OCR

import json
import os

from jsonschema import validate
from perceptron import Client, image

client = Client(api_key=os.environ["PERCEPTRON_API_KEY"])
image_url = (
    "https://raw.githubusercontent.com/perceptron-ai-inc/perceptron/"
    "main/cookbook/_shared/assets/capabilities/ocr/grocery_labels.webp"
)
schema = {
    "type": "object",
    "properties": {
        "items": {
            "type": "array",
            "items": {
                "type": "object",
                "properties": {
                    "product": {"type": ["string", "null"]},
                    "price": {"type": ["string", "null"]},
                },
                "required": ["product", "price"],
                "additionalProperties": False,
            },
        },
    },
    "required": ["items"],
    "additionalProperties": False,
}
response = client.chat.completions.create(
    model="perceptron-mk1.5",
    messages=[{
        "role": "user",
        "content": [
            image(image_url),
            {"type": "text", "text": (
                "Extract the visible product names and their associated listed prices "
                "in reading order. Preserve spelling, currency symbols, and decimal "
                "separators exactly as printed. Use null for a field you cannot read; "
                "do not guess or pair a product with an unrelated price. Return an "
                "empty items array if there are no relevant labels."
            )},
        ],
    }],
    reasoning_effort="high",
    max_completion_tokens=2048,
    response_format={
        "type": "json_schema",
        "json_schema": {"name": "product_prices", "strict": True, "schema": schema},
    },
)
choice = response.choices[0]
if choice.finish_reason != "stop" or choice.message.tool_calls:
    raise RuntimeError(f"Incomplete OCR response: {choice.finish_reason}")
result = json.loads(choice.message.content or "")
validate(instance=result, schema=schema)
print(json.dumps(result, indent=2))

{
  "items": [
    {"product": "Example product", "price": "$3.49"},
    {"product": "Another product", "price": null}
  ]
}

response = client.chat.completions.create(
    model="perceptron-mk1.5",
    messages=[{
        "role": "user",
        "content": [
            image(image_url),
            {"type": "text", "text": (
                "Read the visible grocery labels and return a Markdown table with "
                "Product and Price columns, one row per label in reading order. "
                "Preserve the printed text and currency formatting. Write [unreadable] "
                "for unclear text instead of guessing. Do not add code fences."
            )},
        ],
    }],
    reasoning_effort="high",
    max_completion_tokens=2048,
)
choice = response.choices[0]
if choice.finish_reason != "stop" or choice.message.tool_calls:
    raise RuntimeError("The Markdown extraction did not complete")
print(choice.message.content or "")

from pathlib import Path

response = client.chat.completions.create(
    model="perceptron-mk1.5",
    messages=[{
        "role": "user",
        "content": [
            image(image_url),
            {"type": "text", "text": (
                "Locate the visible product-name and price text spans. Return a "
                "flat point_box for each span, with the transcribed text as its mention "
                "and asset_idx=0. Use normalized coordinates, without collections or tracks. Do not invent text "
                "that is too small or obscured to read."
            )},
        ],
    }],
    reasoning_effort="high",
    max_completion_tokens=2048,
    vision_config={"annotation_format": "box"},
)
choice = response.choices[0]
if choice.finish_reason != "stop" or choice.message.tool_calls:
    raise RuntimeError("The grounded OCR answer did not complete")
annotations = choice.message.content or ""
print(annotations)
Path("response.txt").write_text(annotations, encoding="utf-8")