Einstein プロンプトの例

Identify key elements from the specified document and return them in JSON format.
Do not create new information, provide answers only from the text provided. The JSON format is as follows:

{
    "id_data": {
        "doc_number":<replace with value found for License ID or document ID>,
        "first_name": <replace with the first name of the person in the text>,
        "last_name": <replace with the last name of the person in the text>,
        "issue_date": <replace with the date of issue of this document>,
        "dob": <replace with date of birth found in the text also represented as dob>,
        "exp_date": <replace with expiration date, sometimes written as EXP>,
        "state_region": <replace with state or region where this document was issued>,
        "height": <replace with height specified if not found, say "not found">,
        "class": <replace with vehicle classification if found">,
        "eye_color": <replace with eye color if found">,
        "sex": <sex as specified>,
        "weight": <replace with the weight found>,
        "restrictions":<replace with any restrictions listed in the document>,
        "address": {
            "street": <replace with the street line of the address including any apartment numbers>,
            "city":<replace with the city in the address found>,
            "state": <replace with the state found in the address>,
            "zip": <replace with the zipcode found in the address>
        }
    }
}

{
  "id_data": {
    "doc_number": "12345678",
    "first_name": "The Genius",
    "last_name": "Einstein",
    "issue_date": "10/30/2024",
    "dob": "03/14/1879",
    "exp_date": "10/31/2031",
    "state_region": "California",
    "height": "5'5\"",
    "class": "D",
    "eye_color": "BROWN",
    "sex": "M",
    "weight": "150 lb",
    "restrictions": "None",
    "address": {
      "street": "707 South Oakland Avenue",
      "city": "Pasadena",
      "state": "CA",
      "zip": "91106"
    }
  }
}

Classify each page of the following timesheet summary as a unique document type and also identify whether the page continues from the previous document type or it is a new one.
Summarize all the employee's names in the timesheet summary document and the pages where their timesheet entry is found.
Structure the output as a JSON where the employee name is the key and the page number is the value.

{
    "Jane Almeida": 1,
    "Charles Montes": 2,
    "Albert Vignoli": 3,
    "Max the Mule": 4
}

Analyze this form for a medical leave and extract its values. Don't extract document's title.
Present the data as key-value pairs in a JSON formatted response.

If you find a date, format it as YYYY/MM/DD.
If you find a list of handwritten symptoms, return them as an array and label them "Reason for Absence".

Do not create any facts of information, interpret only the information in the document.

An example output JSON is:

    "Patient_Name": {
        "value": "Paul Grant"
    }