🔍 Code Extractor

A dataclass that encapsulates comprehensive analysis results of a document, including page-level and document-level summaries, topics, findings, and confidence metrics.

Purpose

DocumentSummary serves as a structured data container for storing and transferring complete document analysis results. It aggregates information from multi-page document processing, including individual page summaries, extracted topics, key findings, and an overall document summary with a confidence score. This class is typically used as the output format for document analysis pipelines that process PDFs or other multi-page documents.

Source Code

class DocumentSummary:
    """Summary of complete document analysis"""
    total_pages: int
    document_type: str
    main_topics: List[str]
    key_findings: List[str]
    page_summaries: List[str]
    overall_summary: str
    confidence_score: float

Parameters

Name	Type	Default	Kind
bases	-	-

Parameter Details

total_pages: Integer representing the total number of pages analyzed in the document. Must be a positive integer.

document_type: String classification of the document type (e.g., 'report', 'invoice', 'contract', 'research paper'). Helps categorize the document for downstream processing.

main_topics: List of strings containing the primary topics or themes identified across the entire document. Each string represents a distinct topic.

key_findings: List of strings containing the most important findings, conclusions, or insights extracted from the document. Each string represents a significant finding.

page_summaries: List of strings where each element contains the summary of a corresponding page. The list length should match total_pages.

overall_summary: String containing a comprehensive summary of the entire document, synthesizing information from all pages.

confidence_score: Float value between 0.0 and 1.0 representing the confidence level of the analysis. Higher values indicate greater confidence in the extracted information.

Return Value

Instantiation returns a DocumentSummary object containing all the specified attributes. As a dataclass, it automatically generates __init__, __repr__, __eq__, and other methods. The object serves as an immutable-by-convention data structure for passing document analysis results.

Class Interface

Methods

Attributes

Name	Type	Description	Scope
total_pages	int	Total number of pages in the analyzed document	instance
document_type	str	Classification or category of the document (e.g., 'report', 'invoice', 'contract')	instance
main_topics	List[str]	List of primary topics or themes identified across the document	instance
key_findings	List[str]	List of important findings, conclusions, or insights extracted from the document	instance
page_summaries	List[str]	List of summaries for each page, where index corresponds to page number	instance
overall_summary	str	Comprehensive summary synthesizing information from the entire document	instance
confidence_score	float	Confidence level of the analysis results, typically ranging from 0.0 to 1.0	instance

Dependencies

• dataclasses
• typing

Required Imports

from dataclasses import dataclass
from typing import List

Usage Example

from dataclasses import dataclass
from typing import List

@dataclass
class DocumentSummary:
    total_pages: int
    document_type: str
    main_topics: List[str]
    key_findings: List[str]
    page_summaries: List[str]
    overall_summary: str
    confidence_score: float

# Create a document summary instance
summary = DocumentSummary(
    total_pages=5,
    document_type='research paper',
    main_topics=['machine learning', 'natural language processing', 'transformers'],
    key_findings=['Transformers outperform RNNs', 'Attention mechanism is key'],
    page_summaries=['Page 1: Introduction to NLP', 'Page 2: Methodology', 'Page 3: Results', 'Page 4: Discussion', 'Page 5: Conclusion'],
    overall_summary='This paper presents a comprehensive study on transformer models in NLP tasks.',
    confidence_score=0.92
)

# Access attributes
print(f'Document has {summary.total_pages} pages')
print(f'Type: {summary.document_type}')
print(f'Confidence: {summary.confidence_score}')
for topic in summary.main_topics:
    print(f'Topic: {topic}')

Best Practices

• Always ensure total_pages matches the length of page_summaries list for consistency
• Keep confidence_score between 0.0 and 1.0 to maintain standard probability conventions
• Use descriptive and consistent document_type values to enable proper categorization
• Populate main_topics with distinct, non-overlapping topics for clarity
• Keep key_findings concise and actionable, focusing on the most important insights
• Since this is a dataclass, it's immutable by convention - avoid modifying attributes after instantiation
• Consider using frozen=True in the @dataclass decorator if true immutability is required
• Validate data before instantiation to ensure all required fields are properly populated
• Use this class as a return type for document analysis functions to maintain consistent API contracts

Tags

Similar Components

AI-powered semantic similarity - components with related functionality:

• class MultiPageAnalysisResult 75.7% similar

  A dataclass that encapsulates the complete results of analyzing a multi-page document, including individual page analyses, document summary, combined response, and processing statistics.

  From: /tf/active/vicechatdev/e-ink-llm/multi_page_llm_handler.py

• class PageAnalysis 70.6% similar

  A dataclass that encapsulates the analysis results for a single PDF page, including its image representation, text content, dimensions, and optional analysis metadata.

  From: /tf/active/vicechatdev/e-ink-llm/multi_page_processor.py

• class DataSection 64.0% similar

  A dataclass representing a dedicated data analysis section that stores analysis results, plots, dataset information, and conclusions separately from text content.

  From: /tf/active/vicechatdev/vice_ai/models.py

• class AnalysisResult 63.9% similar

  A dataclass that encapsulates the results from statistical analysis operations, including metadata, file paths, and timestamps.

  From: /tf/active/vicechatdev/vice_ai/smartstat_models.py

• class AnalysisResult_v1 63.5% similar

  A dataclass that encapsulates the results from statistical analysis operations, including metadata, file paths, and timestamps.

  From: /tf/active/vicechatdev/vice_ai/models.py

class DocumentSummary:
    """Summary of complete document analysis"""
    total_pages: int
    document_type: str
    main_topics: List[str]
    key_findings: List[str]
    page_summaries: List[str]
    overall_summary: str
    confidence_score: float