Skip to content

Open Source AI & Browser Automation

Enterprise Data Pipeline: Browser-Use

When
Jan – Feb 2026
Length
4 days
Status
Completed

Python pipeline that extracts text from PDFs, spreadsheets and scanned images and runs natural-language browser tasks with Browser-Use, Gemini or Ollama.

Where it sits

EarlierRalphJan 2026LaterResQ Developer PlatformFeb 2026

The project

The Enterprise Data Pipeline is a Python project for processing local documents with AI models.

It can watch a folder or process a chosen file, extracting text from JSON, CSV, PDF and Excel alongside plain-text formats. Scanned PDFs can fall back to OCR. YAML workflows organize model-based analysis steps, while a separate command uses Browser-Use to inspect and fill a web form from extracted data. Gemini and Ollama are available for text generation; the form-filling path uses Gemini. Outputs are saved as Markdown, with a dashboard for processing history and metrics and optional Pinecone storage for earlier results.

Built with