การทำความเข้าใจรูปภาพ

from google import genai

client = genai.Client(api_key="GOOGLE_API_KEY")

myfile = client.files.upload(file="path/to/sample.jpg")

response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents=[myfile, "Caption this image."])

print(response.text)

import {
  GoogleGenAI,
  createUserContent,
  createPartFromUri,
} from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });

async function main() {
  const myfile = await ai.files.upload({
    file: "path/to/sample.jpg",
    config: { mimeType: "image/jpeg" },
  });

  const response = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: createUserContent([
      createPartFromUri(myfile.uri, myfile.mimeType),
      "Caption this image.",
    ]),
  });
  console.log(response.text);
}

await main();

file, err := client.UploadFileFromPath(ctx, "path/to/sample.jpg", nil)
if err != nil {
    log.Fatal(err)
}
defer client.DeleteFile(ctx, file.Name)

model := client.GenerativeModel("gemini-2.0-flash")
resp, err := model.GenerateContent(ctx,
    genai.FileData{URI: file.URI},
    genai.Text("Caption this image."))
if err != nil {
    log.Fatal(err)
}

printResponse(resp)

IMAGE_PATH="path/to/sample.jpg"
MIME_TYPE=$(file -b --mime-type "${IMAGE_PATH}")
NUM_BYTES=$(wc -c < "${IMAGE_PATH}")
DISPLAY_NAME=IMAGE

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 "https://generativelanguage.googleapis.com/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: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${IMAGE_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-2.0-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"file_data":{"mime_type": "${MIME_TYPE}", "file_uri": '$file_uri'}},
          {"text": "Caption this image."}]
        }]
      }' 2> /dev/null > response.json

cat response.json
echo

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

  from google.genai import types

  with open('path/to/small-sample.jpg', 'rb') as f:
      img_bytes = f.read()

  response = client.models.generate_content(
    model='gemini-2.0-flash',
    contents=[
      types.Part.from_bytes(
        data=img_bytes,
        mime_type='image/jpeg',
      ),
      'Caption this image.'
    ]
  )

  print(response.text)

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const base64ImageFile = fs.readFileSync("path/to/small-sample.jpg", {
  encoding: "base64",
});

const contents = [
  {
    inlineData: {
      mimeType: "image/jpeg",
      data: base64ImageFile,
    },
  },
  { text: "Caption this image." },
];

const response = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: contents,
});
console.log(response.text);

model := client.GenerativeModel("gemini-2.0-flash")

bytes, err := os.ReadFile("path/to/small-sample.jpg")
if err != nil {
  log.Fatal(err)
}

prompt := []genai.Part{
  genai.Blob{MIMEType: "image/jpeg", Data: bytes},
  genai.Text("Caption this image."),
}

resp, err := model.GenerateContent(ctx, prompt...)
if err != nil {
  log.Fatal(err)
}

for _, c := range resp.Candidates {
  if c.Content != nil {
    fmt.Println(*c.Content)
  }
}

IMG_PATH=/path/to/your/image1.jpg

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
            {
              "inline_data": {
                "mime_type":"image/jpeg",
                "data": "'\$(base64 \$B64FLAGS \$IMG_PATH)'"
              }
            },
            {"text": "Caption this image."},
        ]
      }]
    }' 2> /dev/null

from google import genai
from google.genai import types

import requests

image_path = "https://goo.gle/instrument-img"
image = requests.get(image_path)

client = genai.Client(api_key="GOOGLE_API_KEY")
response = client.models.generate_content(
    model="gemini-2.0-flash-exp",
    contents=["What is this image?",
              types.Part.from_bytes(data=image.content, mime_type="image/jpeg")])

print(response.text)

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

async function main() {
  const ai = new GoogleGenAI({ apiKey: process.env.GOOGLE_API_KEY });

  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 result = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: [
    {
      inlineData: {
        mimeType: 'image/jpeg',
        data: base64ImageData,
      },
    },
    { text: "Caption this image." }
  ],
  });
  console.log(result.text);
}

main();

func main() {
ctx := context.Background()
client, err := genai.NewClient(ctx, option.WithAPIKey(os.Getenv("GOOGLE_API_KEY")))
if err != nil {
  log.Fatal(err)
}
defer client.Close()

model := client.GenerativeModel("gemini-2.0-flash")

// Download the image.
imageResp, err := http.Get("https://goo.gle/instrument-img")
if err != nil {
  panic(err)
}
defer imageResp.Body.Close()

imageBytes, err := io.ReadAll(imageResp.Body)
if err != nil {
  panic(err)
}

// Create the request.
req := []genai.Part{
  genai.ImageData("jpeg", imageBytes),

  genai.Text("Caption this image."),
}

// Generate content.
resp, err := model.GenerateContent(ctx, req...)
if err != nil {
  panic(err)
}

// Handle the response of generated text.
for _, c := range resp.Candidates {
  if c.Content != nil {
    fmt.Println(*c.Content)
  }
}

}

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

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
            {
              "inline_data": {
                "mime_type":"'"$MIME_TYPE"'",
                "data": "'$(curl -sL "$IMG_URL" | base64 $B64FLAGS)'"
              }
            },
            {"text": "Caption this image."}
        ]
      }]
    }' 2> /dev/null

from google import genai
from google.genai import types

client = genai.Client(api_key="GOOGLE_API_KEY")

# Upload the first image
image1_path = "path/to/image1.jpg"
uploaded_file = client.files.upload(file=image1_path)

# Prepare the second image as inline data
image2_path = "path/to/image2.png"
with open(image2_path, 'rb') as f:
    img2_bytes = f.read()

# Create the prompt with text and multiple images
response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents=[
        "What is different between these two images?",
        uploaded_file,  # Use the uploaded file reference
        types.Part.from_bytes(
            data=img2_bytes,
            mime_type='image/png'
        )
    ]
)

print(response.text)

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });

async function main() {
  // Upload the first image
  const image1_path = "path/to/image1.jpg";
  const uploadedFile = await ai.files.upload({
    file: image1_path,
    config: { mimeType: "image/jpeg" },
  });

  // Prepare the second image as inline data
  const image2_path = "path/to/image2.png";
  const base64Image2File = fs.readFileSync(image2_path, {
    encoding: "base64",
  });

  // Create the prompt with text and multiple images
  const response = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: createUserContent([
      "What is different between these two images?",
      createPartFromUri(uploadedFile.uri, uploadedFile.mimeType),
      {
        inlineData: {
          mimeType: "image/png",
          data: base64Image2File,
        },
      },
    ]),
  });
  console.log(response.text);
}

await main();

+    // Upload the first image
image1Path := "path/to/image1.jpg"
uploadedFile, err := client.UploadFileFromPath(ctx, image1Path, nil)
if err != nil {
    log.Fatal(err)
}
defer client.DeleteFile(ctx, uploadedFile.Name)

// Prepare the second image as inline data
image2Path := "path/to/image2.png"
img2Bytes, err := os.ReadFile(image2Path)
if err != nil {
  log.Fatal(err)
}

// Create the prompt with text and multiple images
model := client.GenerativeModel("gemini-2.0-flash")
prompt := []genai.Part{
  genai.Text("What is different between these two images?"),
  genai.FileData{URI: uploadedFile.URI},
  genai.Blob{MIMEType: "image/png", Data: img2Bytes},
}

resp, err := model.GenerateContent(ctx, prompt...)
if err != nil {
  log.Fatal(err)
}

printResponse(resp)

# Upload the first image
IMAGE1_PATH="path/to/image1.jpg"
MIME1_TYPE=$(file -b --mime-type "${IMAGE1_PATH}")
NUM1_BYTES=$(wc -c < "${IMAGE1_PATH}")
DISPLAY_NAME1=IMAGE1

tmp_header_file1=upload-header1.tmp

curl "https://generativelanguage.googleapis.com/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D upload-header1.tmp \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM1_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME1_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME1}'}}" 2> /dev/null

upload_url1=$(grep -i "x-goog-upload-url: " "${tmp_header_file1}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file1}"

curl "${upload_url1}" \
  -H "Content-Length: ${NUM1_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${IMAGE1_PATH}" 2> /dev/null > file_info1.json

file1_uri=$(jq ".file.uri" file_info1.json)
echo file1_uri=$file1_uri

# Prepare the second image (inline)
IMAGE2_PATH="path/to/image2.png"
MIME2_TYPE=$(file -b --mime-type "${IMAGE2_PATH}")

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi
IMAGE2_BASE64=$(base64 $B64FLAGS $IMAGE2_PATH)

# Now generate content using both images
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "What is different between these two images?"},
          {"file_data":{"mime_type": "'"${MIME1_TYPE}"'", "file_uri": '$file1_uri'}},
          {
            "inline_data": {
              "mime_type":"'"${MIME2_TYPE}"'",
              "data": "'"$IMAGE2_BASE64"'"
            }
          }
        ]
      }]
    }' 2> /dev/null > response.json

cat response.json
echo

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

prompt = "Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000."

const prompt = "Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000.";

prompt := []genai.Part{
    genai.FileData{URI: sampleImage.URI},
    genai.Text("Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000."),
}

PROMPT="Detect the all of the prominent items in the image. The box_2d should be [ymin, xmin, ymax, xmax] normalized to 0-1000."

prompt = """
  Give the segmentation masks for the wooden and glass items.
  Output a JSON list of segmentation masks where each entry contains the 2D
  bounding box in the key "box_2d", the segmentation mask in key "mask", and
  the text label in the key "label". Use descriptive labels.
"""

const prompt = `
  Give the segmentation masks for the wooden and glass items.
  Output a JSON list of segmentation masks where each entry contains the 2D
  bounding box in the key "box_2d", the segmentation mask in key "mask", and
  the text label in the key "label". Use descriptive labels.
`;    

prompt := []genai.Part{
    genai.FileData{URI: sampleImage.URI},
    genai.Text(`
      Give the segmentation masks for the wooden and glass items.
      Output a JSON list of segmentation masks where each entry contains the 2D
      bounding box in the key "box_2d", the segmentation mask in key "mask", and
      the text label in the key "label". Use descriptive labels.
    `),
}

PROMPT='''
  Give the segmentation masks for the wooden and glass items.
  Output a JSON list of segmentation masks where each entry contains the 2D
  bounding box in the key "box_2d", the segmentation mask in key "mask", and
  the text label in the key "label". Use descriptive labels.
'''