app.py

import subprocess
import gradio as gr
from openai import OpenAI
import json
from agno.agent import Agent, RunResponse
from agno.models.openai.like import OpenAILike

subprocess.Popen("bash /home/user/app/start.sh", shell=True)

agent = Agent(
    model=OpenAILike(
        id="model",
        api_key="no-token",
        base_url="http://0.0.0.0:8000/v1",
    )
)


def handle_function_call(function_name, arguments):
    """Handle function calls from the model"""
    if function_name == "browser_search":
        # Implement your browser search logic here
        query = arguments.get("query", "")
        max_results = arguments.get("max_results", 5)
        return f"Search results for '{query}' (max {max_results} results): [Implementation needed]"

    elif function_name == "code_interpreter":
        # Implement your code interpreter logic here
        code = arguments.get("code", "")
        if not code:
            return "No code provided to execute."

        return f"Code interpreter results for '{code}': [Implementation needed]"

    return f"Unknown function: {function_name}"


def respond(
    message,
    history: list[tuple[str, str]] = [],
    system_message=None,
):
    messages = []
    if system_message:
        messages = [{"role": "system", "content": system_message}]

    for user, assistant in history:
        if user:
            messages.append({"role": "user", "content": user})
        if assistant:
            messages.append({"role": "assistant", "content": assistant})

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

    output = ""
    try:
        print("messages", messages)
        stream = agent.run(messages=messages, stream=True)

        for chunk in stream:
            print("chunk", chunk)
            output += chunk.content
            yield output

    except Exception as e:
        print(f"[Error] {e}")
        yield "⚠️ Llama.cpp server error"


demo = gr.ChatInterface(respond)

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