| from langchain_community.document_loaders import PyPDFLoader | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| import os | |
| def load_pdf_files(directory): | |
| documents = [] | |
| for filename in os.listdir(directory): | |
| if filename.endswith('.pdf'): | |
| file_path = os.path.join(directory, filename) | |
| loader = PyPDFLoader(file_path) | |
| documents.extend(loader.load()) | |
| return documents | |
| def create_chunks(documents): | |
| text_splitter = RecursiveCharacterTextSplitter( | |
| chunk_size=1000, | |
| chunk_overlap=200 | |
| ) | |
| return text_splitter.split_documents(documents) |