AI Inference

Raw data
  → Table extraction (unstructured text → columns)
    → Normalize (inconsistent column names → target schema)
      → Validate (flag rows that fail quality checks)
        → Stored in DataLinks

import requests

response = requests.post(
    "https://api.datalinks.com/api/v1/ingest/namespace/datasetName",
    headers={"Authorization": "Bearer YOUR_TOKEN"},
    json={
        "data": [
            {"col1": 123, "col2": "foo", "colWithATable": "direction,size;up,large"},
            {"col1": 444, "col2": "bar"}
        ],
        "infer": {
            "steps": [
                {
                    "type": "table",
                    "deriveFrom": "colWithATable",
                    "helperPrompt": "This text contains a table comma separated, but instead of line breaks we are using a ';'."
                }
            ]
        }
    }
)

{
    "type": "table",
    "deriveFrom": "source_column",
    "helperPrompt": "Optional prompt to guide extraction."
}

{
    "type": "rows",
    "deriveFrom": "json_column"
}

{
    "type": "normalize",
    "mode": "all-in-one",
    "targetCols": {
        "full_name": "The person's full name, without titles like Dr. or Mr.",
        "age": "Age as a number",
        "company": "Company or organization name",
        "email": "Email address"
    },
    "helperPrompt": "This data comes from professional directory listings."
}

{
    "type": "validate",
    "mode": "regex|rows|fields",
    "columns": ["column1", "column2"]
}

{
    "type": "reverseGeo",
    "deriveFrom": "locationColumnName"
}

Extract the following fields: MemberName (full name without academic
titles like Dr. or Prof.), Address (street address), City, Country
(normalize all country names to English), Phone (include country code,
replacing a leading 0 with the appropriate code), Email, Website.

This text contains a semicolon-delimited table. Columns are separated
by commas and rows are separated by semicolons.

If a phone number does not include a country code (+XX), add the
appropriate code based on the country. If latitude/longitude are
present, format them as "lat,long".

Extract all entries. Do not skip any. Omit personal honorifics like
Ms., Mr., Frau, Herr from names.

{
    "type": "table",
    "deriveFrom": "notes",
    "helperPrompt": "Extract product names and prices.",
    "model": "your-model-here",
    "provider": "openai"
}

import requests

# Configuration
API_TOKEN = "YOUR_TOKEN"
NAMESPACE = "your_namespace"
DATASET = "dental_practices"

# Sample data: unstructured directory entries
data = [
    {"entry": "Dr. Alice Chen, Northwind Dental, 42 Oak St, Springfield, (555) 012-3456, alice@northwind.com"},
    {"entry": "Bob Martinez - Rivera Family Dentistry. 100 Main Ave, Portland OR 97201. bob@riveradental.com"}
]

# Inference pipeline configuration
inference_steps = {
    "steps": [
        # Step 1: Extract structured fields from free text
        {
            "type": "table",
            "deriveFrom": "entry",
            "helperPrompt": "Each entry is a dental practice listing. Extract the practitioner name (without Dr. or similar titles), practice name, street address, city, state, phone number (with +1 country code), and email."
        },
        # Step 2: Normalize to consistent schema
        {
            "type": "normalize",
            "mode": "all-in-one",
            "targetCols": {
                "practitioner": "Full name of the dentist, without titles",
                "practice_name": "Name of the dental practice",
                "address": "Street address",
                "city": "City name",
                "state": "US state name or abbreviation",
                "phone": "Phone number with +1 country code",
                "email": "Email address"
            },
            "helperPrompt": "These are US-based dental practices."
        },
        # Step 3: Validate email and phone fields
        {
            "type": "validate",
            "mode": "fields",
            "columns": ["email", "phone"]
        }
    ]
}

# Make the API request
response = requests.post(
    f"https://api.datalinks.com/api/v1/ingest/{NAMESPACE}/{DATASET}",
    headers={
        "Authorization": f"Bearer {API_TOKEN}",
        "Content-Type": "application/json"
    },
    json={
        "data": data,
        "infer": inference_steps
    }
)

# Check result
if response.status_code == 200:
    print("Ingestion successful!")
    print(response.json())
else:
    print(f"Error: {response.status_code}")
    print(response.text)

{
    "dataDescription": "Dental practice directory entries with contact information.",
    "fieldDefinition": "practitioner=Full name without titles\npractice_name=Name of the dental practice\naddress=Street address\ncity=City\nstate=US state\nphone=Phone with country code\nemail=Email address"
}