📃🤖 AI-powered document extraction system with custom schema generation, visual grounding, OCR processing, and structured data extraction.
-
Updated
Jan 14, 2026 - TypeScript
#
ai-extraction
Here are 7 public repositories matching this topic...
BlockData decomposes documents into blocks, applies user-defined schemas with parallel AI processing, and exports structured outputs for downstream pipelines.
json knowledge-graph structured-data block-processing observability json-db jsonl vector-search edge-functions immutable-data supabase document-intelligence schema-driven ai-extraction huge-corpora document-reconstruction
-
Updated
Mar 3, 2026 - TypeScript
ai powered structured extraction
scraper extract schema-generation structured structured-data-extraction bun-runtime playwright-automation ai-extraction llm-parsing intelligent-web-scraping
-
Updated
Dec 4, 2025
This repository provides practical examples of website link scraping using Python and Node.js.
nodejs python crawler web-scraping web-crawling sitemap-parser url-extraction ai-extraction hasdata-api
-
Updated
May 19, 2025 - JavaScript
AI website data extraction tool
scraper typescript ai universal web-scraping structured-data gpt content-parser crawlee ai-extraction
-
Updated
Dec 7, 2025
Lightweight job application tracker with Supabase files + Gemini AI extract (diff + selective apply). Deployed on Netlify.
productivity nextjs postgresql job-tracker tailwindcss job-applications supabase supabase-storage gemini-ai ai-extraction
-
Updated
Jan 29, 2026 - TypeScript
API OCR (Optical Character Recognition) berbasis Gemini AI dari Google, dengan output rapi berupa JSON terstruktur.
json ocr serverless document-parser gemini-api cloudflare-workers pdf-ocr google-generative-ai image-to-json ai-extraction
-
Updated
Aug 13, 2025 - HTML
Improve this page
Add a description, image, and links to the ai-extraction topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the ai-extraction topic, visit your repo's landing page and select "manage topics."