Loading
MindXchange
MindXchange
MindXchange

Quipoin Menu

Learn • Practice • Grow

Tutorial Exercises MCQs Interview Q & A Tests
rag / Document Loading
tutorial
VideosDiscussion

Document Loading

The first step in any RAG pipeline is loading documents from various sources. LangChain provides document loaders for PDFs, text files, web pages, and more. This chapter covers the most common ones.

Loading PDFs

Use the `PyPDFLoader` to load PDF files.
from langchain.document_loaders import PyPDFLoader

loader = PyPDFLoader("document.pdf")
pages = loader.load()
print(len(pages))
Each page becomes a separate document object.

Loading Text Files

from langchain.document_loaders import TextLoader

loader = TextLoader("notes.txt")
documents = loader.load()

Loading Web Pages

from langchain.document_loaders import WebBaseLoader

loader = WebBaseLoader("https://example.com")
docs = loader.load()

Loading CSV Files

from langchain.document_loaders import CSVLoader

loader = CSVLoader("data.csv")
docs = loader.load()

Directory Loader (Multiple Files)

from langchain.document_loaders import DirectoryLoader

loader = DirectoryLoader("./docs/ glob=""**/*.txt"")
docs = loader.load()


Two Minute Drill
  • Use `PyPDFLoader` for PDFs `TextLoader` for text files.
  • `WebBaseLoader` loads web pages.
  • `CSVLoader` loads tabular data.
  • `DirectoryLoader` loads many files at once.
"

Need more clarification?

Drop us an email at career@quipoinfotech.com