Update app.py
Browse files
app.py
CHANGED
|
@@ -21,9 +21,8 @@ def ensure_list(x):
|
|
| 21 |
|
| 22 |
|
| 23 |
CHECKPOINTS = {
|
| 24 |
-
"LayoutLMv1
|
| 25 |
-
"
|
| 26 |
-
"Donut 🍩": "naver-clova-ix/donut-base-finetuned-docvqa",
|
| 27 |
}
|
| 28 |
|
| 29 |
PIPELINES = {}
|
|
@@ -71,34 +70,6 @@ def normalize_bbox(box, width, height, padding=0.005):
|
|
| 71 |
return [min_x * width, min_y * height, max_x * width, max_y * height]
|
| 72 |
|
| 73 |
|
| 74 |
-
examples = [
|
| 75 |
-
[
|
| 76 |
-
"invoice.png",
|
| 77 |
-
"What is the invoice number?",
|
| 78 |
-
],
|
| 79 |
-
[
|
| 80 |
-
"contract.jpeg",
|
| 81 |
-
"What is the purchase amount?",
|
| 82 |
-
],
|
| 83 |
-
[
|
| 84 |
-
"statement.png",
|
| 85 |
-
"What are net sales for 2020?",
|
| 86 |
-
],
|
| 87 |
-
# [
|
| 88 |
-
# "docquery.png",
|
| 89 |
-
# "How many likes does the space have?",
|
| 90 |
-
# ],
|
| 91 |
-
# [
|
| 92 |
-
# "hacker_news.png",
|
| 93 |
-
# "What is the title of post number 5?",
|
| 94 |
-
# ],
|
| 95 |
-
]
|
| 96 |
-
|
| 97 |
-
question_files = {
|
| 98 |
-
"What are net sales for 2020?": "statement.pdf",
|
| 99 |
-
"How many likes does the space have?": "https://huggingface.co/spaces/impira/docquery",
|
| 100 |
-
"What is the title of post number 5?": "https://news.ycombinator.com",
|
| 101 |
-
}
|
| 102 |
|
| 103 |
|
| 104 |
def process_path(path):
|
|
@@ -288,14 +259,11 @@ gradio-app h2, .gradio-app h2 {
|
|
| 288 |
"""
|
| 289 |
|
| 290 |
with gr.Blocks(css=CSS) as demo:
|
| 291 |
-
gr.Markdown("#
|
| 292 |
gr.Markdown(
|
| 293 |
-
"
|
| 294 |
-
" uses LayoutLMv1 fine-tuned on DocVQA, a document visual question"
|
| 295 |
" answering dataset, as well as SQuAD, which boosts its English-language comprehension."
|
| 296 |
-
" To use it, simply upload an image or PDF, type a question, and click 'submit'
|
| 297 |
-
" click one of the examples to load them."
|
| 298 |
-
" DocQuery is MIT-licensed and available on [Github](https://github.com/impira/docquery)."
|
| 299 |
)
|
| 300 |
|
| 301 |
document = gr.Variable()
|
|
@@ -330,16 +298,12 @@ with gr.Blocks(css=CSS) as demo:
|
|
| 330 |
)
|
| 331 |
gr.Markdown("— or —")
|
| 332 |
upload = gr.File(label=None, interactive=True, elem_id="short-upload-box")
|
| 333 |
-
gr.Examples(
|
| 334 |
-
examples=examples,
|
| 335 |
-
inputs=[example_image, example_question],
|
| 336 |
-
)
|
| 337 |
|
| 338 |
with gr.Column() as col:
|
| 339 |
gr.Markdown("## 2. Ask a question")
|
| 340 |
question = gr.Textbox(
|
| 341 |
label="Question",
|
| 342 |
-
placeholder="e.g. What is the
|
| 343 |
lines=1,
|
| 344 |
max_lines=1,
|
| 345 |
)
|
|
|
|
| 21 |
|
| 22 |
|
| 23 |
CHECKPOINTS = {
|
| 24 |
+
"LayoutLMv1": "impira/layoutlm-document-qa",
|
| 25 |
+
"distilbert": "distilbert/distilbert-base-cased-distilled-squad",
|
|
|
|
| 26 |
}
|
| 27 |
|
| 28 |
PIPELINES = {}
|
|
|
|
| 70 |
return [min_x * width, min_y * height, max_x * width, max_y * height]
|
| 71 |
|
| 72 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
|
| 75 |
def process_path(path):
|
|
|
|
| 259 |
"""
|
| 260 |
|
| 261 |
with gr.Blocks(css=CSS) as demo:
|
| 262 |
+
gr.Markdown("# Document Chatbot")
|
| 263 |
gr.Markdown(
|
| 264 |
+
"Document Chatbot uses LayoutLMv1 fine-tuned on DocVQA, a document visual question"
|
|
|
|
| 265 |
" answering dataset, as well as SQuAD, which boosts its English-language comprehension."
|
| 266 |
+
" To use it, simply upload an image or PDF, type a question, and click 'submit'."
|
|
|
|
|
|
|
| 267 |
)
|
| 268 |
|
| 269 |
document = gr.Variable()
|
|
|
|
| 298 |
)
|
| 299 |
gr.Markdown("— or —")
|
| 300 |
upload = gr.File(label=None, interactive=True, elem_id="short-upload-box")
|
|
|
|
|
|
|
|
|
|
|
|
|
| 301 |
|
| 302 |
with gr.Column() as col:
|
| 303 |
gr.Markdown("## 2. Ask a question")
|
| 304 |
question = gr.Textbox(
|
| 305 |
label="Question",
|
| 306 |
+
placeholder="e.g. What is the document about?",
|
| 307 |
lines=1,
|
| 308 |
max_lines=1,
|
| 309 |
)
|