Update app.py

app.py

@@ -1,39 +1,25 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
 import torch
-
-
-title = "🤖AI ChatBot"
-description = "Building open-domain chatbots is a challenging area for machine learning research."
-examples = [["How are you?"]]
-
-
-tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
-model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
-
-
-def predict(input, history=[]):
-    # tokenize the new input sentence
-    new_user_input_ids = tokenizer.encode(
-        input + tokenizer.eos_token, return_tensors="pt"
-    )
-
-    # append the new user input tokens to the chat history
-    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
-
-    # generate a response
-    history = model.generate(
-        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
-    ).tolist()
-
-    # convert the tokens to text, and then split the responses into lines
-    response = tokenizer.decode(history[0]).split("<|endoftext|>")
-    # print('decoded_response-->>'+str(response))
-    response = [
-        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
-    ]  # convert to tuples of list
-    # print('response-->>'+str(response))
-    return response, history
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+
+title = "🍀고민 해결 도서 추천 챗봇🍀"
+description = "고민이 무엇인가요? 고민 해결을 도와줄 책을 추천해드립니다"
+examples = [["요즘 잠이 안 온다"]]
+
+
+model = SentenceTransformer('jhgan/ko-sroberta-multitask')
+
+def response(message):
+  embedding = model.encode(message)
+  df['distance'] = df['embedding'].map(lambda x: cosine_similarity([embedding], [x]).squeeze())
+  answer = df.loc[df['distance'].idxmax()]
+  Book_title = answer['제목']
+  Book_author = answer['작가']
+  Book_publisher = answer['출판사']
+  Book_comment = answer['서평']
+  return print(message)
 
 
 gr.Interface(