← Latest products

Smelt

Extract structured data from PDFs and HTML using LLM. I built a CLI tool in Go that extracts structured data (JSON, CSV, Parquet) from messy PDFs and HTML pages.

Open source

10 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. LLM Scraper

    github.com

    turn any webpage into structured data

    Hacker News88 pts

  2. xmllm

    github.com

    Structured LLM streaming output using lenient XML parsing

    Hacker News5 pts

  3. A lightweight LLM proxy to get structured results from most LLMs

    l1m.io

    After struggling with complex prompt engineering and unreliable parsing, we built L1M, a simple API that lets you extract structured data from unstructured text and images.

    Hacker News13 pts

  4. Extrai

    github.com

    An open-source tool to fight LLM randomness in data extraction

    Hacker News5 pts

  5. Docuglean

    github.com

    Extract Structured Data from PDFs/Images Using AI

    Hacker News5 pts