Gemini Robotics ER 2 概览

from google import genai
from google.genai import types

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(
    enterprise=True,
    project="your-project-id",
    location="global",
)

# Load your image
with open("my-image.png", 'rb') as f:
    image_bytes = f.read()

image_response = client.models.generate_content(
    model="gemini-robotics-er-2-preview",
    contents=[
        types.Part.from_bytes(
            data=image_bytes,
            mime_type='image/png',
        ),
        PROMPT
    ],
    config = types.GenerateContentConfig(
        temperature=1.0,
        thinking_config=types.ThinkingConfig(
            thinking_level=types.ThinkingLevel.HIGH
        ),
    )
)

print(image_response.text)

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

# Set your Google Cloud project and location.
export PROJECT_ID="your-project-id"
export LOCATION="global"
export MODEL="gemini-robotics-er-2-preview"

# For the "global" location, use the aiplatform.googleapis.com host.
# For a regional location, prefix the host with the region, for example:
# https://us-central1-aiplatform.googleapis.com

curl -X POST \
  "https://aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL}:generateContent" \
  -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "'"${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."
          }
        ]
      }
    ],
    "generationConfig": {
      "temperature": 1.0,
      "thinkingConfig": {
        "thinkingLevel": "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"}
]