Releasedv1.0.0Document AI · RAG · LLM

Enterprise Document Intelligence Platform

Enterprise document intelligence with retrieval, citation-backed answers, evaluation harness, and production FastAPI packaging.

IDP with ingest, retrieval, RAG citations, field extraction, evaluation harness, and FastAPI delivery.

Interactive Demo GitHub Metrics Architecture API Docs Presentation README

Problem

Enterprise knowledge is trapped in documents

Search alone does not produce grounded answers

Black-box chatbots without citations fail trust reviews

IDP needs evaluation — not prompt demos

Solution

Document intelligence with measurable retrieval

Ingest → chunk → embed → retrieve → cite
Hit-rate, citation coverage, faithfulness checks
FastAPI contracts for integration demos

Pipeline

Interactive system flow

Selected stage

Ingest

Accept PDF/TXT into the document store.

Architecture

System architecture

Download

Interactive Demo

Use the real system

Start with Run Example — one click fills a realistic payload and calls the live FastAPI via this site's proxy.

Capability focus: grounded RAG — answer markers map to colored source passages (citations required).

Upload PDF/TXT (optional)

Question

// Grounded answer + numbered citations appear here

Loading Interactive Demo…

Performance

Measured evaluation results

Numbers below match this project's evaluation reports. Dataset scope, baselines, and limitations are documented under Integrity.

Hit-rate@5

1.00

Citation coverage

1.00

Faithfulness

1.00

Comparison chart · source: project reports/metrics

Metric	Primary	Baseline
Hit-rate@5	1.00	—
Citation coverage	1.00	—
Faithfulness	1.00	—

Loading Performance…

Engineering Quality

Production packaging signals

RAG pipeline

Custom retrieval stack

Evaluation

Fixture harness

Docker

Dockerfile

GitHub Actions

OpenAPI

FastAPI contracts

Docs

Engineering docs 00–28

Integrity

Engineering decisions & limitations

Citations required for answers
Sample/public corpus — not a customer archive
Extractive default unless LLM_API_KEY is set
Metrics from labeled evaluation fixtures
Optional API key gate for demos

Repository

Source of truth

README Architecture Presentation Dashboard Repository Release v1.0.0

Presentation

Hiring presentation pack

Presentation pack Performance dashboard Architecture page

API Docs

Execute live FastAPI contracts

// Response JSON appears here

Loading API Explorer…

README

Source documentation

Open project README →

About Engineer

Mohammad Ahmadian

AI / Machine Learning Engineer

Production-oriented AI/ML systems — evaluation, APIs, and honest limitations. Turkey (GMT+3).

GitHub Email Resume Contact