File size: 2,067 Bytes
ed16dde
dc732ec
 
ed16dde
dc732ec
ed16dde
fad1354
dc732ec
fad1354
 
 
 
dc732ec
ed16dde
dc732ec
 
 
b2f2152
dc732ec
 
b2f2152
 
dc732ec
 
 
 
b2f2152
dc732ec
 
 
 
ed16dde
 
fad1354
dc732ec
 
 
 
fad1354
dc732ec
 
 
 
 
 
 
 
 
fad1354
dc732ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ed16dde
dc732ec
fad1354
dc732ec
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
import gradio as gr
from huggingface_hub import InferenceClient
from typing import List, Dict

# Response function for the chatbot
def respond(
    message: str,
    history: List[Dict[str, str]],
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
    hf_token: gr.OAuthToken,
):
    """
    Sends a chat message to the Hugging Face Inference API using the provided token and parameters.
    """
    client = InferenceClient(
        token=hf_token.token,
        model="Bocklitz-Lab/lit2vec-tldr-bart-model"
    )

    messages = [{"role": "system", "content": system_message}] + history
    messages.append({"role": "user", "content": message})

    response = ""

    for message_chunk in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        if message_chunk.choices and message_chunk.choices[0].delta.content:
            token = message_chunk.choices[0].delta.content
            response += token
            yield response

# Define the Gradio interface
chatbot = gr.ChatInterface(
    fn=respond,
    type="messages",
    additional_inputs=[
        gr.Textbox(
            value="You are a friendly chatbot.",
            label="System message",
            lines=1
        ),
        gr.Slider(
            minimum=1,
            maximum=2048,
            value=512,
            step=1,
            label="Max new tokens"
        ),
        gr.Slider(
            minimum=0.1,
            maximum=4.0,
            value=0.7,
            step=0.1,
            label="Temperature"
        ),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)"
        ),
    ],
)

# Set up the full Gradio Blocks layout with login
with gr.Blocks() as demo:
    with gr.Row():
        with gr.Column(scale=1):
            gr.LoginButton()
    chatbot.render()

# Run the app
if __name__ == "__main__":
    demo.launch()