Update app.py

app.py

@@ -19,10 +19,14 @@ if not os.path.exists("knowledge_base"):
     exit()
 
 # Load all PDFs from a local folder
-# loader = DirectoryLoader("knowledge_base/", glob="**/*.pdf", loader_cls=PyPDFLoader)
-# raw_documents = loader.load()
 from datasets import load_dataset
-dataset = load_dataset("BBQlover/DDaT_with_RAG")
+from langchain.docstore.document import Document
+
+# Load a dataset hosted on Hugging Face
+dataset = load_dataset("BBQlover/DDaT_with_RAG", split="train")
+
+# Convert each entry to LangChain-compatible document
+raw_documents = [Document(page_content=entry["text"]) for entry in dataset]
 
 # Optional: split documents into smaller chunks for better retrieval
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)