import re import requests 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 import gradio as gr SHOPEE_API_URL = """https://shopee.co.id/api/v2/item/get_ratings?filter=0&flag=1&itemid={item_id}&limit=20&offset={offset}&shopid={shop_id}&type=0""" shop_id = "" item_id = "" item = {} LIMIT = 1000 # Limit to 1000 reviews so that processing does not take too long def get_product_id(URL): # Get shop id and item id from input URL r = re.search(r"i\.(\d+)\.(\d+)", URL) shop_id, item_id = r[1], r[2] return shop_id, item_id def scrape(URL): try: shop_id, item_id = get_product_id(URL) except: return None offset = 0 reviews = [] while True: # Get JSON data using shop_id and item_id from input URL data = requests.get( SHOPEE_API_URL.format(shop_id=shop_id, item_id=item_id, offset=offset) ).json() i = 1 for i, review in enumerate(data["data"]["ratings"], 1): reviews.append(review["comment"]) if i % 20: break offset += 20 if offset >= LIMIT: break df = pd.DataFrame(reviews, columns=["comment"]) return 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 Shopee Indonesia" ) 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 Shopee Indonesia (https://shopee.co.id/). Harap bersabar, bot ini dapat memakan waktu agak lama saat mengambil ulasan dari Shopee dan menyiapkan jawabannya.", allow_flagging="never", examples=[ [ "https://shopee.co.id/Bantal-Selimut-Balmut-Mini-Karakter-kain-CVC-i.2392232.8965506?xptdk=324a77c0-7860-4059-b00d-5d3b340f8dfe", "Apa yang orang katakan tentang kualitas produknya?", ], [ "https://shopee.co.id/Bantal-Selimut-Balmut-Mini-Karakter-kain-CVC-i.2392232.8965506?xptdk=324a77c0-7860-4059-b00d-5d3b340f8dfe", "Bagaimana pendapat orang yang kurang puas dengan produknya?", ], ], ).launch()