Spaces:
Sleeping
Sleeping
File size: 1,243 Bytes
6a9c9f9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
import os
from langchain.document_loaders import (
TextLoader,
PyPDFLoader,
UnstructuredWordDocumentLoader,
UnstructuredFileLoader
)
def load_and_split_resume(file_path: str):
"""
Loads a resume file and splits it into text chunks using LangChain.
Args:
file_path (str): Path to the resume file (.txt, .pdf, .docx, etc.)
chunk_size (int): Maximum characters per chunk.
chunk_overlap (int): Overlap between chunks to preserve context.
Returns:
List[str]: List of split text chunks.
"""
if not os.path.exists(file_path):
raise FileNotFoundError(f"File not found: {file_path}")
ext = os.path.splitext(file_path)[1].lower()
# Select the appropriate loader
if ext == ".txt":
loader = TextLoader(file_path, encoding="utf-8")
elif ext == ".pdf":
loader = PyPDFLoader(file_path)
elif ext in [".docx", ".doc"]:
loader = UnstructuredWordDocumentLoader(file_path)
else:
# Fallback for other common formats
loader = UnstructuredFileLoader(file_path)
# Load the file as LangChain documents
documents = loader.load()
return documents
# return [doc.page_content for doc in split_docs]
|