Spaces:
Running
Running
Commit
·
ede8cb5
1
Parent(s):
f7048ce
init
Browse files- app.py +41 -0
- requirements.txt +2 -0
app.py
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import tiktoken
|
3 |
+
|
4 |
+
def count_tokens(text):
|
5 |
+
"""
|
6 |
+
Calculate the number of tokens in the input text using tiktoken.
|
7 |
+
|
8 |
+
Args:
|
9 |
+
text (str): The input text to be tokenized.
|
10 |
+
|
11 |
+
Returns:
|
12 |
+
int: The number of tokens in the input text.
|
13 |
+
"""
|
14 |
+
# Choose the encoding based on the model you are targeting.
|
15 |
+
# Here, we use 'gpt-3.5-turbo' as an example.
|
16 |
+
encoding = tiktoken.encoding_for_model("gpt-4")
|
17 |
+
|
18 |
+
# Encode the input text to get the list of token IDs
|
19 |
+
tokens = encoding.encode(text)
|
20 |
+
|
21 |
+
# Return the number of tokens
|
22 |
+
return len(tokens)
|
23 |
+
|
24 |
+
# Define the Gradio interface
|
25 |
+
iface = gr.Interface(
|
26 |
+
fn=count_tokens, # The function to call
|
27 |
+
inputs=gr.Textbox(lines=10, placeholder="Enter your text here..."), # Input component
|
28 |
+
outputs="number", # Output component
|
29 |
+
title="Token Counter with tiktoken",
|
30 |
+
description="Enter text below to calculate the number of tokens using the tiktoken library.",
|
31 |
+
examples=[
|
32 |
+
["Hello, how are you doing today?"],
|
33 |
+
["Gradio makes it easy to create web apps for machine learning models."],
|
34 |
+
["OpenAI's GPT models are powerful tools for natural language processing tasks."]
|
35 |
+
],
|
36 |
+
theme="default"
|
37 |
+
)
|
38 |
+
|
39 |
+
# Launch the app
|
40 |
+
if __name__ == "__main__":
|
41 |
+
iface.launch()
|
requirements.txt
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
tiktoken
|
2 |
+
gradio
|