Repository History
238 repositories tagged with Python
llama-cpp-python: Python Bindings for llama.cpp
llama-cpp-python provides robust Python bindings for the popular llama.cpp library, enabling efficient local inference with large language models. It offers a high-level API compatible with OpenAI's API, facilitating easy integration into existing applications. The project also includes a powerful web server for local deployment and supports various hardware acceleration backends.
FuncVul: Function-Level Vulnerability Detection with LLMs and Code Chunks
FuncVul is an innovative model designed to detect vulnerabilities at the function level in C/C++ and Python code, addressing a critical gap in software supply chain security. By leveraging large language models (LLMs) and a code chunk-based approach, FuncVul significantly improves the precision of vulnerability identification. The model demonstrates superior performance compared to existing state-of-the-art methods, achieving high accuracy and F1 scores across various datasets.
Podcastfy: Transform Multimodal Content into AI-Generated Multilingual Podcasts
Podcastfy is an open-source Python package that transforms diverse multimodal content, such as text, images, and videos, into engaging multilingual audio conversations. Utilizing generative AI, it offers a flexible and programmatic alternative to tools like NotebookLM, focusing on customization and scalability. This makes it an excellent solution for content creators, educators, and researchers aiming to broaden their audience reach and improve content accessibility.
Marker: High-Accuracy Document Conversion to Markdown and JSON
Marker is an open-source Python tool designed for high-accuracy conversion of documents like PDFs, images, and office files into Markdown, JSON, and HTML. It excels at preserving complex formatting, extracting images, and can leverage LLMs for even greater precision. This makes Marker a powerful solution for structured document intelligence.
Instructor: Structured Outputs for LLMs with Pydantic and Python
Instructor is a powerful Python library designed to simplify obtaining structured outputs from Large Language Models (LLMs). By leveraging Pydantic, it provides robust validation, type safety, and IDE support, eliminating the need for manual JSON parsing, error handling, or retries. This tool streamlines the process of extracting reliable, structured data from any LLM provider.
python-readability: Extract Clean Main Content from HTML Documents
python-readability is a fast Python port of arc90's Readability tool, designed to extract and clean the main body text and title from any given HTML document. It provides an efficient way to process web content, making it easier to focus on essential information. This library is regularly updated to match the latest readability.js functionalities, ensuring modern compatibility and performance.
handit.ai: Your AI Teammate for Reliable Production AI
handit.ai is an open-source AI teammate designed to ensure the reliability of your AI applications in production. It automatically detects issues like hallucinations and schema breaks, generates and tests fixes, and ships them as pull requests. This tool eliminates 2 AM debugging sessions, making AI truly dependable.
FlashVideo: Efficient High-Resolution Video Generation with Flowing Fidelity
FlashVideo is an innovative GitHub repository that introduces a novel approach for efficient high-resolution video generation. It leverages a two-stage diffusion model to produce detailed videos, scaling from 270p to 1080p. This project focuses on maintaining fidelity to detail while significantly improving the efficiency of the video generation process.
Stream-Framework: Build Scalable News Feeds and Activity Streams in Python
Stream-Framework is a powerful Python library designed for building robust news feeds, activity streams, and notification systems. It leverages Cassandra and/or Redis for high performance and scalability, making it ideal for applications requiring real-time feed capabilities. The library provides asynchronous tasks and reusable components, simplifying the development of complex feed-based systems.
Text Generation Inference: High-Performance LLM Serving by Hugging Face
Text Generation Inference (TGI) is a robust toolkit from Hugging Face designed for deploying and serving Large Language Models (LLMs) with high performance. It powers Hugging Face's production services, including Hugging Chat and their Inference API. TGI offers optimized text generation, supporting popular open-source LLMs and implementing advanced features for efficient and scalable inference.
Argus: The Ultimate Python Toolkit for Information Gathering and Reconnaissance
Argus is a powerful, Python-based toolkit designed for comprehensive information gathering and reconnaissance. It features an intuitive command-line interface and over 130 modules for in-depth analysis of networks, web applications, and security configurations. This tool empowers users to efficiently explore target systems, providing valuable insights for educational and ethical security assessments.
3b1b/videos: Exploring the Code Behind 3Blue1Brown's Math Animations
The 3b1b/videos repository hosts the Python code used to generate the captivating mathematical animations featured in 3Blue1Brown's educational videos. Primarily utilizing the Manim library, this project offers a unique insight into the creation process of complex visual explanations. It serves as an invaluable resource for those interested in mathematical visualization and the Manim animation engine.