คู่มือสำหรับนักพัฒนาซอฟต์แวร์ Gemini 3

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-pro-preview",
    input="Find the race condition in this multi-threaded C++ snippet: [code here]",
)

print(interaction.output_text)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

async function run() {
  const interaction = await client.interactions.create({
    model: "gemini-3.1-pro-preview",
    input: "Find the race condition in this multi-threaded C++ snippet: [code here]",
  });

  console.log(interaction.output_text);
}

run();

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.1-pro-preview",
    "input": "Find the race condition in this multi-threaded C++ snippet: [code here]"
  }'

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-pro-preview",
    input="How does AI work?",
    generation_config={"thinking_level": "low"},
)

print(interaction.output_text)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: "gemini-3.1-pro-preview",
    input: "How does AI work?",
    generation_config: {
      thinking_level: "low",
    },
  });

console.log(interaction.output_text);

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.1-pro-preview",
    "input": "How does AI work?",
    "generation_config": {
      "thinking_level": "low"
    }
  }'

from google import genai
from pydantic import BaseModel, Field
from typing import List

class MatchResult(BaseModel):
    winner: str = Field(description="The name of the winner.")
    final_match_score: str = Field(description="The final match score.")
    scorers: List[str] = Field(description="The name of the scorer.")

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-pro-preview",
    input="Search for all details for the latest Euro.",
    tools=[
        {"type": "google_search"},
        {"type": "url_context"}
    ],
    response_format={
        "type": "text",
        "mime_type": "application/json",
        "schema": MatchResult.model_json_schema()
    },
)

result = MatchResult.model_validate_json(interaction.output_text)
print(result)

import { GoogleGenAI } from "@google/genai";
import * as z from "zod";

const matchJsonSchema = {
  type: "object",
  properties: {
    winner: { type: "string", description: "The name of the winner." },
    final_match_score: { type: "string", description: "The final score." },
    scorers: {
      type: "array",
      items: { type: "string" },
      description: "The name of the scorer."
    }
  },
  required: ["winner", "final_match_score", "scorers"]
};

const matchSchema = z.fromJSONSchema(matchJsonSchema);

const client = new GoogleGenAI({});

async function run() {
  const interaction = await client.interactions.create({
    model: "gemini-3.1-pro-preview",
    input: "Search for all details for the latest Euro.",
    tools: [
      { type: "google_search" },
      { type: "url_context" }
    ],
    response_format: {
        type: "text",
        mime_type: "application/json",
        schema: matchJsonSchema
    },
  });

  const match = matchSchema.parse(JSON.parse(interaction.output_text));
  console.log(match);
}

run();

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.1-pro-preview",
    "input": "Search for all details for the latest Euro.",
    "tools": [
      {"type": "google_search"},
      {"type": "url_context"}
    ],
    "response_format": {
        "type": "text",
        "mime_type": "application/json",
        "schema": {
            "type": "object",
            "properties": {
                "winner": {"type": "string", "description": "The name of the winner."},
                "final_match_score": {"type": "string", "description": "The final score."},
                "scorers": {
                    "type": "array",
                    "items": {"type": "string"},
                    "description": "The name of the scorer."
                }
            },
            "required": ["winner", "final_match_score", "scorers"]
        }
    }
  }'

from google import genai
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-pro-image-preview",
    input="Generate an infographic of the current weather in Tokyo.",
    tools=[{"type": "google_search"}],
    response_format={
        "type": "image",
        "aspect_ratio": "16:9",
        "image_size": "4K"
    }
)

from PIL import Image
import io

generated_image = interaction.output_image
if generated_image:
    image_data = base64.b64decode(generated_image.data)
    image = Image.open(io.BytesIO(image_data))
    image.save('weather_tokyo.png')
    image.show()

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

const client = new GoogleGenAI({});

async function run() {
  const interaction = await client.interactions.create({
    model: "gemini-3-pro-image-preview",
    input: "Generate a visualization of the current weather in Tokyo.",
    tools: [{ type: "google_search" }],
    response_format: {
      type: "image",
      aspect_ratio: "16:9",
      image_size: "4K"
    }
  });

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('weather_tokyo.png', buffer);
}

run();

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-pro-image-preview",
    "input": "Generate a visualization of the current weather in Tokyo.",
    "tools": [{"type": "google_search"}],
    "response_format": {
        "type": "image",
        "aspect_ratio": "16:9",
        "image_size": "4K"
    }
  }'

from google import genai
from google.genai import types
import requests
from PIL import Image
import io
import base64

image_path = "https://goo.gle/instrument-img"
image_bytes = requests.get(image_path).content
image = types.Part.from_bytes(data=image_bytes, mime_type="image/jpeg")

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        image,
        "Zoom into the expression pedals and tell me how many pedals are there?"
    ],
    tools=[{"type": "code_execution"}],
)

from IPython.display import display
from PIL import Image
import io

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                 display(Image.open(io.BytesIO(base64.b64decode(content_block.data))))
    elif step.type == "code_execution_call":
        print(step.code)
    elif step.type == "code_execution_result":
        print(step.output)

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

async function main() {
  const imageUrl = "https://goo.gle/instrument-img";
  const response = await fetch(imageUrl);
  const imageArrayBuffer = await response.arrayBuffer();
  const base64ImageData = Buffer.from(imageArrayBuffer).toString("base64");

  const interaction = await client.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
      {
        type: "image",
        mime_type: "image/jpeg",
        data: base64ImageData,
      },
      {
        type: "text",
        text: "Zoom into the expression pedals and tell me how many pedals are there?",
      },
    ],
    tools: [{ type: "code_execution" }],
  });

  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log("Text:", contentBlock.text);
        }
      }
    } else if (step.type === "code_execution_call") {
      console.log("Code:", step.code);
    } else if (step.type === "code_execution_result") {
      console.log("Output:", step.output);
    }
  }
}

main();

IMG_URL="https://goo.gle/instrument-img"
MODEL="gemini-3-flash-preview"

MIME_TYPE=$(curl -sIL "$IMG_URL" | grep -i '^content-type:' | awk -F ': ' '{print $2}' | sed 's/\r$//' | head -n 1)
if [[ -z "$MIME_TYPE" || ! "$MIME_TYPE" == image/* ]]; then
  MIME_TYPE="image/jpeg"
fi

if [[ "$(uname)" == "Darwin" ]]; then
  IMAGE_B64=$(curl -sL "$IMG_URL" | base64 -b 0)
elif [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  IMAGE_B64=$(curl -sL "$IMG_URL" | base64)
else
  IMAGE_B64=$(curl -sL "$IMG_URL" | base64 -w0)
fi

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
      "model": "'$MODEL'",
      "input": [
            {
              "type": "image",
              "mime_type":"'"$MIME_TYPE"'",
              "data": "'"$IMAGE_B64"'"
            },
            {"type": "text", "text": "Zoom into the expression pedals and tell me how many pedals are there?"}
      ],
      "tools": [{"type": "code_execution"}]
    }'

# This will only work for SDK newer than 2.0.0
from google import genai
import requests
import base64

client = genai.Client()

# 1. Define the tool
get_image_tool = {
    "type": "function",
    "name": "get_image",
    "description": "Retrieves the image file reference for a specific order item.",
    "parameters": {
        "type": "object",
        "properties": {
            "item_name": {
                "type": "string",
                "description": "The name or description of the item ordered (e.g., 'instrument')."
            }
        },
        "required": ["item_name"],
    },
}

# 2. Send the request with tools
interaction_1 = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Show me the instrument I ordered last month.",
    tools=[get_image_tool],
)

# 3. Find the function call step
fc_step = next(s for s in interaction_1.steps if s.type == "function_call")
print(f"Tool Call: {fc_step.name}({fc_step.arguments})")

# Execute tool (fetch image)
image_path = "https://goo.gle/instrument-img"
image_bytes = requests.get(image_path).content
image_b64 = base64.b64encode(image_bytes).decode("utf-8")

# 4. Send multimodal function result back
interaction_2 = client.interactions.create(
    model="gemini-3-flash-preview",
    previous_interaction_id=interaction_1.id,
    input=[{
        "type": "function_result",
        "name": fc_step.name,
        "call_id": fc_step.id,
        "result": [
            {"type": "text", "text": "instrument.jpg"},
            {
                "type": "image",
                "mime_type": "image/jpeg",
                "data": image_b64,
            }
        ]
    }],
    tools=[get_image_tool]
)

print(f"\nFinal model response: {interaction_2.output_text}")

import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});

const getImageTool = {
    type: 'function',
    name: 'get_image',
    description: 'Retrieves the image file reference for a specific order item.',
    parameters: {
        type: 'object',
        properties: {
            item_name: {
                type: 'string',
                description: "The name or description of the item ordered (e.g., 'instrument').",
            },
        },
        required: ['item_name'],
    },
};

const interaction1 = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: 'Use the get_image tool to show me the instrument I ordered last month.',
    tools: [getImageTool],
});

const fcStep = interaction1.steps.find(s => s.type === 'function_call');
console.log(`Tool Call: ${fcStep.name}(${JSON.stringify(fcStep.arguments)})`);

const imageUrl = 'https://goo.gle/instrument-img';
const response = await fetch(imageUrl);
const imageArrayBuffer = await response.arrayBuffer();
const base64ImageData = Buffer.from(imageArrayBuffer).toString('base64');

const interaction2 = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    previous_interaction_id: interaction1.id,
    input: [{
        type: 'function_result',
        name: fcStep.name,
        call_id: fcStep.id,
        result: [
            { type: 'text', text: 'instrument.jpg' },
            {
                type: 'image',
                mime_type: 'image/jpeg',
                data: base64ImageData,
            }
        ]
    }],
    tools: [getImageTool]
});

console.log(`\nFinal model response: ${interaction2.output_text}`);

IMG_URL="https://goo.gle/instrument-img"

MIME_TYPE=$(curl -sIL "$IMG_URL" | grep -i '^content-type:' | awk -F ': ' '{print $2}' | sed 's/\r$//' | head -n 1)
if [[ -z "$MIME_TYPE" || ! "$MIME_TYPE" == image/* ]]; then
  MIME_TYPE="image/jpeg"
fi

# Check for macOS
if [[ "$(uname)" == "Darwin" ]]; then
  IMAGE_B64=$(curl -sL "$IMG_URL" | base64 -b 0)
elif [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  IMAGE_B64=$(curl -sL "$IMG_URL" | base64)
else
  IMAGE_B64=$(curl -sL "$IMG_URL" | base64 -w0)
fi

# 1. First interaction (triggers function call)
# curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
#   -H "x-goog-api-key: $GEMINI_API_KEY" \
#   -H 'Content-Type: application/json' \
#   -d '{ "model": "gemini-3-flash-preview", "input": "Show me the instrument I ordered last month.", "tools": [...] }'

# 2. Send multimodal function result back (Replace INTERACTION_ID and CALL_ID)
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3-flash-preview",
    "previous_interaction_id": "INTERACTION_ID",
    "input": [{
      "type": "function_result",
      "name": "get_image",
      "call_id": "CALL_ID",
      "result": [
        { "type": "text", "text": "instrument.jpg" },
        {
          "type": "image",
          "mime_type": "'"$MIME_TYPE"'",
          "data": "'"$IMAGE_B64"'"
        }
      ]
    }]
  }'

from google import genai
from google.genai import types

client = genai.Client()

getWeather = {
    "type": "function",
    "name": "getWeather",
    "description": "Gets the weather for a requested city.",
    "parameters": {
        "type": "object",
        "properties": {
            "city": {
                "type": "string",
                "description": "The city and state, e.g. Utqiaġvik, Alaska",
            },
        },
        "required": ["city"],
    },
}

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="What is the northernmost city in the United States? What's the weather like there today?",
    tools=[
        {"type": "google_search"},
        getWeather
    ],
)

fc_step = next((s for s in interaction.steps if s.type == "function_call"), None)

if fc_step:
    result = {"response": "Very cold. 22 degrees Fahrenheit."}

    final_interaction = client.interactions.create(
        model="gemini-3-flash-preview",
        input=[
            {"type": "function_result", "name": fc_step.name, "call_id": fc_step.id, "result": result}
        ],
        tools=[
            {"type": "google_search"},
            getWeather
        ],
        previous_interaction_id=interaction.id,
    )

    print(final_interaction.output_text)

import { GoogleGenAI, Type } from '@google/genai';

const client = new GoogleGenAI({});

const getWeatherDeclaration = {
  type: 'function',
  name: 'getWeather',
  description: 'Gets the weather for a requested city.',
  parameters: {
    type: Type.OBJECT,
    properties: {
      city: {
        type: Type.STRING,
        description: 'The city and state, e.g. Utqiaġvik, Alaska',
      },
    },
    required: ['city'],
  },
};

const interaction = await client.interactions.create({
  model: 'gemini-3-flash-preview',
  input: "What is the northernmost city in the United States? What's the weather like there today?",
  tools: [
    { type: "google_search" },
    getWeatherDeclaration
  ],
});

const fcStep = interaction.steps.find(s => s.type === 'function_call');

if (fcStep) {
  const result = { response: "Very cold. 22 degrees Fahrenheit." };

  const finalInteraction = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: [
      { type: 'function_result', name: fcStep.name, call_id: fcStep.id, result: result }
    ],
    tools: [
      { type: "google_search" },
      getWeatherDeclaration
    ],
    previous_interaction_id: interaction.id,
  });

  console.log(finalInteraction.output_text);
}