Ankur Goyal
commited on
Commit
•
bc12901
1
Parent(s):
9c27f12
Initial Commit
Browse files- .gitignore +4 -0
- README.md +5 -6
- app.py +50 -0
- requirements.txt +3 -0
.gitignore
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
venv
|
2 |
+
*.swo
|
3 |
+
*.swp
|
4 |
+
*.pyc
|
README.md
CHANGED
@@ -1,13 +1,12 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: streamlit
|
7 |
sdk_version: 1.10.0
|
8 |
app_file: app.py
|
9 |
-
pinned:
|
10 |
-
license: mit
|
11 |
---
|
12 |
|
13 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
1 |
---
|
2 |
+
title: DocQuery
|
3 |
+
emoji: 🦉
|
4 |
+
colorFrom: gray
|
5 |
+
colorTo: pink
|
6 |
sdk: streamlit
|
7 |
sdk_version: 1.10.0
|
8 |
app_file: app.py
|
9 |
+
pinned: true
|
|
|
10 |
---
|
11 |
|
12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
app.py
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
|
3 |
+
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
4 |
+
|
5 |
+
import streamlit as st
|
6 |
+
|
7 |
+
import torch
|
8 |
+
from docquery.pipeline import get_pipeline
|
9 |
+
from docquery.document import load_bytes
|
10 |
+
|
11 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
12 |
+
pipeline = get_pipeline(device=device)
|
13 |
+
|
14 |
+
|
15 |
+
def process_document(file, question):
|
16 |
+
# prepare encoder inputs
|
17 |
+
document = load_document(file.name)
|
18 |
+
return pipeline(question=question, **document.context)
|
19 |
+
|
20 |
+
|
21 |
+
def ensure_list(x):
|
22 |
+
if isinstance(x, list):
|
23 |
+
return x
|
24 |
+
else:
|
25 |
+
return [x]
|
26 |
+
|
27 |
+
|
28 |
+
st.title("DocQuery: Query Documents Using NLP")
|
29 |
+
file = st.file_uploader("Upload a PDF or Image document")
|
30 |
+
question = st.text_input("QUESTION", "")
|
31 |
+
|
32 |
+
document = None
|
33 |
+
|
34 |
+
if file is not None:
|
35 |
+
col1, col2 = st.columns(2)
|
36 |
+
|
37 |
+
document = load_bytes(file, file.name)
|
38 |
+
col1.image(document.preview, use_column_width=True)
|
39 |
+
|
40 |
+
if document is not None and question is not None and len(question) > 0:
|
41 |
+
predictions = pipeline(question=question, **document.context)
|
42 |
+
|
43 |
+
col2.header("Probabilities")
|
44 |
+
for p in ensure_list(predictions):
|
45 |
+
col2.subheader(f"{ p['answer'] }: { round(p['score'] * 100, 1)}%")
|
46 |
+
|
47 |
+
|
48 |
+
"DocQuery uses LayoutLMv1 fine-tuned on DocVQA, a document visual question answering dataset, as well as SQuAD, which boosts its English-language comprehension. To use it, simply upload an image or PDF, type a question, and click 'submit', or click one of the examples to load them."
|
49 |
+
|
50 |
+
"[Github Repo](https://github.com/impira/docquery)"
|
requirements.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
torch
|
2 |
+
git+https://github.com/huggingface/transformers.git
|
3 |
+
docquery
|