Create app.py

app.py

@@ -0,0 +1,53 @@
+!pip install gradio
+!pip install transformers
+from transformers import BertTokenizerFast, BertModel
+import gradio as gr
+
+tokenizer_bert = BertTokenizerFast.from_pretrained("kykim/bert-kor-base")
+model_bert = BertModel.from_pretrained("kykim/bert-kor-base")
+
+from sklearn.metrics.pairwise import cosine_similarity
+
+import pandas as pd
+df = pd.read_pickle('BookData_real_real_final.pkl')
+df_emb = pd.read_pickle('review_emb.pkl')
+
+
+def embed_text(text):
+    inputs = tokenizer_bert(text, return_tensors="pt")
+    outputs = model_bert(**inputs)
+    embeddings = outputs.last_hidden_state.mean(dim=1)  # 평균 임베딩 사용
+    return embeddings.detach().numpy()[0]
+    
+def recommend(message):
+  
+  columns = ['거리']
+  list_df = pd.DataFrame(columns=columns)
+
+  emb = embed_text(message)
+  list_df['거리'] = df_emb['서평임베딩'].map(lambda x: cosine_similarity([emb], [x]).squeeze())
+  answer = df.loc[list_df['거리'].idxmax()]
+  book_title = answer['제목']
+
+  return book_title
+
+
+
+
+
+title = "🍀고민 해결 도서 추천 챗봇🍀"
+description = "당신의 고민 해결을 도와줄 책을 추천 해드립니다"
+examples = [["요즘 잠이 안 와"]]
+
+
+
+
+gr.Interface(
+    fn=recommend,
+    title=title,
+    description=description,
+    examples=examples,
+    inputs=["text", "state"],
+    outputs=["chatbot", "state"],
+    theme="finlaymacklon/boxy_violet",
+).launch()