Academic Metrics Documentation

AI System

Generative AI Classification System:

• AI package
  • Submodules
  • AI.abstract_classifier module
  • Module contents

Prompts

Prompts used in the AI system:

• Prompt Templates
  • Pre-classification prompts
  • Classification Prompts
  • Human Prompts
  • Theme Recognition

ChainBuilder

Langchain wrapper for quickly building LLM chains:

• ChainBuilder package
  • Submodules
  • ChainBuilder.ChainBuilder module
  • Module contents

Core

Core data processing and formatting:

• core package
  • Submodules
  • core.category_processor module
  • Module contents

Configuration

Logging configuration and constants:

• Global Configuration
  • Overview
  • Module Constants
  • Classes
  • Functions

Constants

Constants used for directory paths and execution time:

• constants package
  • Submodules
  • constants.dir_paths module
  • Module contents

Data Collection

Crossref API and Scraping:

• data_collection package
  • Submodules
  • data_collection.CrossrefWrapper module
  • data_collection.scraper module
  • Module contents

Data Classes

Data class models used throughout the system:

• dataclass_models package
  • Submodules
  • dataclass_models.abstract_base_dataclass module
  • dataclass_models.concrete_dataclasses module
  • Module contents

Database

Class for interacting with the database:

• DB package
  • Submodules
  • DB.DatabaseSetup module
  • Module contents

Enums

Enums used for type safety in factory/decorator/strategy patterns:

• enums package
  • Submodules
  • enums.dataclass_enums module
  • enums.enums module
  • Module contents

Factories

Factory classes for creating objects:

• factories package
  • Submodules
  • factories.abstract_classifier_factory module
  • factories.dataclass_factory module
  • factories.strategy_factory module
  • Module contents

Orchestrators

Orchestrator classes for AI system and data processing:

• orchestrators package
  • Submodules
  • orchestrators.category_data_orchestrator module
  • orchestrators.classification_orchestrator module
  • Module contents

Other

Taxonomy string representation:

• other package
  • Submodules
  • other.in_memory_taxonomy module

Postprocessing

Duplicate detection and removal:

• postprocessing package
  • Submodules
  • postprocessing.BasePostprocessor module
  • postprocessing.DepartmentPostprocessor module
  • postprocessing.FacultyPostprocessor module
  • Module contents

Runners

Runner classes for executing the entire pipeline:

• runners package
  • Submodules
  • runners.pipeline module
  • Module contents

Strategies

Strategy classes:

• strategies package
  • Submodules
  • strategies.AttributeExtractionStrategies module
  • Module contents

Utils

Utility classes and functions:

• utils package
  • Submodules
  • utils.api_key_validator module
  • utils.minhash_util module
  • utils.taxonomy_util module
  • utils.unicode_chars_dict module
  • utils.utilities module
  • utils.warning_manager module
  • Module contents

Indices and tables

• Index

• Module Index

• Search Page