app.py

import re
from urllib.parse import urlparse, parse_qs
import pandas as pd
import unicodedata as uni
import emoji
from langchain.chat_models import ChatOpenAI
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.document_loaders import DataFrameLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.chains import RetrievalQA
from tokopedia import request_product_id, request_product_review
import gradio as gr

shop_id = ""
item_id = ""
item = {}
LIMIT = 1000  # Limit to 1000 reviews so that processing does not take too long

def scrape(URL, max_reviews=LIMIT):
    parsed_url = urlparse(URL)
    *_, SHOP, PRODUCT_KEY = parsed_url.path.split("/")
    product_id = request_product_id(SHOP, PRODUCT_KEY).json()["data"]["pdpGetLayout"][
        "basicInfo"
    ]["id"]
    all_reviews = []
    page = 1
    has_next = True

    while has_next and len(all_reviews) <= max_reviews:
        response = request_product_review(product_id, page=page)
        data = response.json()["data"]["productrevGetProductReviewList"]
        reviews = data["list"]
        all_reviews.extend(reviews)
        has_next = data["hasNext"]
        page += 1

    reviews_df = pd.json_normalize(all_reviews)
    return reviews_df

# Clean
def clean(df):
    df = df.dropna().copy().reset_index(drop=True)  # drop reviews with empty comments
    df = df[df["comment"] != ""].reset_index(drop=True)  # remove empty reviews
    df["comment"] = df["comment"].apply(lambda x: clean_text(x))  # clean text
    df = df[df["comment"] != ""].reset_index(drop=True)  # remove empty reviews
    return df


def clean_text(text):
    text = uni.normalize("NFKD", text)  # normalise characters
    text = emoji.replace_emoji(text, "")  # remove emoji
    text = re.sub(r"(\w)\1{2,}", r"\1", text)  # repeated chars
    text = re.sub(r"[ ]+", " ", text).strip()  # remove extra spaces
    return text


# LLM
OpenAIModel = "gpt-3.5-turbo"
llm = ChatOpenAI(model=OpenAIModel, temperature=0.1)

# Embeddings
embeddings = HuggingFaceEmbeddings(model_name="Blaxzter/LaBSE-sentence-embeddings")

cache_URL = ""
db = None
qa = None


def generate(URL, query):
    global cache_URL, db, qa
    if URL != cache_URL:
        # Get reviews
        try:
            reviews = scrape(URL)
            # Clean reviews
            cleaned_reviews = clean(reviews)
            # Load data
            loader = DataFrameLoader(cleaned_reviews, page_content_column="comment")
            documents = loader.load()
        except Exception as e:
            return "Error getting reviews: " + str(e)

        # Split text
        text_splitter = RecursiveCharacterTextSplitter(
            chunk_size=1000, chunk_overlap=50
        )
        docs = text_splitter.split_documents(documents)
        cache_URL = URL
        # Vector store
        db = FAISS.from_documents(docs, embeddings)
        # Chain to answer questions
        qa = RetrievalQA.from_chain_type(llm=llm, retriever=db.as_retriever())
    return qa.run(query)


# Gradio
product_box = gr.Textbox(
    label="URL Produk", placeholder="URL produk dari Tokopedia"
)
query_box = gr.Textbox(
    lines=2,
    label="Kueri",
    placeholder="Contoh: Apa yang orang katakan tentang kualitas produknya?, Bagaimana pendapat orang yang kurang puas dengan produknya?",
)

gr.Interface(
    fn=generate,
    inputs=[product_box, query_box],
    outputs=gr.Textbox(label="Jawaban"),
    title="RingkasUlas",
    description="Bot percakapan yang bisa meringkas ulasan-ulasan produk di Tokopedia Indonesia (https://tokopedia.com/). Harap bersabar, bot ini dapat memakan waktu agak lama saat mengambil ulasan dari Tokopedia dan menyiapkan jawabannya.",
    allow_flagging="never",
    examples=[
        [
            "https://www.tokopedia.com/benitashop/telur-asin-powder-madam-kwan-golden-salted-egg-powder",
            "Berapa lama produknya bisa bertahan?",
        ],
        [
            "https://www.tokopedia.com/benitashop/telur-asin-powder-madam-kwan-golden-salted-egg-powder",
            "Produknya bisa dipakai untuk memasak apa?",
        ],
    ],
).launch()