Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -80,7 +80,7 @@ def read_documents_from_directory(directory):
|
|
| 80 |
|
| 81 |
|
| 82 |
#train_directory = r'C:\Users\writa\Downloads\Crypto'
|
| 83 |
-
|
| 84 |
|
| 85 |
def main():
|
| 86 |
load_dotenv()
|
|
@@ -96,9 +96,9 @@ def main():
|
|
| 96 |
pdf_links = [link.get('href') for link in soup.find_all('a') if link.get('href').endswith('.pdf')]
|
| 97 |
return pdf_links
|
| 98 |
|
| 99 |
-
dataset_url = 'https://huggingface.co/datasets/Writo/realestate_data/tree/main'
|
| 100 |
-
pdf_links = get_pdf_links_from_dataset(dataset_url)
|
| 101 |
-
print(pdf_links)
|
| 102 |
|
| 103 |
# Processing text and setting up the AI model
|
| 104 |
char_text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000,
|
|
|
|
| 80 |
|
| 81 |
|
| 82 |
#train_directory = r'C:\Users\writa\Downloads\Crypto'
|
| 83 |
+
url = "https://huggingface.co/datasets/Writo/realestate_data/tree/main"
|
| 84 |
|
| 85 |
def main():
|
| 86 |
load_dotenv()
|
|
|
|
| 96 |
pdf_links = [link.get('href') for link in soup.find_all('a') if link.get('href').endswith('.pdf')]
|
| 97 |
return pdf_links
|
| 98 |
|
| 99 |
+
dataset_url = 'https://huggingface.co/datasets/Writo/realestate_data/tree/main'
|
| 100 |
+
pdf_links = get_pdf_links_from_dataset(dataset_url)
|
| 101 |
+
print(pdf_links)
|
| 102 |
|
| 103 |
# Processing text and setting up the AI model
|
| 104 |
char_text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000,
|