# cf-docuvision

Document parsing service for CircuitForge products. Parses scanned documents, PDFs, forms, and receipts into structured elements (headings, paragraphs, tables, figures) using [Dolphin-v2](https://huggingface.co/ByteDance/Dolphin-v2) (ByteDance, Apache 2.0).

**Status:** v0.1.0 — production-ready for single-page documents.

---

## Prerequisites

### Hardware

| GPU VRAM | Result |
|----------|--------|
| 16GB+ | Recommended — fast single-page parsing (1–3 seconds) |
| 8GB | Minimum — works for most documents |
| Under 8GB | Likely CUDA out-of-memory on model load |
| CPU only | Works — expect 60–120 seconds per page |

If you are on CPU or have limited VRAM, set `CF_DOCUVISION_DEVICE=cpu` before starting. The service logs a warning and continues — CPU fallback is slow but functional.

### Model download

First startup downloads approximately **5–8 GB** from HuggingFace. Subsequent runs use the local cache. No HuggingFace account required (model is Apache 2.0, not gated).

To speed up large downloads:

```bash
pip install hf-transfer
export HF_HUB_ENABLE_HF_TRANSFER=1
```

---

## Quick start (Docker Compose)

```bash
git clone https://git.opensourcesolarpunk.com/Circuit-Forge/cf-docuvision.git
cd cf-docuvision
cp .env.example .env    # edit if needed
docker compose up -d
```

Watch model load progress:

```bash
docker compose logs -f cf-docuvision
```

The service is ready when logs show `cf-docuvision: ready`. Confirm:

```bash
curl http://localhost:8003/health
# {"status": "ok", "model": "ByteDance/Dolphin-v2"}
```

---

## Direct Python run

```bash
pip install -r requirements.txt
CF_DOCUVISION_DEVICE=cuda uvicorn app.main:app --host 0.0.0.0 --port 8003
```

CPU fallback:

```bash
CF_DOCUVISION_DEVICE=cpu uvicorn app.main:app --host 0.0.0.0 --port 8003
```

---

## Configuration

| Variable | Default | Description |
|---|---|---|
| `CF_DOCUVISION_MODEL` | `ByteDance/Dolphin-v2` | HuggingFace model ID or local path |
| `CF_DOCUVISION_DEVICE` | `auto` | `cuda`, `cpu`, or `auto` (GPU if available) |
| `CF_DOCUVISION_PORT` | `8003` | Service port (Docker Compose only) |

To skip HuggingFace download, set `CF_DOCUVISION_MODEL` to a local directory:

```bash
# Optional: uncomment the volume mount in compose.yml
# - /Library/Assets/LLM/dolphin-v2:/models/dolphin-v2:ro
CF_DOCUVISION_MODEL=/models/dolphin-v2
```

---

## Connecting from a product

Set `CF_DOCUVISION_URL` in the product's `.env`:

```bash
CF_DOCUVISION_URL=http://localhost:8003
```

Products using cf-core's `DocuvisionClient` pick this up automatically.

> **Kiwi note:** Kiwi v0.10.x gates the docuvision call on `CF_ORCH_URL` — `CF_DOCUVISION_URL` is not yet read directly. Fix is tracked at [kiwi#150](https://git.opensourcesolarpunk.com/Circuit-Forge/kiwi/issues/150). Once that ships, set `CF_DOCUVISION_URL` in Kiwi's `.env` and leave `CF_ORCH_URL` unset.

---

## API reference

### `GET /health`

Returns 200 when the model is loaded and ready.

```json
{"status": "ok", "model": "ByteDance/Dolphin-v2"}
```

Returns 503 while the model is still loading at startup.

### `POST /extract`

Parse a document image into structured elements.

**Request:**

```json
{
  "image_b64": "<base64-encoded image bytes (JPEG, PNG, TIFF)>",
  "hint": "auto"
}
```

`hint` controls extraction focus:

| Value | Behaviour |
|---|---|
| `auto` | General parsing — balanced detection of all element types (default) |
| `table` | Prioritise HTML table rendering |
| `text` | Prioritise text content and heading hierarchy |
| `form` | Prioritise form fields and key-value pairs |

**Response:**

```json
{
  "elements": [
    {"type": "heading", "text": "Invoice", "bbox": [0.05, 0.02, 0.9, 0.08]},
    {"type": "paragraph", "text": "Due date: 2026-07-01", "bbox": [0.05, 0.10, 0.6, 0.14]}
  ],
  "tables": [
    {"html": "<table>...</table>", "bbox": [0.05, 0.20, 0.95, 0.60]}
  ],
  "raw_text": "Invoice\nDue date: 2026-07-01\n...",
  "metadata": {
    "source": "cf-docuvision",
    "model": "ByteDance/Dolphin-v2",
    "hint": "auto",
    "elapsed_ms": 1240
  }
}
```

Element types: `heading`, `paragraph`, `list`, `table`, `figure`, `formula`, `code`.

`bbox` values are normalised to [0, 1] relative to the image dimensions.

---

## Troubleshooting

**`CUDA out of memory` at startup**
Dolphin-v2 requires ~8GB VRAM. Set `CF_DOCUVISION_DEVICE=cpu` to use CPU mode instead.

**`503 Model not loaded` on first request**
The model is still loading. Watch logs for `cf-docuvision: ready` before sending requests. The Docker healthcheck waits up to 120 seconds.

**Very slow processing**
CPU mode is expected to take 60–120 seconds per page. This is normal. If you need speed, a GPU is required.

**`trust_remote_code=True` warning**
Dolphin-v2 requires `trust_remote_code=True` for its custom architecture. The model is Apache 2.0 and auditable at [huggingface.co/ByteDance/Dolphin-v2](https://huggingface.co/ByteDance/Dolphin-v2).

---

## License

- cf-docuvision service: [MIT](LICENSE) — CircuitForge LLC
- Dolphin-v2 model: [Apache 2.0](https://huggingface.co/ByteDance/Dolphin-v2) — ByteDance