Gemini Robotics ER

from google import genai

PROMPT = """
          Point to no more than 10 items in the image. The label returned
          should be an identifying name for the object detected.
          The answer should follow the json format: [{"point": <point>,
          "label": <label1>}, ...]. The points are in [y, x] format
          normalized to 0-1000.
        """
client = genai.Client()

uploaded_file = client.files.upload(file="my-image.png")

image_response = client.interactions.create(
    model="gemini-robotics-er-2-preview",
    input=[
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        },
        {"type": "text", "text": PROMPT}
    ],
    generation_config={"thinking_level": "high"},
)

print(image_response.output_text)

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

const PROMPT = `
  Point to no more than 10 items in the image. The label returned
  should be an identifying name for the object detected.
  The answer should follow the json format: [{"point": <point>,
  "label": <label1>}, ...]. The points are in [y, x] format
  normalized to 0-1000.
`;
const client = new GoogleGenAI();

const uploadedFile = await client.files.upload({ file: "my-image.png" });

const imageResponse = await client.interactions.create({
  model: "gemini-robotics-er-2-preview",
  input: [
    {
      type: "image",
      uri: uploadedFile.uri,
      mime_type: uploadedFile.mimeType,
    },
    { type: "text", text: PROMPT },
  ],
  generation_config: { thinking_level: "high" },
});

console.log(imageResponse.output_text);

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.GenerationConfig;
import com.google.genai.gaos.models.interactions.ImageContent;
import com.google.genai.gaos.models.interactions.ImageContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.interactions.ThinkingLevel;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.types.File;
import com.google.genai.types.UploadFileConfig;
import java.util.List;

Client client = new Client();

String prompt =
    "Point to no more than 10 items in the image. The label returned "
        + "should be an identifying name for the object detected. "
        + "The answer should follow the json format: [{\"point\": <point>, "
        + "\"label\": <label1>}, ...]. The points are in [y, x] format "
        + "normalized to 0-1000.";

File uploadedFile =
    client.files.upload(
        new java.io.File("my-image.png"),
        UploadFileConfig.builder().mimeType("image/png").build());

Content imageContent =
    ImageContent.builder()
        .uri(uploadedFile.uri().orElse(""))
        .mimeType(ImageContentMimeType.of(uploadedFile.mimeType().orElse("image/png")))
        .build();
Content textContent = TextContent.builder().text(prompt).build();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-robotics-er-2-preview"))
        .input(InteractionsInput.ofContent(List.of(imageContent, textContent)))
        .generationConfig(
            GenerationConfig.builder().thinkingLevel(ThinkingLevel.HIGH).build())
        .build();

Interaction imageResponse =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(imageResponse.outputText().orElse(""));

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    prompt := `Point to no more than 10 items in the image. The label returned
should be an identifying name for the object detected.
The answer should follow the json format: [{"point": <point>,
"label": <label1>}, ...]. The points are in [y, x] format
normalized to 0-1000.`

    uploadedFile, err := client.Files.UploadFromPath(ctx, "my-image.png", &genai.UploadFileConfig{
        MIMEType: "image/png",
    })
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-robotics-er-2-preview"),
            Input: interactions.NewInteractionsInput([]interactions.Content{
                interactions.NewContent(interactions.ImageContent{
                    URI:      genai.Ptr(uploadedFile.URI),
                    MimeType: genai.Ptr(interactions.ImageMimeTypeImagePng),
                }),
                interactions.NewContent(interactions.TextContent{
                    Text: prompt,
                }),
            }),
            GenerationConfig: &interactions.GenerationConfig{
                ThinkingLevel: interactions.ThinkingLevelHigh.ToPointer(),
            },
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

# First, ensure you have the image file locally.
# Encode the image to base64
IMAGE_BASE64=$(base64 -w 0 my-image.png)

curl -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-robotics-er-2-preview",
    "input": {
      "parts": [
        {
          "inlineData": {
            "mimeType": "image/png",
            "data": "'"${IMAGE_BASE64}"'"
          }
        },
        {
          "text": "Point to no more than 10 items in the image. The label returned should be an identifying name for the object detected. The answer should follow the json format: [{\"point\": [y, x], \"label\": <label1>}, ...]. The points are in [y, x] format normalized to 0-1000."
        }
      ]
    },
    "generation_config": {
      "thinking_config": {
        "thinking_level": "high"
      }
    }
  }'

[
  {"point": [376, 508], "label": "small banana"},
  {"point": [287, 609], "label": "larger banana"},
  {"point": [223, 303], "label": "pink starfruit"},
  {"point": [435, 172], "label": "paper bag"},
  {"point": [270, 786], "label": "green plastic bowl"},
  {"point": [488, 775], "label": "metal measuring cup"},
  {"point": [673, 580], "label": "dark blue bowl"},
  {"point": [471, 353], "label": "light blue bowl"},
  {"point": [492, 497], "label": "bread"},
  {"point": [525, 429], "label": "lime"}
]