Update app.py
Browse files
app.py
CHANGED
@@ -1,32 +1,32 @@
|
|
1 |
-
import gradio as gr
|
2 |
-
from byaldi import RAGMultiModalModel # Importing the ColPali model
|
3 |
-
|
4 |
-
# Initialize the ColPali model
|
5 |
-
model = RAGMultiModalModel.from_pretrained("vidore/colpali")
|
6 |
-
|
7 |
-
def extract_and_search(image, keyword):
|
8 |
-
# Use the model to extract text from the image
|
9 |
-
extracted_text = model.predict(image) # Replace with actual prediction method
|
10 |
-
|
11 |
-
# Perform keyword search
|
12 |
-
matching_lines = [line for line in extracted_text.splitlines() if keyword.lower() in line.lower()]
|
13 |
-
|
14 |
-
return extracted_text, matching_lines
|
15 |
-
|
16 |
-
# Create Gradio interface
|
17 |
-
interface = gr.Interface(
|
18 |
-
fn=extract_and_search,
|
19 |
-
inputs=[
|
20 |
-
gr.Image(type="pil", label="Upload Image"),
|
21 |
-
gr.Textbox(label="Enter Keyword")
|
22 |
-
],
|
23 |
-
outputs=[
|
24 |
-
gr.Textbox(label="Extracted Text"),
|
25 |
-
gr.Textbox(label="Matching Lines")
|
26 |
-
],
|
27 |
-
title="ColPali OCR with Keyword Search",
|
28 |
-
description="Upload an image and enter a keyword to search within the extracted text."
|
29 |
-
)
|
30 |
-
|
31 |
-
# Launch the app
|
32 |
-
interface.launch(share=True)
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from byaldi import RAGMultiModalModel # Importing the ColPali model
|
3 |
+
|
4 |
+
# Initialize the ColPali model
|
5 |
+
model = RAGMultiModalModel.from_pretrained("vidore/colpali-v1.2")
|
6 |
+
|
7 |
+
def extract_and_search(image, keyword):
|
8 |
+
# Use the model to extract text from the image
|
9 |
+
extracted_text = model.predict(image) # Replace with actual prediction method
|
10 |
+
|
11 |
+
# Perform keyword search
|
12 |
+
matching_lines = [line for line in extracted_text.splitlines() if keyword.lower() in line.lower()]
|
13 |
+
|
14 |
+
return extracted_text, matching_lines
|
15 |
+
|
16 |
+
# Create Gradio interface
|
17 |
+
interface = gr.Interface(
|
18 |
+
fn=extract_and_search,
|
19 |
+
inputs=[
|
20 |
+
gr.Image(type="pil", label="Upload Image"),
|
21 |
+
gr.Textbox(label="Enter Keyword")
|
22 |
+
],
|
23 |
+
outputs=[
|
24 |
+
gr.Textbox(label="Extracted Text"),
|
25 |
+
gr.Textbox(label="Matching Lines")
|
26 |
+
],
|
27 |
+
title="ColPali OCR with Keyword Search",
|
28 |
+
description="Upload an image and enter a keyword to search within the extracted text."
|
29 |
+
)
|
30 |
+
|
31 |
+
# Launch the app
|
32 |
+
interface.launch(share=True)
|