Show HN: Open-source tool for converting docs into .md and loading into Postgres

https://github.com/pgEdge/pgedge-docloader
by pgedge_postgres • 6 months ago
4 0 6 months ago

pgedge-docloader is an open-source tool for converting documents into Markdown, and loading them into PostgreSQL with extracted metadata.

Our docloader strips out unimportant content such as additional markup and image tags so that chunking can be as efficient as possible. This helps avoid unnecessary token usage when developing with AI, and also maximizes efficiency of the searches.

Convert from HTML, Markdown, reStructuredText, and SGML/DocBook.

Related Stories

Loading related stories...

Source preview

github.com