🔍 Code Extractor

Browse Components

• class LanguageDetector

  A language detection class that identifies whether invoice documents are written in English, French, or Dutch using both rule-based keyword matching and LLM-based detection.

  File: /tf/active/vicechatdev/invoice_extraction/core/language_detector.py | Lines: 10-236

  language-detection nlp invoice-processing text-analysis multilingual

• class DocumentProcessor_v3

  A comprehensive PDF document processor that handles text extraction, OCR (Optical Character Recognition), layout analysis, table detection, and metadata extraction from PDF files.

  File: /tf/active/vicechatdev/invoice_extraction/core/document_processor.py | Lines: 12-451

  pdf-processing ocr text-extraction document-processing invoice-processing

• class DocumentProcessor_v8

  Process different document types for indexing

  File: /tf/active/vicechatdev/docchat/document_indexer.py | Lines: 230-787

  class documentprocessor

• class DocumentProcessor_v7

  Lightweight document processor for chat upload functionality

  File: /tf/active/vicechatdev/vice_ai/document_processor.py | Lines: 97-1028

  class documentprocessor

• class DocumentProcessor_v6

  Process different document types for RAG context extraction

  File: /tf/active/vicechatdev/offline_docstore_multi.py | Lines: 189-1177

  class documentprocessor

• class DocumentProcessor_v5

  Process different document types for RAG context extraction

  File: /tf/active/vicechatdev/offline_docstore_multi_vice.py | Lines: 197-1216

  class documentprocessor

• class DocumentProcessor_v4

  Handles document processing and text extraction using llmsherpa (same approach as offline_docstore_multi_vice.py).

  File: /tf/active/vicechatdev/docchat/document_processor.py | Lines: 44-611

  class documentprocessor

• class InvoiceProcessor

  Main orchestrator class that coordinates the complete invoice processing pipeline from PDF extraction through validation to Excel generation.

  File: /tf/active/vicechatdev/invoice_extraction/main.py | Lines: 36-189

  invoice-processing document-processing pdf-extraction entity-classification language-detection

• function load_config

  Loads configuration from multiple fallback locations, returning a Config instance with application settings.

  File: /tf/active/vicechatdev/invoice_extraction/config.py | Lines: 350-390

  configuration config-loading file-io environment-variables yaml

• function load_config_v1

  Loads configuration settings from a file by instantiating and returning a Config object with the specified configuration file path.

  File: /tf/active/vicechatdev/contract_validity_analyzer/config/config.py | Lines: 120-130

  configuration config-loading file-io settings initialization

• class Config_v5

  A hierarchical configuration manager that loads and manages settings from multiple sources (defaults, files, environment variables) with support for nested structures and dynamic updates.

  File: /tf/active/vicechatdev/invoice_extraction/config.py | Lines: 10-347

  configuration settings config-management yaml json

• class Config_v6

  A dataclass that stores configuration settings for a ChromaDB cleanup process, including connection parameters, cleaning/clustering options, and summarization settings.

  File: /tf/active/vicechatdev/chromadb-cleanup/src/config.py | Lines: 6-33

  configuration dataclass chromadb settings cleanup

• function setup_logging_v1

  Configures and initializes Python's logging system with customizable log level and output destination (console or file).

  File: /tf/active/vicechatdev/QA_updater/utils/logging_utils.py | Lines: 5-32

  logging configuration setup initialization file-handling

• function setup_logging_v4

  Configures Python's logging system for testing purposes with both console and file output.

  File: /tf/active/vicechatdev/contract_validity_analyzer/test_implementation.py | Lines: 23-32

  logging testing configuration setup file-logging

• function setup_logging_v3

  Configures Python's logging system with both console and file output, creating a timestamped log file for real document testing sessions.

  File: /tf/active/vicechatdev/contract_validity_analyzer/test_real_documents.py | Lines: 23-35

  logging configuration debugging file-output testing

• function setup_logging_v2

  Configures Python's logging system with console and rotating file handlers, creating necessary directories and setting appropriate log levels for the application and third-party libraries.

  File: /tf/active/vicechatdev/email-forwarder/src/utils/logger.py | Lines: 17-58

  logging configuration initialization file-rotation console-output

• class GoogleSearchClient

  A client class for performing Google searches using the Serper API through LangChain's GoogleSerperAPIWrapper, providing both single and batch search capabilities.

  File: /tf/active/vicechatdev/QA_updater/data_access/google_search_client.py | Lines: 7-85

  google-search serper-api web-search langchain api-client

• class ClinicalTrialsClient

  A client class for searching and retrieving clinical trial data from multiple international sources including ClinicalTrials.gov, EU Clinical Trials Register, WHO ICTRP, and OpenTrials.

  File: /tf/active/vicechatdev/QA_updater/data_access/clinical_trials_client.py | Lines: 12-432

  clinical-trials medical-research api-client data-aggregation rate-limiting

• class DocumentDownloader

  A client class for downloading documents (primarily PDFs) from various sources, managing download caching, respecting rate limits per domain, and processing documents using llmsherpa for content extraction.

  File: /tf/active/vicechatdev/QA_updater/data_access/document_downloader.py | Lines: 14-312

  document-download pdf-processing rate-limiting caching llmsherpa

• class CompanyNewsClient

  A client class for accessing company news and information from multiple sources including GDELT Project and NewsAPI, with built-in rate limiting and error handling.

  File: /tf/active/vicechatdev/QA_updater/data_access/company_news_client.py | Lines: 16-219

  news-api gdelt news-aggregation company-news rate-limiting