app.py

import os
import subprocess
import gradio as gr
from huggingface_hub import InferenceClient
from src.prompt.prompt_catalog import PromptCatalog
from src.llm_factory import get_llm
from src.plan.app_text2plan import demo_text2plan
from llama_index.core.llms import ChatMessage

if False:
    llm = get_llm("openrouter-paid-gemini-2.0-flash-001")
    messages = [
        ChatMessage(
            role="system", content="You are a pirate with a colorful personality"
        ),
        ChatMessage(role="user", content="What is your name"),
    ]
    resp = llm.stream_chat(messages)

    for r in resp:
        print(r.delta, end="")


if False:
    # Load modules from src
    prompt_catalog = PromptCatalog()
    prompt_catalog.load(os.path.join(os.path.dirname(__file__), 'src', 'plan', 'data', 'simple_plan_prompts.jsonl'))
    prompt_item = prompt_catalog.find("4dc34d55-0d0d-4e9d-92f4-23765f49dd29")
    print(prompt_item)

if False:
    # Spawn a child process that lists files in the current directory.
    result = subprocess.run(["pwd"], capture_output=True, text=True)
    print("Child process output:")
    print(result.stdout)

if False:
    # Write a file
    with open("output.txt", "w") as f:
        f.write("Hello from Hugging Face 1 Spaces!")

    # Read the file back
    with open("output.txt", "r") as f:
        content = f.read()
        print("File content:", content)


"""
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("HuggingFaceH4/zephyr-7b-beta")


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=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        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,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo_text2plan.launch()