Python library for easily interacting with trained machine learning models
## Installation
```bash
pip install gradio_pdf
```
## Usage
```python
import gradio as gr
from gradio_pdf import PDF
from pdf2image import convert_from_path
from transformers import pipeline
from pathlib import Path
dir_ = Path(__file__).parent
p = pipeline(
"document-question-answering",
model="impira/layoutlm-document-qa",
)
def qa(question: str, doc: str) -> str:
img = convert_from_path(doc)[0]
output = p(img, question)
return sorted(output, key=lambda x: x["score"], reverse=True)[0]['answer']
demo = gr.Interface(
qa,
[gr.Textbox(label="Question"), PDF(label="Document")],
gr.Textbox(),
examples=[["What is the total gross worth?", str(dir_ / "invoice_2.pdf")],
["Whos is being invoiced?", str(dir_ / "sample_invoice.pdf")]]
)
if __name__ == "__main__":
demo.launch()
```
## `PDF`
### Initialization
| name | type | default | description |
|---|---|---|---|
value |
```python Any ``` | None |
None |
height |
```python int | None ``` | None |
None |
label |
```python str | None ``` | None |
None |
info |
```python str | None ``` | None |
None |
show_label |
```python bool | None ``` | None |
None |
container |
```python bool ``` | True |
None |
scale |
```python int | None ``` | None |
None |
min_width |
```python int | None ``` | None |
None |
interactive |
```python bool | None ``` | None |
None |
visible |
```python bool ``` | True |
None |
elem_id |
```python str | None ``` | None |
None |
elem_classes |
```python list[str] | str | None ``` | None |
None |
render |
```python bool ``` | True |
None |
load_fn |
```python Callable[Ellipsis, Any] | None ``` | None |
None |
every |
```python float | None ``` | None |
None |