app.py

import argparse
import logging

import datasets
import gradio as gr
import sentence_transformers

logging.disable(logging.CRITICAL)

model = sentence_transformers.SentenceTransformer(
    "dangvantuan/sentence-camembert-large", device="cpu")

dataset = datasets.load_dataset("json", data_files=["./dataset.json"], split="train")
dataset.load_faiss_index("embeddings", "index.faiss")

def search(query, k=3):
    query_embedding = model.encode(query)
    _, retrieved_examples = dataset.get_nearest_examples(
        "embeddings",
        query_embedding,
        k=int(k),
    )
    results = []
    for text, start, end, title, url in zip(
        retrieved_examples["text"],
        retrieved_examples["start"],
        retrieved_examples["end"],
        retrieved_examples["title"],
        retrieved_examples["url"],
    ):
        start = start
        end = end
        result = {
            "title": title,
            "transcript": f"[{str(start)} ====> {str(end)}] {text}",
            "link": url,
        }
        results.append(result)
    return results

iface = gr.Interface(
    fn=search,
    inputs=[
        gr.inputs.Textbox(
            label="Query", placeholder="Type in a search query...", lines=3
        ),
        gr.inputs.Number(
            label="K",
            default=3,
            description="Number of results to return",
        ),
    ],
    outputs=[
        gr.outputs.Label(
            label="Result 1", type="auto", default="Search results will appear here."
        ),
        gr.outputs.Label(
            label="Result 2", type="auto", default=""
        ),
        gr.outputs.Link(
            label="Result 3", type="auto", default=""
        ),
    ],
    title="Camembert and Faiss-powered Search Engine",
    description="Search through a dataset using Camembert and Faiss",
    theme="default",
    layout="vertical",
    allow_flagging=False,
    allow_screenshot=False,
    allow_share=True,
    allow_download=False
)

iface.launch()