card: code status note, link to the GGUF build for llama.cpp
Browse files
README.md
CHANGED
|
@@ -50,6 +50,12 @@ frame ≈ 80); `"detail": "high"` allows up to 1920×1200.
|
|
| 50 |
|
| 51 |
## Usage
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
```python
|
| 54 |
from openthai_systemone import SystemOneClient
|
| 55 |
c = SystemOneClient("iapp/OpenThai-SystemOne-Vision")
|
|
|
|
| 50 |
|
| 51 |
## Usage
|
| 52 |
|
| 53 |
+
> **Code status (2026-11-15).** The Python client shown on this card (image inputs, `point`, `point_refine`) is not in the
|
| 54 |
+
> public GitHub repository yet; it arrives with the next code update there. What runs today with public code: the GGUF build
|
| 55 |
+
> [iapp/OpenThai-SystemOne-Vision-GGUF](https://huggingface.co/iapp/OpenThai-SystemOne-Vision-GGUF) on stock llama.cpp
|
| 56 |
+
> (`llama-server`, `/v1/systemone`): choice / score / noul questions, with or without a screenshot. It has no `point` head, so
|
| 57 |
+
> a click there is a choice among the controls the app reads from the screen (see that card).
|
| 58 |
+
|
| 59 |
```python
|
| 60 |
from openthai_systemone import SystemOneClient
|
| 61 |
c = SystemOneClient("iapp/OpenThai-SystemOne-Vision")
|