app.py

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from huggingface_hub import InferenceClient
import os
import gradio as gr

app = FastAPI()

client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta", token=os.getenv("huggingface_token"))

class Message(BaseModel):
    input: str
    history: list

@app.get("/")
async def home():
    return {"message": "Welcome to the chatbot API!"}

@app.post("/chat")
async def chat(message: Message):
    try:
        input_message = message.input
        
        # Call the chatbot function
        response = chatbot(input_message)
        
        return {"response": response}
    
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

def chatbot(input, history):
    try:
        # Call your chatbot function here
        message = [{"role": "user", "content": input}]
        history = [{"role": "system", "content": "You are a helpful assistant."}]
        messages = history + message
        
        output = client.chat_completion(
            messages=messages,
            max_tokens=4000,
            temperature=0.7
        )
        
        return output.choices[0].message.content
    
    except Exception as e:
        raise Exception(str(e))

# Define the Gradio chat interface
def gradio_chat(input):
    response = chatbot(input, [])
    return response

# Define Gradio inputs and outputs
inputs = [gr.Textbox(lines=5, label="Input")]
output = gr.Textbox(label="Response")

# Create Gradio interface
gr.Interface(chatbot, inputs=inputs, outputs=output, title="Chatbot",fill_height=True).launch()