Show HN: LLM-powered data extraction from messy spreadsheets

https://github.com/mehdigmira/tablereader
by mehdig10 • 7 months ago
1 0 7 months ago

Uses an LLM to identify where tables actually start/end in Excel/CSV files, then extracts clean, typed data.

Handles all the messy formatting (currency, percentages, different number formats) and streams efficiently for large files.

Works with OpenAI, DeepSeek, or any compatible API.

Related Stories

Loading related stories...

Source preview

github.com