Download app.py from S2gamzaS2/chatbot: direct link, hf CLI and curl.
- Browser
- Download file 1.6 kB
-
https://huggingface.co/spaces/S2gamzaS2/chatbot/resolve/main/app.py
- Command line
-
hf download hf://spaces/S2gamzaS2/chatbot/app.py
-
curl -L -o app.py https://huggingface.co/spaces/S2gamzaS2/chatbot/resolve/main/app.py
1.6 kB
| import gradio as gr | |
| import pandas as pd | |
| from sentence_transformers import SentenceTransformer | |
| from sklearn.metrics.pairwise import cosine_similarity | |
| title = "๐๊ณ ๋ฏผ ํด๊ฒฐ ๋์ ์ถ์ฒ ์ฑ๋ด๐" | |
| description = "๊ณ ๋ฏผ์ด ๋ฌด์์ธ๊ฐ์? ๊ณ ๋ฏผ ํด๊ฒฐ์ ๋์์ค ์ฑ ์ ์ถ์ฒํด๋๋ฆฝ๋๋ค" | |
| examples = [["์์ฆ ์ ์ด ์ ์จ๋ค"]] | |
| model = SentenceTransformer('jhgan/ko-sroberta-multitask') | |
| df = pd.read_pickle('BookData_emb.pkl') | |
| df_emb = df[['์ํ์๋ฒ ๋ฉ']].copy() | |
| def recommend(message): | |
| embedding = model.encode(message) | |
| df_emb['๊ฑฐ๋ฆฌ'] = df_emb['์ํ์๋ฒ ๋ฉ'].map(lambda x: cosine_similarity([embedding], [x]).squeeze()) | |
| answer = df.loc[df_emb['๊ฑฐ๋ฆฌ'].idxmax()] | |
| Book_title = answer['์ ๋ชฉ'] | |
| Book_author = answer['์๊ฐ'] | |
| Book_publisher = answer['์ถํ์ฌ'] | |
| Book_comment = answer['์ํ'] | |
| return Book_title | |
| gr.ChatInterface( | |
| fn=recommend, | |
| textbox=gr.Textbox(placeholder="๋ง๊ฑธ์ด์ฃผ์ธ์..", container=False, scale=7), | |
| title="์ด๋ค ์ฑ๋ด์ ์ํ์ฌ๋ฏธ๊น?", | |
| description="๋ฌผ์ด๋ณด๋ฉด ๋ตํ๋ ์ฑ๋ด์๋ฏธ๋ค.", | |
| theme="soft", | |
| examples=[["์๋ฝ"], ["์์ฆ ๋ฅ๋ค ใ ใ "], ["์ ์ฌ๋ฉ๋ด ์ถ์ฒ๋ฐ๋, ์ง์ฅ ์งฌ๋ฝ ํ 1"]], | |
| retry_btn="๋ค์๋ณด๋ด๊ธฐ โฉ", | |
| undo_btn="์ด์ ์ฑ ์ญ์ โ", | |
| clear_btn="์ ์ฑ ์ญ์ ๐ซ").launch() | |
| # gr.Interface( | |
| # fn=response, | |
| # title=title, | |
| # description=description, | |
| # examples=examples, | |
| # inputs=["text", "state"], | |
| # outputs=["chatbot", "state"], | |
| # theme="finlaymacklon/boxy_violet", | |
| # ).launch() |