e67a25c0bd
* Add Adobe reader as the multimodal loader * Allow FullQAPipeline to reasoning on figures * fix: move the adobe import to avoid ImportError, notify users whenever they run the AdobeReader --------- Co-authored-by: cin-albert <albert@cinnamon.is>
22 lines
580 B
Python
22 lines
580 B
Python
# TODO: This test is broken and should be rewritten
|
|
from pathlib import Path
|
|
|
|
from kotaemon.loaders import AdobeReader
|
|
|
|
# from dotenv import load_dotenv
|
|
|
|
|
|
input_file = Path(__file__).parent / "resources" / "multimodal.pdf"
|
|
|
|
# load_dotenv()
|
|
|
|
|
|
def test_adobe_reader():
|
|
reader = AdobeReader()
|
|
documents = reader.load_data(input_file)
|
|
table_docs = [doc for doc in documents if doc.metadata.get("type", "") == "table"]
|
|
assert len(table_docs) == 2
|
|
|
|
figure_docs = [doc for doc in documents if doc.metadata.get("type", "") == "image"]
|
|
assert len(figure_docs) == 2
|