3 repositorios
Representations of codebase structure as interconnected nodes for deep architectural reasoning.
Distinct from Codebase Knowledge Sources: Distinct from general codebase knowledge sources by specifically implementing a knowledge graph for impact analysis.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Knowledge Graphs. Refine with filters or upvote what's useful.
scrape-it is a Node.js web scraper and HTML parser designed to extract structured data from websites and HTML files. It functions as a web data extraction tool that retrieves specific information from DOM elements and converts web content into usable data fields. The tool uses CSS selectors to target specific data points and employs schema-driven data mapping to organize unstructured web text into a consistent format. It supports custom value transformation to convert raw extracted strings into specific data formats. The system provides capabilities for web data extraction and automated cont
Maps CSS selectors to predefined output fields to ensure structured and consistent data extraction.
s2client-proto provides a set of structured data definitions and language-neutral communication protocols used to exchange information between an external client and the StarCraft II engine. It utilizes protocol buffer definitions to establish a binary serialization schema for these data exchanges. The project defines the underlying communication layer necessary for game engine automation, game state analysis, and the development of software agents for competitive gaming. The framework covers interface definition languages to ensure compatibility across programming languages and employs sche
Translates raw game state identifiers into human-readable names using predefined mapping files.
Entity-Relation-Extraction es un framework de machine learning diseñado para identificar entidades y sus conexiones lógicas dentro de texto no estructurado. Funciona como una tubería (pipeline) que transforma documentos crudos en grafos de conocimiento estructurados utilizando modelos de deep learning y arquitecturas transformer. El proyecto se distingue por un enfoque basado en esquemas, que mapea la información extraída a plantillas relacionales predefinidas para asegurar la consistencia de la salida. Emplea un proceso de varias etapas que combina la clasificación de tokens de etiquetado de secuencias con codificación contextual para delinear los límites de las entidades y clasificar las relaciones entre ellas. El kit de herramientas proporciona componentes para ajustar (fine-tuning) modelos de lenguaje preentrenados y orquestar datos a través de grafos computacionales. Incluye utilidades para evaluar el rendimiento del modelo frente a conjuntos de datos de referencia (ground truth) para verificar la precisión del proceso de extracción.
Structures extracted data according to predefined relational templates to ensure output conforms to specific domain requirements.