401 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Convert documents to structured data effortlessly. Unstructured is open-source E... | 5.2M | |
| docTR (Document Text Recognition) - a seamless, high-performing & accessible lib... | 287K | |
| A very simple framework for state-of-the-art Natural Language Processing (NLP) | 171K | |
| This is an open-source version of the representation engineering framework for s... | 167K | |
| The memory for your AI Agents in 6 lines of code | 121K | |
| news-please - an integrated web crawler and information extractor for news that ... | 118K | |
| A Python 3 compatible version of goose http://goose3.readthedocs.io/en/latest/in... | 81K | |
| Customizable and skinnable social platform dedicated to open data. | 76K | |
| OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for s... | 75K | |
| An autonomous agent that conducts deep research on any data using any LLM provid... | 74K | |
| the LLM vulnerability scanner | 73K | |
| 🐢 Open-Source Evaluation & Testing library for LLM Agents | 40K | |
| A fully customisable language detection pipeline for spaCy | 38K | |
| Personal AI agent that runs your life alongside you | 32K | |
| NeMo Retriever Library is a scalable, performance-oriented document content and ... | 31K | |
| Extract what matters from any media source. Available as Python Library, macOS S... | 31K | |
| An Model Context Protocol (MCP) server for AWS SupportAPI. | 26K | |
| Go ahead and axolotl questions | 20K | |
| Pulse Engine — Hybrid framework for building Pulse products | 18K | |
| Free and Open Source Machine Translation API. Self-hosted, offline capable and e... | 15K | |
| A framework for evaluating language models - packaged by NVIDIA | 14K | |
| The robust European language model benchmark. | 13K | |
| 🍊 :page_facing_up: Text Mining add-on for Orange3 | 11K | |
| Un chatbot pour les ludothèques | 11K | |
| INSPIRE-specific rules to transform from MARCXML to JSON and back. | 9K | |
| Primitives for machine learning and data science. | 7K | |
| ktrain is a Python library that makes deep learning and AI more accessible and e... | 7K | |
| 7K | ||
| CLI tool to convert txt file to ebook format | 7K | |
| [NSFW] Useful tools for crawling adult learning resources. | 7K | |
| Hermes is a lightweight, powerful abstraction layer over LlamaIndex that simplif... | 6K | |
| Comprehensive LLM evaluation at scale: A production-ready framework for evaluati... | 6K | |
| test processing | 5K | |
| A library and command line tool for extracting indicators of compromise (IOCs) f... | 5K | |
| The robust European language model benchmark. | 5K | |
| A tool for running on-premises large language models on non-public data | 5K | |
| A short description of the package. | 5K | |
| AI based lecture auto-generation system | 5K | |
| Completely free and open-source human-like Instagram bot. Powered by UIAutomator... | 5K | |
| InPhO Topic Explorer | 5K | |
| A very simple news crawler with a funny name | 5K | |
| AI agent that turns natural language into executable automation workflows. 412 b... | 5K | |
| Prosodic: a metrical-phonological parser, written in Python. For English and Fin... | 4K | |
| A software development kit for climate policy radar software. | 4K | |
| A course management system currently used at DTU | 3K | |
| Document reader with OCR & image detection support. | 3K | |
| CCMM runtime dependencies for NRP Invenio | 3K | |
| Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases | 3K | |
| Common library for MEx python projects. | 3K | |
| :sunrise: next generation web crawling using machine intelligence | 3K |
