Unstructured's repositories
unstructured
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.
pipeline-sec-filings
Preprocessing pipeline notebooks and API supporting text extraction from SEC documents
unstructured-python-client
A Python client for the Unstructured Platform API
unstructured-js-client
A JavaScript/Typescript client for the Unstructured Platform API
unstructured.PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
pipeline-paddleocr
Pipeline for converting PDFs to raw text with PaddleOCR
pipeline-oer
Pipeline for extraction information from Army OERs
base-images
Store Dockerfiles and Packer configs for images to use as a base to build upon
unstructured.pytesseract
A Python wrapper for Google Tesseract
azure-ai-hub-gateway-solution-accelerator
Reference architecture that provides a set of guidelines and best practices for implementing a central AI API gateway to empower various line-of-business units in an organization to leverage Azure AI services
model-cards
FedRAMP formatted model cards
rag-over-hybrid-data-sources
Two sources (S3, ElasticSearch) to RAG DB pipeline.
js-client-batch
JS Client Batch Processing
aws-blog-post-example
Script to accompany the AWS blog post on unstructured data ETL with Unstructured Ingest library
pairing-technical-challenge
Pairing Technical Challenge
wolfi-dev-os
Main package repository for production Wolfi images