظیم احتمال دریافت پاسخ‌هایی که ممکن است مضر تلقی شوند، استفاده کنید. به‌طور پیش‌فرض، تنظیمات ایمنی محتوایی را با احتمال متوسط ​​و/یا زیاد ناامن بودن محتوا در همه ابعاد مسدود می‌کند. درباره تنظیمات ایمنی بیشتر بیاموزید.

مثال زیر مقادیری را برای تمام پارامترهای متد generateContent مشخص می کند.

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."

جریان تولید محتوا

متد generateContent پس از تکمیل کل فرآیند تولید، پاسخی را برمی‌گرداند. می توانید با منتظر ماندن برای کل نتیجه به تعاملات سریع تری برسید و در عوض از streamGenerateContent برای برگرداندن نتایج جزئی استفاده کنید.

!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"}]}]}

توکن ها را بشمار

هنگام استفاده از اعلان های طولانی، ممکن است شمارش نشانه ها قبل از ارسال هر محتوایی به مدل مفید باشد.

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
}

جاسازی

جاسازی تکنیکی است که برای نمایش اطلاعات به عنوان لیستی از اعداد ممیز شناور در یک آرایه استفاده می شود. با Gemini، می‌توانید متن (کلمات، جملات و بلوک‌های متن) را به شکل برداری نمایش دهید، که مقایسه و تضاد جاسازی‌ها را آسان‌تر می‌کند. برای مثال، دو متنی که موضوع یا احساسات مشابهی دارند باید دارای تعبیه‌های مشابهی باشند که از طریق تکنیک‌های مقایسه ریاضی مانند شباهت کسینوس قابل شناسایی است.

از مدل embedding-001 با embedContents یا batchEmbedContents استفاده کنید:

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,

اطلاعات مدل

مدل بگیرید

اگر URL یک مدل GET ، API از روش get برای بازگشت اطلاعات در مورد آن مدل مانند نسخه ، نام نمایش ، محدودیت توکن ورودی و غیره استفاده می کند.

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
}

مدل های لیست

اگر دایرکتوری models GET ، از روش list برای لیست کلیه مدل های موجود از طریق API ، از جمله مدل های Gemini و Palm Family استفاده می کند.

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
    }
  ]
}