github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-16 23:13:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Mathpix pdf loader (#3727)

Browse Source 
Inspo
https://twitter.com/danielgross/status/1651695062307274754?s=46&t=1zHLap5WG4I_kQPPjfW9fA

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This commit is contained in:
Davis Chase
2023-04-28 20:11:22 -07:00
committed by GitHub
parent 37ed6f2177
commit 220a7076ac
4 changed files with 167 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
tests/integration_tests/document_loaders/test_pdf.py
View File

@@ -6,6 +6,7 @@ from langchain.document_loaders import (
PyMuPDFLoader,
UnstructuredPDFLoader,
)
from langchain.document_loaders.pdf import MathpixPDFLoader
def test_unstructured_pdf_loader() -> None:
@@ -69,3 +70,19 @@ def test_pymupdf_loader() -> None:
assert loader.web_path == web_path
assert loader.file_path != web_path
assert len(docs) == 1
def test_mathpix_loader() -> None:
file_path = Path(__file__).parent.parent / "examples/hello.pdf"
loader = MathpixPDFLoader(str(file_path))
docs = loader.load()
assert len(docs) == 1
print(docs[0].page_content)
file_path = Path(__file__).parent.parent / "examples/layout-parser-paper.pdf"
loader = MathpixPDFLoader(str(file_path))
docs = loader.load()
assert len(docs) == 1
print(docs[0].page_content)