app.py

import gradio as gr
from huggingface_hub import InferenceClient
from datasets import load_dataset  # Import the datasets library

"""
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")

# Load the dataset from Hugging Face
dataset = load_dataset("samhog/psychology-RLAIF", split="train")  # Load the training split

# Inspect the dataset structure
print("Dataset Columns:", dataset.column_names)
print("Sample Data:", dataset[0])

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Attempt to find a response in the dataset
    try:
        closest_match = None
        for entry in dataset:
            if message.lower() in entry["question"].lower():  # Adjust based on actual column names
                closest_match = entry["answer"]  # Adjust based on actual column names
                break

        # If a match is found, return the dataset answer
        if closest_match:
            return closest_match

    except Exception as e:
        # Log errors during dataset querying
        print(f"Dataset Query Error: {e}")

    # If no match is found, or there's an error, fall back to chatbot model
    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
"""
# Use the custom theme by setting the `theme` parameter as a string
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)",
        ),
    ],
    theme="allenai/gradio-theme"  # Apply the custom theme
)

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