app.py

from typing import Iterator

import gradio as gr
from huggingface_hub import InferenceClient


model_id = "microsoft/Phi-3-mini-4k-instruct"
client = InferenceClient(model_id)

GENERATE_DATASET_NAMES_FOR_QUERY = (
        "A Machine Learning Practioner is looking for a dataset that matches '{query}'. "
        "Generate a list of 10 names of quality dataset that don't exist but sound plausible and would "
        "be helpful. Feel free to reuse words from the query '{query}' to name the datasets. "
        "Give each dataset descriptive tags/keywords and use the following format:\n1. DatasetName (tag1, tag2, tag3)"
)


def stream_reponse(msg: str) -> Iterator[str]:
    for message in client.chat_completion(
        messages=[{"role": "user", "content": msg}],
        max_tokens=500,
        stream=True,
    ):
        yield message.choices[0].delta.content


def gen_datasets(query: str) -> Iterator[str]:
    output = ""
    for token in stream_reponse(GENERATE_DATASET_NAMES_FOR_QUERY.format(query=query)):
        output += token
        yield output


demo = gr.Interface(fn=gen_datasets, inputs="text", outputs="text")
demo.launch()