Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
import warnings
|
2 |
warnings.simplefilter(action='ignore', category=FutureWarning)
|
3 |
|
|
|
4 |
import gradio as gr
|
5 |
from langchain.prompts import PromptTemplate
|
6 |
from langchain.chains.summarize import load_summarize_chain
|
@@ -18,11 +19,22 @@ llm = HuggingFaceEndpoint(
|
|
18 |
)
|
19 |
llm_engine_hf = ChatHuggingFace(llm=llm)
|
20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
def summarize(file, n_words):
|
22 |
# Read the content of the uploaded file
|
23 |
file_path = file.name
|
24 |
-
|
25 |
-
file_content =
|
|
|
|
|
|
|
|
|
26 |
document = Document(file_content)
|
27 |
# Generate the summary
|
28 |
text = document.page_content
|
|
|
1 |
import warnings
|
2 |
warnings.simplefilter(action='ignore', category=FutureWarning)
|
3 |
|
4 |
+
import PyPDF2
|
5 |
import gradio as gr
|
6 |
from langchain.prompts import PromptTemplate
|
7 |
from langchain.chains.summarize import load_summarize_chain
|
|
|
19 |
)
|
20 |
llm_engine_hf = ChatHuggingFace(llm=llm)
|
21 |
|
22 |
+
def read_pdf(file_path):
|
23 |
+
pdf_reader = PyPDF2.PdfReader(file_path)
|
24 |
+
text = ""
|
25 |
+
for page in range(len(pdf_reader.pages)):
|
26 |
+
text += pdf_reader.pages[page].extract_text()
|
27 |
+
return text
|
28 |
+
|
29 |
def summarize(file, n_words):
|
30 |
# Read the content of the uploaded file
|
31 |
file_path = file.name
|
32 |
+
if file_path.endswith('.pdf'):
|
33 |
+
file_content = read_pdf(file_path)
|
34 |
+
else:
|
35 |
+
with open(file_path, 'r', encoding='utf-8') as f:
|
36 |
+
file_content = f.read()
|
37 |
+
|
38 |
document = Document(file_content)
|
39 |
# Generate the summary
|
40 |
text = document.page_content
|