Update app.py
Browse files
app.py
CHANGED
@@ -1,49 +1,26 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
# def extract_text(pdf_file):
|
7 |
-
|
8 |
-
# # Load a document
|
9 |
-
# loader = PDFMinerLoader(pdf_file)
|
10 |
-
# doc = loader.load()
|
11 |
-
|
12 |
-
# text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
|
13 |
-
# texts = text_splitter.split_documents(doc)
|
14 |
-
|
15 |
-
# texts = [i.page_content for i in texts]
|
16 |
-
|
17 |
-
# return texts[0]
|
18 |
-
|
19 |
-
|
20 |
-
# # def upload_file(file):
|
21 |
-
# # return file.name
|
22 |
-
|
23 |
-
# # with gr.Blocks() as demo:
|
24 |
-
# # file_output = gr.File()
|
25 |
-
# # upload_button = gr.UploadButton("Click to Upload a File", file_types="file")
|
26 |
-
# # upload_button.upload(upload_file, upload_button, file_output)
|
27 |
-
|
28 |
-
|
29 |
-
# gr.inputs.File(label="upload file")
|
30 |
|
31 |
-
# iface = gr.Interface(
|
32 |
-
# fn=extract_text,
|
33 |
-
# inputs=gr.File(type="filepath", label="Upload PDF"),
|
34 |
-
# outputs="text"
|
35 |
-
# )
|
36 |
|
37 |
-
# iface.launch()
|
38 |
|
39 |
import gradio as gr
|
40 |
|
41 |
def upload_pdf(file):
|
42 |
# Save the uploaded file
|
43 |
file_name = file.name
|
44 |
-
|
45 |
-
|
46 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
|
48 |
iface = gr.Interface(
|
49 |
fn=upload_pdf,
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from langchain.document_loaders import PDFMinerLoader, PyMuPDFLoader
|
3 |
+
from langchain.text_splitter import CharacterTextSplitter
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
|
|
|
|
|
|
|
|
|
|
|
5 |
|
|
|
6 |
|
7 |
import gradio as gr
|
8 |
|
9 |
def upload_pdf(file):
|
10 |
# Save the uploaded file
|
11 |
file_name = file.name
|
12 |
+
pdf_filename = os.path.basename(file_path)
|
13 |
+
|
14 |
+
# Load a document
|
15 |
+
loader = PDFMinerLoader(pdf_filename)
|
16 |
+
doc = loader.load()
|
17 |
+
|
18 |
+
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
|
19 |
+
texts = text_splitter.split_documents(doc)
|
20 |
+
|
21 |
+
texts = [i.page_content for i in texts]
|
22 |
+
|
23 |
+
return texts[0]
|
24 |
|
25 |
iface = gr.Interface(
|
26 |
fn=upload_pdf,
|