Prompting reference

curl -X POST "https://api.perceptron.inc/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PERCEPTRON_API_KEY" \
  -d '{
  "model": "isaac-0.1",
  "messages": [
    { "role": "system", "content": [{"type": "text", "text": "<hint>BOX</hint>"}] },
    { "role": "user",
      "content": [
        {"type": "image_url", "image_url": {"url": "<image-url>"}},
        {"type": "text", "text": "Find all the safety equipment"}
      ]
    }
  ]
}'

curl -X POST "https://api.perceptron.inc/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PERCEPTRON_API_KEY" \
  -d '{
  "model": "isaac-0.1",
  "messages": [
    { "role": "system", "content": [{"type": "text", "text": "<hint>POINT</hint>"}] },
    { "role": "user",
      "content": [
        {"type": "image_url", "image_url": {"url": "<image-url>"}},
        {"type": "text", "text": "Point at each visible helmet"}
      ]
    }
  ]
}'

from perceptron import configure, perceive, image, text

configure(provider="perceptron", api_key="YOUR_API_KEY")

@perceive(model="isaac-0.1")
def analyze(photo):
    return image(photo) + text("Identify the dominant colors in this scene")

result = analyze("scene.jpg")
print(result.text)

from pydantic import BaseModel
from perceptron import configure, perceive, pydantic_format, image, text

configure(provider="perceptron", api_key="YOUR_API_KEY")

class SceneAnalysis(BaseModel):
    primary_color: str
    object_count: int
    description: str

@perceive(model="isaac-0.1", response_format=pydantic_format(SceneAnalysis))
def analyze_scene(photo):
    return image(photo) + text("Analyze this image and return the structured result.")

scene = analyze_scene("photo.jpg")
print(scene.primary_color, scene.object_count)