الاستدلال المكاني

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)

# 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"