Create app.py

app.py

@@ -0,0 +1,21 @@
+from datasets import load_dataset
+from datasets import Dataset
+from langchain.docstore.document import Document as LangchainDocument
+from sentence_transformers import SentenceTransformer
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
+from sentence_transformers import SentenceTransformer
+from huggingface_hub import Repository, upload_file
+
+url = "https://oxyjon.com/blog/"
+loader = WebBaseLoader(url)
+document = loader.load()
+    
+# split the document into chunks
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=256, chunk_overlap=50)
+texts = text_splitter.split_documents(document)
+print(texts[1])
+print(texts[3)
+print(texts[17)
+