app.py

from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient(
    "facebook/incoder-1B"
)




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, temperature=0.9, max_new_tokens=1024, 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,
    )

    formatted_prompt = format_prompt(f"{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


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"),
    title="Psychological Assistant: Expert in Assessment and Strategic Planning",
    description="Enter counseling notes to generate an assessment and plan.",
    examples=examples,
    concurrency_limit=20,
).launch(show_api=False, debug=True)