example_basic.py

"""
ExisEcho API - Basic Example

This example demonstrates basic duplicate detection using the ExisEcho API.

Get your FREE test API key by emailing: exisllc@gmail.com
Documentation: https://www.fuzzy-logic.com/Api
"""

from exisecho import ExisEchoClient

# Replace with your API key
API_KEY = "your-api-key-here"


def main():
    # Initialize the client
    client = ExisEchoClient(API_KEY)

    # Sample data with potential duplicates
    records = [
        {"id": "1", "fields": {"name": "John Smith", "email": "john.smith@example.com"}},
        {"id": "2", "fields": {"name": "Jon Smyth", "email": "jon.smyth@example.com"}},
        {"id": "3", "fields": {"name": "Jane Doe", "email": "jane.doe@example.com"}},
        {"id": "4", "fields": {"name": "John A. Smith", "email": "johnsmith@example.com"}},
        {"id": "5", "fields": {"name": "Robert Johnson", "email": "bob.johnson@example.com"}},
        {"id": "6", "fields": {"name": "Bob Johnson", "email": "robert.j@example.com"}},
    ]

    print("ExisEcho API - Basic Example")
    print("=" * 50)
    print()
    print(f"Checking {len(records)} records for duplicates...")
    print()

    # Find duplicates with default settings
    result = client.find_duplicates(
        records=records,
        threshold=0.7,
        column_options={
            "name": {
                "usePhoneticMatching": True,
                "equateSynonyms": True,
                "ignoreWordOrder": True
            }
        }
    )

    if result["success"]:
        summary = result["summary"]
        print(f"Results:")
        print(f"  - Records analyzed: {summary['totalRecordsAnalyzed']}")
        print(f"  - Duplicates found: {summary['totalMatches']}")
        print(f"  - Processing time: {summary['processingTimeMs']}ms")
        print()

        if result["matches"]:
            print("Potential Duplicates:")
            print("-" * 50)
            for match in result["matches"]:
                # Find the original records for display
                rec1 = next(r for r in records if r["id"] == match["record1Id"])
                rec2 = next(r for r in records if r["id"] == match["record2Id"])

                print(f"  Match Score: {match['score']:.0%} ({match['quality']})")
                print(f"    Record {match['record1Id']}: {rec1['fields']['name']}")
                print(f"    Record {match['record2Id']}: {rec2['fields']['name']}")
                print()

        # Show usage info
        usage = result["usage"]
        print(f"API Usage:")
        print(f"  - Units consumed: {usage['unitsConsumed']}")
        print(f"  - Units remaining: {usage['unitsRemaining']}")
    else:
        print(f"Error: {result.get('error', 'Unknown error')}")


if __name__ == "__main__":
    main()