Browse categories
Explore
Fiverr Pro
English
$
USD
I will extract data from pdfs and documents into excel, CSV or json
AI Engineer for LLM agents, private LLMs and Python backends
I build LLM systems that run in production: agents with tool calling, RAG over your own documents, and self-hosted open-weight models (llama.cpp, sglang) so sensitive data stays on your own servers. R...
About this Gig
Got data stuck in PDFs, scans or Word files? I'll turn it into a clean Excel, CSV or JSON file, and hand you the Python script so you can run it again next month.
What I can extract:
- invoices, receipts and statements
- tables in reports, price lists and catalogs
- forms and contracts (dates, parties, amounts)
- scanned documents (OCR), in English and German
Send me a sample first, and I'll confirm which fields I can extract reliably before you order. Where layouts vary I combine Python with an LLM and check totals and formats, so the numbers are verified, not guessed.
About me: MSc in actuarial mathematics, 9 years building software for insurers and banks, including extracting structured data from PDF tables. Your files are deleted after delivery.
Technology:
Excel
•
Python
FAQ
Can you handle scanned or handwritten documents?
Scanned documents yes, via OCR. Handwriting only if it is clearly legible. Send me a sample and I'll tell you before you order.
What do you need from me?
A few sample files and a list of the fields or columns you want. If you have an example of the finished spreadsheet, even better.
Is my data safe?
Your files are processed on my own machine and are not sent to third-party AI services unless you agree. They are deleted after delivery.
Can I rerun the extraction myself later?
Yes. The Standard and Premium packages include the Python script with instructions, so you can process new files of the same type yourself.
