adejones

def docx_replace(doc, data):
	paragraphs = list(doc.paragraphs)
	for t in doc.tables:
		for row in t.rows:
			for cell in row.cells:
				for paragraph in cell.paragraphs:
					paragraphs.append(paragraph)
	for p in paragraphs:
		for key, val in data.items():
			key_name = '${{{}}}'.format(key) # use placeholders in the form ${PlaceholderName}

ctlllll

import tiktoken
import langdetect
T = tiktoken.get_encoding("o200k_base")

length_dict = {}

for i in range(T.n_vocab):
    try:
        length_dict[i] = len(T.decode([i]))
    except: