Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -68,23 +68,22 @@ else:
|
|
68 |
def preprocess_text(text):
|
69 |
sentences = sent_tokenize(text)
|
70 |
return sentences
|
71 |
-
|
72 |
def upload_files(files):
|
73 |
global faiss_index
|
74 |
try:
|
75 |
for file in files:
|
76 |
file_name = file.name
|
77 |
|
78 |
-
#
|
79 |
-
if
|
80 |
-
file_content = file
|
81 |
else:
|
82 |
-
|
83 |
|
84 |
if file_name.endswith('.pdf'):
|
85 |
-
text = extract_text_from_pdf(file_content)
|
86 |
elif file_name.endswith('.docx'):
|
87 |
-
text = extract_text_from_docx(file_content)
|
88 |
else:
|
89 |
return {"error": "Unsupported file format"}
|
90 |
|
|
|
68 |
def preprocess_text(text):
|
69 |
sentences = sent_tokenize(text)
|
70 |
return sentences
|
|
|
71 |
def upload_files(files):
|
72 |
global faiss_index
|
73 |
try:
|
74 |
for file in files:
|
75 |
file_name = file.name
|
76 |
|
77 |
+
# Extract file content
|
78 |
+
if isinstance(file, str):
|
79 |
+
file_content = file
|
80 |
else:
|
81 |
+
file_content = file.read().decode("utf-8")
|
82 |
|
83 |
if file_name.endswith('.pdf'):
|
84 |
+
text = extract_text_from_pdf(file_content.encode())
|
85 |
elif file_name.endswith('.docx'):
|
86 |
+
text = extract_text_from_docx(file_content.encode())
|
87 |
else:
|
88 |
return {"error": "Unsupported file format"}
|
89 |
|