OCR

from perceptron import image, ocr

result = ocr(
    image(image_path),         # ImageNode wrapping a path/URL/bytes
    prompt="Extract item",     # Optional str: Instruction override
    expects="text",            # str: "text" | "box" | "point"
    reasoning=True,            # bool: enable reasoning and include chain-of-thought
)

print(result.reasoning)        # Chain-of-thought (None when reasoning=False)
print(result.text)

# When expects="box", access grounded text spans via result.boxes
for box in result.boxes or []:
    print(box.mention, box)

from pathlib import Path
from urllib.request import urlretrieve

from perceptron import configure, image, ocr
from PIL import Image as PILImage, ImageDraw

configure(
    provider="perceptron",
    model="isaac-0.2-2b-preview",
    api_key="YOUR_API_KEY",
)

# Download sample image
IMAGE_URL = "https://raw.githubusercontent.com/perceptron-ai-inc/perceptron/main/cookbook/_shared/assets/capabilities/in-context-learning-video/mini_wheats.jpeg"
IMAGE_PATH = Path("mini_wheats.jpeg")
ANNOTATED_PATH = Path("mini_wheats_annotated.png")

if not IMAGE_PATH.exists():
    urlretrieve(IMAGE_URL, IMAGE_PATH)

# Run OCR
result = ocr(
    image(str(IMAGE_PATH)),
    prompt="Extract brand and product name from this package.",
    expects="box",
)

print(result.text)

# Draw grounded regions
img = PILImage.open(IMAGE_PATH).convert("RGB")
draw = ImageDraw.Draw(img)
pixel_boxes = result.boxes_to_pixels(width=img.width, height=img.height) or []

for box in pixel_boxes:
    draw.rectangle(
        [
            int(box.top_left.x),
            int(box.top_left.y),
            int(box.bottom_right.x),
            int(box.bottom_right.y),
        ],
        outline="yellow",
        width=3,
    )
    label = box.mention or "text"
    draw.text((int(box.top_left.x), max(int(box.top_left.y) - 18, 0)), label, fill="yellow")

img.save(ANNOTATED_PATH)
print(f"Saved annotated image to {ANNOTATED_PATH}")

perceptron ocr <image_path_or_url> [--prompt "instruction"] [--format text|json]

# Default transcription
perceptron ocr mini_wheats.jpeg

# Target specific fields and request JSON output
perceptron ocr mini_wheats.jpeg --prompt "Extract brand and product name." --format json