File size: 1,263 Bytes
a04b074
0e0aaae
f4a8cd0
 
47c842b
 
 
 
f4a8cd0
e0b749f
045101e
 
 
 
 
 
 
 
0e0aaae
e0b749f
 
 
 
 
 
 
0e0aaae
f4a8cd0
0e0aaae
47c842b
e0b749f
 
a04b074
e0b749f
a04b074
 
e0b749f
 
47c842b
e0b749f
 
 
 
045101e
47c842b
 
035158a
a04b074
045101e
 
14e0605
a04b074
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
!pip install gradio 
import gradio as gr
from huggingface_hub import InferenceClient

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=600,
        stream=True,
        temperature=0.7,
        top_p=0.95,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,)


if __name__ == "__main__":
    demo.launch()