All MicroEvals
Írj egx brutalisan maximalis reszletessegu system promptpt a...
Create MicroEval
Header image for Írj egx brutalisan maximalis reszletessegu system promptpt a...

Írj egx brutalisan maximalis reszletessegu system promptpt a...

Prompt

Írj egx brutalisan maximalis reszletessegu system promptpt amodelhez hogy minden képet amit kap maximálisan elemezze és pixel pontosan minden részletet adatot stbt json formába írja ki. Code Execution with images (Gemini 3) The Gemini 3 Flash model can now write and execute Python code to actively manipulate and inspect images. Use cases Zoom and inspect: The model implicitly detects when details are too small (e.g., reading a distant gauge) and writes code to crop and re-examine the area at higher resolution. Visual math: The model can run multi-step calculations using code (e.g., summing line items on a receipt). Image annotation: The model can annotate images to answer questions, such as drawing arrows to show relationships. Note: While the model automatically handles zooming for small details, you should prompt it explicitly to use code for other tasks, such as "Write code to count the number of gears" or "Rotate this image to make it upright". Enable Code Execution with images Code Execution with images is officially supported in Gemini 3 Flash. You can activate this behavior by enabling both Code Execution as a tool and Thinking. Python JavaScript REST from google import genai import requests import base64 from PIL import Image import io image_path = "https://goo.gle/instrument-img" image_bytes = requests.get(image_path).content client = genai.Client() interaction = client.interactions.create( model="gemini-3.7-flash", input=[ {"type": "image", "data": base64.b64encode(image_bytes).decode('utf-8'), "mime_type": "image/jpeg"}, {"type": "text", "text": "Zoom into the expression pedals and tell me how many pedals are there?"} ], tools=[{"type": "code_execution"}] ) 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": img = Image.open(io.BytesIO(base64.b64decode(content_block.data))) img.show() # or: img.save("output_image.jpg") elif step.type == "code_execution_call": print(step.arguments.code) elif step.type == "code_execution_result": print(step.result)