Spaces:
Running
Running
Delete app.py
Browse files
app.py
DELETED
@@ -1,43 +0,0 @@
|
|
1 |
-
import gradio as gr
|
2 |
-
from groq import Groq
|
3 |
-
from transformers import TextStreamer
|
4 |
-
|
5 |
-
# Initialize the Groq client with your API key
|
6 |
-
client = Groq(
|
7 |
-
api_key=("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"),
|
8 |
-
)
|
9 |
-
|
10 |
-
# Define the function that will generate responses
|
11 |
-
def generate_response(input_text):
|
12 |
-
chat_completion = client.chat.completions.create(
|
13 |
-
messages=[
|
14 |
-
{
|
15 |
-
"role": "user",
|
16 |
-
"content": input_text,
|
17 |
-
}
|
18 |
-
],
|
19 |
-
model="llama3-8b-8192",
|
20 |
-
)
|
21 |
-
|
22 |
-
# Set up TextStreamer for streaming the response
|
23 |
-
streamer = TextStreamer(client=client)
|
24 |
-
|
25 |
-
# Stream the assistant's response
|
26 |
-
response = ""
|
27 |
-
for chunk in chat_completion.choices[0].message.content:
|
28 |
-
response += chunk
|
29 |
-
streamer.write(response) # Stream each chunk of text
|
30 |
-
|
31 |
-
return response
|
32 |
-
|
33 |
-
# Create the Gradio interface
|
34 |
-
iface = gr.Interface(
|
35 |
-
fn=generate_response,
|
36 |
-
inputs="text",
|
37 |
-
outputs="text",
|
38 |
-
title="Fast Language Model Chatbot with Streaming",
|
39 |
-
description="Ask any question and receive a response from the Groq API using the llama3-8b-8192 model, streamed in real-time.",
|
40 |
-
)
|
41 |
-
|
42 |
-
# Launch the interface
|
43 |
-
iface.launch()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|