AIPython★ 1,524
emcf/thepipe
THEPIPE: DATA FROM DOCUMENTS FAST
ThePipe uses vision‑language models to extract data from PDF, Word and PowerPoint. It recognises tables, text and images, turning them into ready‑to‑use structures. Supports batch API.
// KEY FEATURES
- Extracts tables and text from scanned PDF with >95% accuracy via VLM.
- Converts complex Word documents to structured JSON, preserving styles and metadata.
- Processes batches of PowerPoint files, extracting text from slides and image captions.
- Provides REST API and Python SDK for integration into ETL and RAG pipelines.
#document-ai#large-language-models#microsoft-word#multimodal#pdf#powerpoint#python#scanned-pdf#scrapers#scraping#unstructured-data#vision-language-model
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram