generated from john/python-template
77 lines
2.1 KiB
Markdown
77 lines
2.1 KiB
Markdown
# Transcription
|
|
|
|
Historical document transcription system for family-history documents.
|
|
|
|
The app lets you upload a document image/PDF, queues a background transcription job, and then shows job status and results in a web UI.
|
|
|
|
## What the app does
|
|
|
|
- Upload document files (`.jpg`, `.jpeg`, `.png`, `.tif`, `.tiff`, `.pdf`)
|
|
- Persist document + job records in SQLite
|
|
- Process jobs in a background worker (`queued -> processing -> transcribed/failed`)
|
|
- Store transcript text (or failure detail)
|
|
- Track transcript revisions (AI-generated and manual updates)
|
|
- Show status and results in the NiceGUI interface
|
|
|
|
## Quick start
|
|
|
|
### 1) Install dependencies
|
|
|
|
```bash
|
|
uv sync
|
|
```
|
|
|
|
### 2) Configure environment
|
|
|
|
Create a `.env` file in the project root (minimum required setting shown):
|
|
|
|
```env
|
|
OPENROUTER_API_KEY=your_openrouter_api_key
|
|
```
|
|
|
|
Optional settings (defaults shown):
|
|
|
|
```env
|
|
DATABASE_URL=sqlite:///./transcription.db
|
|
UPLOAD_DIR=./uploads
|
|
PROMPT_DIR=./prompts
|
|
```
|
|
|
|
### 3) Run the app
|
|
|
|
```bash
|
|
uv run uvicorn transcription.app:create_app --factory --reload
|
|
```
|
|
|
|
### 4) Open in browser
|
|
|
|
- GUI: [http://[IP_ADDRESS]:8000/ui](http://[IP_ADDRESS]:8000/ui)
|
|
- Health check: [http://[IP_ADDRESS]:8000/healthz](http://[IP_ADDRESS]:8000/healthz)
|
|
|
|
## How to navigate the GUI
|
|
|
|
- **Upload page** (`/ui`)
|
|
- Select a supported file to upload.
|
|
- The app creates a queued transcription job.
|
|
- Use the **View jobs** link to inspect progress.
|
|
|
|
- **Jobs page** (`/ui/jobs`)
|
|
- See all jobs and their status.
|
|
- Use **Refresh** to reload current states.
|
|
- Open a specific job to see details.
|
|
|
|
- **Job detail page** (`/ui/jobs/{job_id}`)
|
|
- Shows job metadata and status.
|
|
- Shows transcript metadata, including provider and model.
|
|
- Shows a version table with `Created` and `Version`.
|
|
- Displays latest version text in an editable textbox.
|
|
- **Update** creates a new transcript version.
|
|
- Displays failure detail for failed revisions.
|
|
|
|
## Prompt artifacts
|
|
|
|
Prompt files are stored in `prompts/` and loaded from `PROMPT_DIR` (default: `./prompts`).
|
|
|
|
The canonical MVP prompt is:
|
|
- `prompts/transcribe_document.md`
|