import gradio as gr
import torch


from paper_rec import recommender, etl
from gradio.inputs import Textbox


def recommend(txt):
    if len(txt.strip()) <= 0:
        return {"msg": "no recommendations available for the input text."}

    top_n = 10
    # model user preferences:
    cleaned_txt = etl.clean_text(txt)
    sentences = etl.get_sentences_from_txt(txt)
    rec = recommender.Recommender()
    # loading data and model from HF
    rec.load_data()
    rec.load_model()
    # compute user embedding
    user_embedding = torch.from_numpy(rec.embedding(sentences))
    # get recommendations based on user preferences
    recs = rec.recommend(user_embedding, top_k=100)
    # deduplicate
    recs_output = []
    seen_paper = set()
    for p in recs:
        if p["id"] not in seen_paper:
            recs_output.append({"id": p["id"],
             "title": p["title"],
             "abstract": p["authors"],
             "abstract": p["abstract"]
             })
            seen_paper.add(p["id"])
        if len(recs_output) >= top_n:
            break

    # report top-n
    return recs_output


def inputs():
    pass


title = "Interactive demo: paper-rec"
description = "Demo that recommends you what recent papers in AI/ML to read next based on what you like."

iface = gr.Interface(fn=recommend,
                     inputs=[Textbox(lines=10, placeholder="Titles and abstracts from papers you like", default="", label="Sample of what I like <3")],
                     outputs="json",
                     layout='vertical'
                     )
iface.launch()