mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
c64f98e2bb
Co-authored-by: Andrew White <white.d.andrew@gmail.com> Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net> Co-authored-by: Peng Qu <82029664+pengqu123@users.noreply.github.com>
20 lines
743 B
Python
20 lines
743 B
Python
"""Test splitting with page numbers included."""
|
|
import os
|
|
|
|
from langchain.document_loaders import PagedPDFSplitter
|
|
from langchain.embeddings.openai import OpenAIEmbeddings
|
|
from langchain.vectorstores import FAISS
|
|
|
|
|
|
def test_pdf_pagesplitter() -> None:
|
|
"""Test splitting with page numbers included."""
|
|
script_dir = os.path.dirname(__file__)
|
|
loader = PagedPDFSplitter(os.path.join(script_dir, "examples/hello.pdf"))
|
|
docs = loader.load()
|
|
assert "page" in docs[0].metadata
|
|
assert "source" in docs[0].metadata
|
|
|
|
faiss_index = FAISS.from_documents(docs, OpenAIEmbeddings())
|
|
docs = faiss_index.similarity_search("Complete this sentence: Hello", k=1)
|
|
assert "Hello world" in docs[0].page_content
|