7 مستودعات
Settings for managing concurrency, retry logic, and performance tuning during evaluation tasks.
Distinct from Model Parameter Configurations: Distinct from Model Parameter Configurations: focuses on evaluation-specific execution parameters like concurrency and retries rather than model fine-tuning.
Explore 7 awesome GitHub repositories matching artificial intelligence & ml · Execution Parameter Configurators. Refine with filters or upvote what's useful.
Luigi is a Python framework designed for building and managing complex batch data pipelines. It functions as a workflow orchestration engine that organizes tasks into directed acyclic graphs, ensuring that jobs execute in the correct logical order based on their dependencies. By utilizing a centralized scheduler, the system coordinates task execution across distributed environments, tracks global workflow state, and prevents redundant processing by verifying the existence of output targets before triggering any work. The project distinguishes itself through a robust state-tracking mechanism t
Enables configuration of task parameters via command line or external files to override default behaviors.
Ragas is an evaluation framework designed to measure the performance of retrieval-augmented generation pipelines and autonomous agent workflows. It provides a comprehensive suite of tools for benchmarking system outputs, utilizing language models as automated judges to score performance against defined rubrics and reference data. By standardizing inputs, retrieved contexts, and generated responses into a unified schema, the project enables consistent analysis across complex AI applications. The framework distinguishes itself through its ability to generate synthetic test datasets from existin
Adjusts concurrency and retry logic for evaluation tasks to manage performance and reliability.
zvec is an embedded vector database engine and indexing library designed for high-dimensional similarity search. It functions as a hybrid search engine and a retrieval-augmented generation knowledge base, allowing for the storage and retrieval of dense and sparse vectors. The system is distinguished by its hybrid retrieval pipeline, which fuses vector similarity, full-text keyword matching, and scalar metadata filtering into single query operations. It supports a plugin-based model integration system for registering custom embedding models and rerankers, as well as language bindings for nativ
Sets global logging and concurrency levels during startup to optimize runtime performance and observability.
Empire is a post-exploitation command-and-control (C2) framework designed for red team operations. It deploys and manages agents written in PowerShell, Python, C#, Go, and C across Windows, Linux, and macOS, using encrypted communication channels over HTTP, HTTPS, and SMB. The framework executes over 400 built-in modules for reconnaissance, privilege escalation, credential theft, and lateral movement, and provides a modular engine for authoring custom attack modules. What sets Empire apart is its multi-language agent deployment system, which allows operators to choose implants that suit each
Configures module parameters, selects language, reviews security notes, and chooses execution mode.
Kùzu is an embedded property graph database engine designed for high-performance analytical queries and local data management. It operates as a library within the host application process, utilizing a columnar-based storage architecture and just-in-time query compilation to execute complex graph traversals and pattern matching efficiently. By mapping database files directly into system memory, it ensures data durability and high-speed access while maintaining ACID-compliant transactional integrity. The engine distinguishes itself by integrating vector similarity search and full-text search di
Adjusts system-level settings to optimize performance for specific workloads.
تعمل هذه الأداة كخادم لبروتوكول سياق النموذج (Model Context Protocol) الذي يربط نماذج الذكاء الاصطناعي ببيئات التطوير المحلية. فهي تمكن مساعدي الذكاء الاصطناعي من إجراء تحليل لقاعدة الكود، وتنفيذ أدوات سطر الأوامر، وتطبيق تعديلات برمجية مؤتمتة مباشرة على ملفات المشروع المحلية. ومن خلال التكامل مع Gemini API، يسهل النظام التفاعل العميق بين النماذج الخارجية وموارد النظام المحلي. يتميز المشروع بإطار عمل قوي للأمان والموثوقية مصمم لسير عمل التطوير المؤتمت. فهو يفرض ضوابط وصول صارمة تعتمد على المسارات لحماية الملفات الحساسة، ويستخدم بيئات معزولة (sandbox) لتنفيذ الكود المولد. ولضمان التشغيل المستمر، تطبق الأداة توجيهاً ديناميكياً للنماذج (fallback routing)، والذي يقوم بالتبديل تلقائياً بين مستويات النماذج إذا تم الوصول إلى حدود الاستخدام، كما يستخدم تقييم نموذج ثانوي للتحقق من جودة المخرجات المولدة. يدعم النظام مجموعة واسعة من العمليات التقنية، بما في ذلك استخراج البيانات المهيكلة من مخرجات الطرفية، وإدارة سجل المحادثات، وتهيئة معلمات التنفيذ للمهام طويلة الأمد. كما يوفر قدرات شاملة لمسح أدلة المشروع، وتوليد رؤى تقنية، وإدارة نوافذ السياق للتعامل مع التوثيق المكثف ومعلومات قاعدة الكود.
Provides configurable runtime settings for timeouts and output handling to support long-running AI development tasks.
This project serves as a curated directory and resource hub for developers working with generative artificial intelligence. It provides a comprehensive index of open-source software solutions, frameworks, and project examples designed to help users discover and implement advanced AI systems. The repository focuses on practical implementations of agentic, multimodal, and retrieval-augmented generation architectures. It highlights tools for building conversational assistants, voice-enabled agents, and automated workflows that leverage large language models. By showcasing diverse technical domai
Manages concurrency, retry logic, and performance tuning during evaluation tasks.