automatic-goggles 0.1.0

A package for extracting structured fields from call transcripts with confidence scores

Automatic Goggles

A Python package for extracting structured fields from call transcripts with confidence scores using DSPy and OpenAI's language models.

Features

• Extract structured fields from conversation transcripts
• Get confidence scores for extracted data using log probabilities
• Support for multiple field types (currently supports string fields)
• Easy integration with OpenAI API
• Similar functionality to RetellAI post-call processing

Installation

pip install automatic-goggles

Quick Start

from transtype import TranscriptProcessor

# Initialize the processor with your OpenAI API key
processor = TranscriptProcessor(api_key="your-openai-api-key")

# Define your input data
data = {
    "messages": [
        {
            "role": "assistant",
            "content": "Hi, this is Marcus, I'm a customer service representative with TechFlow Solutions in Downtown Seattle."
        },
        {
            "role": "user", 
            "content": "I need to discuss my account billing issues."
        }
    ],
    "fields": [
        {
            "field_name": "representative_name",
            "field_type": "string",
            "format_example": "Sarah Chen"
        }
    ]
}

# Process the transcript
result = processor.process(data)
print(result)

Output Format

{
    "fields": [
        {
            "field_name": "representative_name",
            "field_value": "Marcus",
            "field_confidence": 0.95,
            "field_reason": "Representative introduced himself as 'Marcus' at the beginning of the conversation"
        }
    ]
}

Requirements

• Python 3.8+
• OpenAI API key

License

MIT License