14 repositorios
Using large language models to perform complex text transformations like translation and summarization.
Distinct from Text Summarization: Unlike specific tasks like summarization, this covers the architectural use of LLMs for multiple text processing types.
Explore 14 awesome GitHub repositories matching artificial intelligence & ml · LLM-Based Text Processing. Refine with filters or upvote what's useful.
openai-translator is a cross-platform translation tool and language learning utility available as a browser extension and desktop application. It functions as a client for large language model APIs to translate, summarize, and polish text across different digital environments. The project differentiates itself by integrating optical character recognition to translate text extracted from images and screenshots. It also includes a language learning workflow that allows users to save new vocabulary to a digital book and use text-to-speech synthesis for pronunciation. The tool provides broad tex
Implements the core engine for translation, summarization, and polishing using large language model APIs.
Nextai-translator is an AI-powered text processor and cross-platform translation application. Available as a desktop app and browser extension, it uses large language model APIs to translate, summarize, and refine multilingual content in real time. The tool integrates with clipboard managers and text selection utilities to trigger automated translations immediately after content is copied or highlighted. It also functions as an OCR translation utility, extracting and translating text from screenshots and non-selectable image content. Additional capabilities include a vocabulary management sy
Uses large language models to perform context-aware text transformations including translation and summarization.
ChatPaper is a suite of AI agents and utilities designed for academic literature automation, manuscript editing, and research assistance. The system functions as a research assistant that summarizes, translates, and analyzes scholarly papers, while providing specialized tools for converting academic PDFs into structured markdown to preserve formulas for analysis. The project features a literature survey automator that crawls research repositories and synthesizes domain reports, alongside a research mind map generator that transforms linear document content into non-linear node-based maps. It
Pipes extracted text from academic papers into LLMs for summarization, translation, and critical analysis.
anx-reader is a cross-platform e-book reader and cloud-synced library manager. It renders various electronic book formats into a standardized HTML view with customizable themes and fonts for a consistent experience across different operating systems. The project integrates a large language model as a reading assistant to summarize text and answer questions about book content. It also functions as a digital annotation tool for creating color-coded highlights and detailed notes for external research export. The system includes capabilities for organizing digital library collections, synchroniz
Integrates large language models to perform text processing tasks such as summarization and content analysis.
This project is a long context inference engine and optimizer designed to process infinite text streams using large language models without memory growth or performance degradation. It serves as a system for maintaining constant memory usage during the generation of text from arbitrarily long input sequences. The implementation utilizes a rolling key-value cache manager and attention sink mechanisms to stabilize the attention process during continuous stream processing. By retaining initial tokens and employing a sliding window of key-value pairs, the system enables constant-time inference an
Uses large language models to process and maintain context over massive volumes of text.
Bili.Copilot es un cliente de escritorio nativo para Windows para Bilibili que integra modelos de lenguaje grandes para proporcionar navegación multimedia mejorada por IA y resumen de video. Funciona como un navegador de medios y resumidor de video, permitiendo a los usuarios generar resúmenes concisos de videos y artículos mediante el procesamiento de subtítulos y texto. La aplicación permite a los usuarios interactuar con modelos de IA para consultar información específica y evaluar contenido dentro de los videos. Estas capacidades se entregan a través de una interfaz nativa de Windows construida con el SDK de aplicaciones de Windows y WinUI. El software cubre la gestión de medios y el consumo de contenido, incluyendo la descarga de videos para visualización sin conexión y renderizado de reproducción integrado. También gestiona la identidad del usuario mediante autenticación basada en QR y métodos de inicio de sesión basados en web.
Integrates large language models for complex text processing of subtitles and content.
Sparrow es una plataforma de extracción de documentos basada en LLM y un motor de inferencia visual diseñado para convertir imágenes y PDFs en datos estructurados validados. Funciona como un orquestador de flujos de trabajo agenticos que encadena tareas de clasificación, extracción y validación en pipelines de múltiples pasos. El sistema se distingue por una capa de inferencia agnóstica al backend que gestiona modelos en GPUs locales, Apple Silicon y proveedores en la nube. Emplea grounding visual basado en coordenadas para mapear el texto extraído a coordenadas precisas de cuadros delimitadores y utiliza dirección de modelos basada en pistas para guiar la atención y normalizar formatos de datos. La plataforma cubre flujos de trabajo de inteligencia documental, incluyendo procesamiento especializado de tablas basadas en imágenes para mantener la integridad estructural y validación basada en esquemas para verificar la exactitud de los campos extraídos. También proporciona un panel de análisis documental para monitorear el rendimiento de la API, analíticas de uso y el estado del sistema. La arquitectura incluye un sistema de extensión basado en plugins para integrar librerías de terceros utilizadas en indexación y orquestación.
Executes text-based analysis, validation, and decision-making tasks using an inference API without document input.
Humanizer is a text processing system designed to remove machine-generated patterns from writing to make it sound more natural and conversational. It functions as an auditor and rewriter that identifies robotic signatures, formulaic tropes, and mechanical formatting in machine output. The project features a style-matching system that analyzes provided writing samples to replicate a user's specific sentence rhythms, vocabulary, and punctuation habits. This allows the tool to mirror a personal voice and apply a calibrated tone to the rewritten text. The system covers a broad range of linguisti
Removes machine patterns from LLM output to make AI-generated text sound more natural and conversational.
RedInk is an AI content automation tool designed to generate coordinated social media posts, including titles, body text, and matching visual assets, from a single user-provided topic. It functions as a stateless content pipeline that uses large language models to transform topics into structured marketing copy and image prompts. The system utilizes prompt-template orchestration to combine static instructions with dynamic inputs, guiding artificial intelligence toward specific output formats. Users can manage these AI behaviors and API preferences through a web-based settings interface that t
Implements a pipeline using large language models to transform topics into structured marketing text and image prompts.
CapsWriter-Offline is a suite of desktop tools that operates without an internet connection, combining local media browsing, voice dictation, audio and video transcription, and 360-degree media viewing into a single application. The project's core identity centers on providing offline functionality for both media handling and speech-to-text workflows. What distinguishes it is the integration of voice dictation with a persistent local storage layer that saves every audio recording and daily transcript logs, along with a rule-based text normalization engine that converts spoken number phrases a
Routes recognized speech to a language model for role-specific polishing based on predefined names.
Novel-Plus es un sistema de gestión de contenido y plataforma de lectura online diseñada para alojar, gestionar y distribuir novelas web a través de interfaces web de PC y móviles. Proporciona un entorno integral para la publicación de novelas web, contando con un lector multiplataforma con estanterías, temas personalizables y sistemas de comentarios comunitarios. La plataforma integra un crawler de contenido automatizado para recopilar y actualizar datos literarios desde fuentes remotas externas y emplea un sistema de almacenamiento de texto escalable utilizando fragmentación de base de datos (sharding) y archivos planos para manejar grandes volúmenes de contenido. También incluye un asistente de escritura integrado que utiliza modelos de lenguaje grandes para ayudar a los autores a expandir, pulir y continuar su texto, junto con capacidades de IA para generar arte de portada para novelas. El sistema cubre la monetización de contenido digital mediante una plataforma de membresía y facturación para gestionar suscripciones pagas y pagos a autores. Las capacidades adicionales incluyen gestión de contenido literario con búsqueda por palabras clave y motores de recomendación, analítica de rendimiento en tiempo real y herramientas administrativas para operaciones de plataforma y moderación de contenido.
Uses large language models to perform complex text transformations including expansion and polishing within the editor.
Este proyecto es un scraper web de Sina Weibo y una tubería de datos de redes sociales diseñada para extraer perfiles de usuario, publicaciones, comentarios y activos multimedia. Funciona como un crawler de datos contenedorizado que automatiza la recopilación y el almacenamiento local de contenido de redes sociales y métricas de interacción. El sistema incluye una capa de procesamiento que utiliza modelos de lenguaje de gran tamaño (LLM) para analizar el texto extraído, generando resúmenes y análisis de sentimiento. Se diferencia por un modelo de contenedor listo para el despliegue que cuenta con una interfaz HTTP para gestionar tareas de extracción y monitorear el progreso de los trabajos. El crawler cubre una amplia gama de capacidades, incluyendo el monitoreo de redes sociales mediante actualizaciones incrementales programadas, el archivo de activos multimedia en discos locales y la exportación de datos en múltiples formatos a archivos planos o bases de datos. También captura interacciones sociales detalladas, como comentarios de primer nivel y republicaciones.
Utilizes large language models to perform text transformations such as summarization and sentiment analysis.
This repository is a collection of node-based pipeline configurations, examples, and templates for generating AI media. It provides a workflow library and a curated gallery of blueprints designed for creating images, videos, and 3D assets using diffusion models. The project specifically offers a set of pre-configured node graphs for implementing advanced image generation and refinement techniques, with a focus on Stable Diffusion workflows. These examples demonstrate how to interconnect processing nodes to define complex generative logic without writing code. The available templates cover a
Utilizes external large language models to perform text-based chat and analysis.
Humanizer-zh is a tool designed to transform AI-generated content into natural-sounding writing by removing repetitive patterns and mechanical formatting. It functions as an AI content de-optimizer and text humanizer specifically focused on making Chinese text sound more human-authored. The project specializes in Chinese language refinement, replacing corporate jargon and artificial linguistic markers with native expressions and varied sentence rhythms. It employs a system to strip formulaic signatures and repetitive structures common in large language model outputs to increase perceived auth
Specializes in removing machine patterns and introducing conversational fluency to humanize AI text.