Search - Code Extractor

function create_excel_report_improved

Creates a multi-sheet Excel report from warranty data, including main report, summary view, complete data, references, and statistics sheets with auto-formatted columns.

File: /tf/active/vicechatdev/improved_convert_disclosures_to_table.py

excel reporting data-export pandas multi-sheet

function main_v14

Orchestrates the conversion of an improved markdown file containing warranty disclosures into multiple tabular formats (CSV, Excel, Word) with timestamp-based file naming.

File: /tf/active/vicechatdev/improved_convert_disclosures_to_table.py

file-conversion markdown-processing warranty-data csv-export excel-export

class RegulatoryExtractor

A class for extracting structured metadata from regulatory guideline PDF documents using LLM-based analysis and storing the results in an Excel tracking spreadsheet.

File: /tf/active/vicechatdev/reg_extractor.py

pdf-extraction regulatory-documents llm-extraction ocr data-extraction

function create_excel_report

Creates a multi-sheet Excel report from warranty data, including main report, summary view, complete data, and statistics sheets with auto-formatted columns.

File: /tf/active/vicechatdev/convert_disclosures_to_table.py

excel reporting data-export pandas openpyxl

function main_v25

Converts a markdown file containing warranty disclosure data into multiple tabular formats (CSV, Excel, Word) with timestamped output files.

File: /tf/active/vicechatdev/convert_disclosures_to_table.py

markdown-conversion data-extraction report-generation csv-export excel-export

class DocumentProcessor_v5

Process different document types for RAG context extraction

File: /tf/active/vicechatdev/offline_docstore_multi_vice.py

class documentprocessor

A class that converts various document formats (Word, Excel, PowerPoint, OpenDocument, Visio) to PDF using LibreOffice's headless conversion capabilities, with support for parallel processing and directory structure preservation.

File: /tf/active/vicechatdev/pdfconverter.py

document-conversion pdf libreoffice batch-processing parallel-processing

class ReferenceManager_v4

Manages extraction and formatting of references for LLM chat responses. Handles both file references and BibTeX citations, formatting them according to various academic citation styles.

File: /tf/active/vicechatdev/OneCo_hybrid_RAG.py

class referencemanager

class PDFConverter

A class that converts various document formats (Word, PowerPoint, Excel, images) to PDF format using LibreOffice and ReportLab libraries.

File: /tf/active/vicechatdev/msg_to_eml.py

pdf conversion document-processing file-conversion libreoffice

class DocumentProcessor_v6

Process different document types for RAG context extraction

File: /tf/active/vicechatdev/offline_docstore_multi.py

class documentprocessor

function view_document

Flask route handler that serves documents for in-browser viewing by accepting a file path as a query parameter, validating security constraints, and returning the file with appropriate MIME types and CORS headers.

File: /tf/active/vicechatdev/docchat/app.py

flask file-serving document-viewer security path-validation

class DocChatRAG

Main RAG engine with three operating modes: 1. Basic RAG (similarity search) 2. Extensive (full document retrieval with preprocessing) 3. Full Reading (process all documents)

File: /tf/active/vicechatdev/docchat/rag_engine.py

class docchatrag

class DocumentProcessor_v8

Process different document types for indexing

File: /tf/active/vicechatdev/docchat/document_indexer.py

class documentprocessor

class DocumentIndexer

A class for indexing documents into ChromaDB with support for multiple file formats (PDF, Word, PowerPoint, Excel, text files), smart incremental indexing, and document chunk management.

File: /tf/active/vicechatdev/docchat/document_indexer.py

document-indexing vector-database chromadb embeddings pdf-processing

class ContractDataExtractor

Extract structured data from legal contracts using LLM analysis

File: /tf/active/vicechatdev/contract_validity_analyzer/extractor.py

class contractdataextractor

function main

Main entry point function for a Legal Contract Data Extractor application that processes contracts from FileCloud, extracts data, and exports results to multiple formats (CSV, Excel, JSON).

File: /tf/active/vicechatdev/contract_validity_analyzer/extractor.py

main-entry-point contract-extraction data-processing filecloud csv-export

function test_excel_output

A test function that validates Excel output generation for contract analysis results, ensuring new fields (third_party_emails, third_party_tax_ids) are properly formatted and persisted.

File: /tf/active/vicechatdev/contract_validity_analyzer/test_excel_output.py

testing unit-test excel data-validation contract-analysis

class ContractAnalyzer

Main class for analyzing contract validity from FileCloud documents.

File: /tf/active/vicechatdev/contract_validity_analyzer/core/analyzer.py

class contractanalyzer

class LLMClient_v2

Client for interacting with LLM providers (OpenAI, Anthropic, Azure, etc.)

File: /tf/active/vicechatdev/contract_validity_analyzer/utils/llm_client.py

class llmclient

class DocumentConverter_v1

A class that converts various document formats (Word, Excel, PowerPoint, images) to PDF format using LibreOffice, unoconv, or PIL.

File: /tf/active/vicechatdev/document_auditor/src/document_converter.py

document-conversion pdf file-processing office-documents image-to-pdf

function convert_european_decimals

Detects and converts numeric data with European decimal format (comma as decimal separator) to standard format (dot as decimal separator) in a pandas DataFrame, handling mixed formats and missing data patterns.