|
from huggingface_hub import InferenceClient |
|
import gradio as gr |
|
|
|
client = InferenceClient( |
|
"mistralai/Mixtral-8x7B-Instruct-v0.1" |
|
) |
|
|
|
def format_prompt(message, history): |
|
prompt = "<s>" |
|
for user_prompt, bot_response in history: |
|
prompt += f"[INST] {user_prompt} [/INST]" |
|
prompt += f" {bot_response}</s> " |
|
prompt += f"[INST] {message} [/INST]" |
|
return prompt |
|
|
|
def generate( |
|
prompt, history, system_prompt, temperature=0.9, max_new_tokens=512, top_p=0.95, repetition_penalty=1.0, |
|
): |
|
temperature = float(temperature) |
|
if temperature < 1e-2: |
|
temperature = 1e-2 |
|
top_p = float(top_p) |
|
|
|
generate_kwargs = dict( |
|
temperature=temperature, |
|
max_new_tokens=max_new_tokens, |
|
top_p=top_p, |
|
repetition_penalty=repetition_penalty, |
|
do_sample=True, |
|
seed=42, |
|
) |
|
|
|
|
|
if not history: |
|
formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history) |
|
else: |
|
formatted_prompt = format_prompt(prompt, history) |
|
|
|
stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False) |
|
output = "" |
|
|
|
for response in stream: |
|
output += response.token.text |
|
yield output |
|
return output |
|
|
|
additional_inputs=[ |
|
gr.Textbox( |
|
label="System Prompt", |
|
max_lines=1, |
|
interactive=True, |
|
) |
|
] |
|
|
|
examples=[ |
|
["Patient is feeling stressed due to work and has trouble sleeping.", None, None, None, None, None], |
|
["Client is dealing with relationship issues and is seeking advice on communication strategies.", None, None, None, None, None], |
|
["Individual has recently experienced a loss and is having difficulty coping with grief.", None, None, None, None, None], |
|
] |
|
|
|
gr.ChatInterface( |
|
fn=generate, |
|
chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"), |
|
additional_inputs=additional_inputs, |
|
title="PsyAssist - ADVANCING MENTAL HEALTH SUPPORT WITH AI-DRIVEN INTERACTION", |
|
examples=examples, |
|
concurrency_limit=20, |
|
).launch(show_api=False) |
