← Back to work

Applied AI & knowledge systems

ArchiveAI

Turn unstructured files into a source-cited knowledge workspace.

Status
Working open-source product
My role
Solo product, AI, backend, and interface engineering
Timeframe
March - June 2026
Core technology
Next.js · FastAPI · LangGraph · Docling
01Source-cited answers
02Multi-format document parsing
03Persistent retrieval workflows

01 / Context

The problem

Important knowledge is trapped across documents in incompatible formats. Generic chat tools make it difficult to inspect what was indexed or trace an answer back to its evidence.

02 / Product

The implemented solution

ArchiveAI gives users a complete document workspace: upload and inspect files, search semantically, manage conversations, and receive streamed answers that remain linked to supporting sources.

03 / System

Architecture, in plain language

A Next.js interface communicates with FastAPI services for ingestion and retrieval. Docling normalizes document structure, PostgreSQL and pgvector store searchable chunks, and a LangGraph workflow orchestrates grounded responses.

InterfaceApplication servicesData & integrations

04 / Judgment

Important decisions

  1. Designed the product around inspectable sources instead of treating citations as an afterthought.
  2. Separated ingestion, retrieval, and conversation concerns so each can evolve independently.
  3. Used persistent conversations to support research sessions rather than one-off prompts.

05 / Boundaries

Limitations and next work

Answer quality still depends on source quality, parsing fidelity, and retrieval coverage. Generated responses require human verification for high-stakes use.

06 / Implementation

Focused technology

Next.js · FastAPI · LangGraph · Docling · PostgreSQL · pgvector