AI-powered CLI that analyzes websites and generates real Playwright web scrapers with built-in data quality checks
Python SDK for WildEdge
Android SDK for WildEdge
A multi-source data pipeline that ingests candidate profiles from structured, semi-structured, and unstructured sources. Resolves identities using an O(N) Union-Find algorithm, performs confidence-based consensus merging with full provenance tracking, and dynamically projects outputs via Pydantic.
LLM-powered restaurant CRUD — IBM Granite 3 8B extracts structured JSON from text paragraphs with auto-repair loop, CLI menu, auto-backup & unittest coverage with mocked inputs
Add a description, image, and links to the llm-data-extraction topic page so that developers can more easily learn about it.
To associate your repository with the llm-data-extraction topic, visit your repo's landing page and select "manage topics."