1rgs/jsonformer

from jsonformer import Jsonformer
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("databricks/dolly-v2-12b")
tokenizer = AutoTokenizer.from_pretrained("databricks/dolly-v2-12b")

json_schema = {
    "type": "object",
    "properties": {
        "name": {"type": "string"},
        "age": {"type": "number"},
        "is_student": {"type": "boolean"},
        "courses": {
            "type": "array",
            "items": {"type": "string"}
        }
    }
}

prompt = "Generate a person's information based on the following schema:"
jsonformer = Jsonformer(model, tokenizer, json_schema, prompt)
generated_data = jsonformer()

print(generated_data)

{"type": "object", "properties": {"car": {"type": "object", "properties": {"make": {"type": "string"}, "model": {"type": "string"}, "year": {"type": "number"}, "colors": {"type": "array", "items": {"type": "string"}}, "features": {"type": "object", "properties": {"audio": {"type": "object", "properties": {"brand": {"type": "string"}, "speakers": {"type": "number"}, "hasBluetooth": {"type": "boolean"}}}, "safety": {"type": "object", "properties": {"airbags": {"type": "number"}, "parkingSensors": {"type": "boolean"}, "laneAssist": {"type": "boolean"}}}, "performance": {"type": "object", "properties": {"engine": {"type": "string"}, "horsepower": {"type": "number"}, "topSpeed": {"type": "number"}}}}}}}, "owner": {"type": "object", "properties": {"firstName": {"type": "string"}, "lastName": {"type": "string"}, "age": {"type": "number"}}}}}

{
  car: {
    make: "audi",
    model: "model A8",
    year: 2016.0,
    colors: [
      "blue"
    ],
    features: {
      audio: {
        brand: "sony",
        speakers: 2.0,
        hasBluetooth: True
      },
      safety: {
        airbags: 2.0,
        parkingSensors: True,
        laneAssist: True
      },
      performance: {
        engine: "4.0",
        horsepower: 220.0,
        topSpeed: 220.0
      }
    }
  },
  owner: {
    firstName: "John",
    lastName: "Doe",
    age: 40.0
  }
}

pip install jsonformer

poetry install

poetry run python -m jsonformer.example