Skip to content

Polish recruiter-facing README #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
fetachino merged 1 commit into from
Aug 15, 2026
Merged

Polish recruiter-facing README #5

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,13 @@

A full-stack document processing workspace that turns uploaded PDFs, images, and DOCX files into searchable, reviewable data. The platform runs OCR, classification, structured extraction, vector indexing, and citation-grounded Q&A through durable background jobs, with tenant isolation and role-based access enforced by the backend.

This repository is a portfolio project focused on understandable service boundaries, deterministic local providers, auditability, and end-to-end verification. Production deployment configuration is not included yet.
This repository is a portfolio project focused on understandable service boundaries, deterministic local providers, auditability, and end-to-end verification. Kubernetes deployment scaffolding is included for the current API, frontend, and worker; production infrastructure, ingress, TLS, managed services, and a live deployment are intentionally not included.

**Quick Links:** [Application Demo](#application-demo) · [Architecture](#architecture) · [Running Locally](#running-locally) · [Security](SECURITY.md)

## Why I Built This

This project demonstrates production-oriented full-stack engineering across document processing, OCR, vector retrieval, grounded Q&A, human review, authentication and tenant isolation, background workers, storage abstractions, CI, and containerized deployment scaffolding.

## Application Demo

Expand All @@ -22,7 +28,7 @@ Shows selected-document semantic retrieval with ranked source chunks, page/chunk

### Grounded Q&A

Shows a grounded answer retrieved across the document collection with citation provenance and supporting document evidence.
Shows a grounded answer retrieved from the selected document with citation provenance and supporting document evidence.

![Grounded Q&A](docs/screenshots/grounded-qa.png)

Expand Down