Table of Contents

Generative AI Classification System:

AI package

Prompts used in the AI system:

Prompt Templates

Langchain wrapper for quickly building LLM chains:

ChainBuilder package

Core data processing and formatting:

core package

Logging configuration and constants:

Global Configuration

Constants used for directory paths and execution time:

constants package

Crossref API and Scraping:

data_collection package

Data class models used throughout the system:

dataclass_models package

Class for interacting with the database:

DB package

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

enums package

Factory classes for creating objects:

factories package

Orchestrator classes for AI system and data processing:

orchestrators package

Taxonomy string representation:

other package

Duplicate detection and removal:

postprocessing package

Runner classes for executing the entire pipeline:

runners package

Strategy classes:

strategies package

Utility classes and functions:

utils package

constants package#

Submodules#

constants.dir_paths module#

constants.dir_paths.get_package_data_dir()[source]#

Get the appropriate data directory for the package based on platform.

Return type:: Path

constants.dir_paths.locate_academic_metrics_root(marker='COSC425-DATA')[source]#

Find the repository root directory.

Parameters:: marker (str | None) – Marker string to search for in the directory hierarchy. Defaults to “COSC425-DATA”.
Return type:: Path

constants.dir_paths.locate_src_root(repo_root=None)[source]#

Find the source code root directory (PythonCode).

Parameters:: repo_root (Path | None) – Repository root directory. Defaults to None.
Return type:: Path

Module contents#