Код: Выделить всё
def load_docs(folder_path):
data_list = []
for file_path in glob.glob(os.path.join(folder_path, "*.pdf")):
loader = PyPDFLoader(file_path)
docs = loader.load()
loader_all = MergedDataLoader(docs) #
docs_all = loader_all.load() #
print(len(docs_all)) # here I'm expecting len of all pdf pages for ex. (pdf-1 has 1 pg, pdf-2 has 2 pg then total len should be 3)
# data = docs[0].page_content
# data_list.append((file_path, data))
return data_list
Есть предложения или решения?
Подробнее здесь: https://stackoverflow.com/questions/790 ... -lazy-load