transcription/docs/ver4/index_v4.md

Document Transcription System Overview (Version 4)

This project is a personal-scale application for transcribing, organizing, and preserving historical documents, images, and related people records.

Start Here

Read architecture_v4.md first for the technical overview and system design.

Core Capabilities

• Folder and multi-image ingestion into sequential Source pages under a single Document.
• Parallel asynchronous AI vision transcription using Python asyncio bounded by rate limits.
• Portable relational storage using SQLModel and SQLAlchemy across SQLite and PostgreSQL.
• Complete prompt and response provenance for every transcription job and page execution.
• File-integrity tracking through SHA-256 hashing and stored file sizes.
• Historical Person management with many-to-many document links and extensible relationship roles.
• Registry-driven DocumentType classification with stable codes and controlled selection.
• Inline human revision of transcribed pages while preserving immutable machine output.
• Partial-failure recovery for multi-page jobs.
• Cross-platform operational workflows driven by Python-based tooling.

Technical Stack

• Application Web Framework: FastAPI + NiceGUI
• Persistence Engine: SQLModel / SQLAlchemy
• Data Validation and Schemas: Pydantic V2
• Concurrency and Workers: Python asyncio
• Vision Providers: OpenAI, Anthropic, and OpenRouter adapters

Core Documentation Index

• System Architecture
• System Requirements
• Data Model
• Error Handling Policy

Transition Documents

• Scope Boundary
• Implementation Plan