Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -23,23 +23,32 @@ genai.configure(api_key=api_key)
|
|
23 |
# Step 4: Function to read files and extract text
|
24 |
def extract_text(file):
|
25 |
text = ""
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
return text
|
44 |
|
45 |
# Step 5: Function to convert text into chunks
|
|
|
23 |
# Step 4: Function to read files and extract text
|
24 |
def extract_text(file):
|
25 |
text = ""
|
26 |
+
try:
|
27 |
+
if file.name.endswith(".pdf"):
|
28 |
+
pdf_reader = PdfReader(file)
|
29 |
+
for page in pdf_reader.pages:
|
30 |
+
text += page.extract_text()
|
31 |
+
elif file.name.endswith(".docx"):
|
32 |
+
text = docx2txt.process(file)
|
33 |
+
elif file.name.endswith(".txt"):
|
34 |
+
text = file.read().decode("utf-8") # Assuming UTF-8 by default
|
35 |
+
elif file.name.endswith(".csv"):
|
36 |
+
df = pd.read_csv(file, encoding='utf-8') # Assuming UTF-8 by default
|
37 |
+
text = df.to_string()
|
38 |
+
elif file.name.endswith(".xlsx"):
|
39 |
+
df = pd.read_excel(file)
|
40 |
+
text = df.to_string()
|
41 |
+
elif file.name.endswith(".json"):
|
42 |
+
data = json.load(file)
|
43 |
+
text = json.dumps(data, indent=4)
|
44 |
+
except UnicodeDecodeError:
|
45 |
+
# Handle the error by trying a different encoding
|
46 |
+
file.seek(0) # Reset the file pointer
|
47 |
+
if file.name.endswith(".txt"):
|
48 |
+
text = file.read().decode("ISO-8859-1") # Try Latin-1 encoding
|
49 |
+
elif file.name.endswith(".csv"):
|
50 |
+
df = pd.read_csv(file, encoding='ISO-8859-1') # Try Latin-1 encoding
|
51 |
+
text = df.to_string()
|
52 |
return text
|
53 |
|
54 |
# Step 5: Function to convert text into chunks
|