did llama hub get rid of the json loader

https://llamahub.ai/l/readers/llama-index-readers-json?from= ?

oh sick and do we just pass that into the simple directory?

this all im seeing

yea we need to flesh out the readmes 😅

you should be able to put that in the file extractor dict for simpledirectory reader yea

Thank you! Question is there a way to integrate spay doc into llama index custom doc. I like the NLP annoation spacy has

I don't think theres a way at the moment 👀 Need to convert spacy docs to llama-index docs/nodes

Cool. Thats why I was about the json haha

def process_pdfs(pdf_directory):
parser_api_url = "http://localhost:5010/api/parseDocument?renderFormat=all"
pdf_reader = LayoutPDFReader(parser_api_url)

data = []
for filename in os.listdir(pdf_directory):
if filename.endswith(".pdf"):
pdf_path = os.path.join(pdf_directory, filename)
print(f"\nProcessing document: {filename}")
doc = pdf_reader.read_pdf(pdf_path),

extra_info_user = get_extra_info()

for chunk in doc.chunks():
chunk_text = chunk.to_text(include_children=True, recurse=True)
docs = nlp(chunk_text)
extra_info_cats = {"summary": docs.text, "classification": docs.cats}

extra_info = {extra_info_user, extra_info_cats}

document = Document(
text= chunk_text,
extra_info=extra_info
)
data.append(document)
return data

summary of each chunk and classification

i have no clue if that does anything lol