Agent frameworks & SDKs
unstructured
Unstructured-IO/unstructured
An open-source ETL library that partitions PDFs and other documents into clean, structured chunks ready for LLMs and RAG pipelines.
Topics
Related projects
EasyOCR30.1kA ready-to-use Python OCR library supporting 80+ languages across Latin, Chinese, Arabic, and Cyrillic scripts.
handson-ml25.6kExample notebooks and exercise solutions accompanying a hands-on machine learning book.
ML-NLP17.8kA curated Chinese study collection of ML and NLP interview notes with code examples.
MNN16.4kA blazing-fast lightweight inference engine from Alibaba for on-device LLMs and edge AI deployment.
sie3.5kA self-hosted inference server and production cluster that serves 100+ open models behind one OpenAI-compatible API, covering embeddings, reranking, OCR, classification, and generation for agent workloads.
PaddleOCR92.4kA developer OCR and document-parsing toolkit that turns PDFs and images into LLM-ready structured data.