Create app.py

app.py

@@ -0,0 +1,75 @@
+import gradio as gr
+import pandas as pd
+import tiktoken
+import pandas as pd
+import time
+import spacy
+from spacy.lang.en.stop_words import STOP_WORDS
+from string import punctuation
+from collections import Counter
+from heapq import nlargest
+import nltk
+import numpy as np
+from tqdm import tqdm
+from sentence_transformers import SentenceTransformer, util
+from sentence_transformers import SentenceTransformer, CrossEncoder, util
+import gzip
+import os
+import torch
+
+from openai.embeddings_utils import get_embedding, cosine_similarity
+import os
+
+
+
+df = pd.read_pickle('entire_data.pkl') #to load 123.pkl back to the dataframe df
+embedder = SentenceTransformer('all-mpnet-base-v2')
+
+def search(query):
+  n = 15
+  query_embedding = embedder.encode(query)
+  df["similarity"] = df.embedding.apply(lambda x: cosine_similarity(x, query_embedding.reshape(768,-1)))
+
+  results = (
+      df.sort_values("similarity", ascending=False)
+      .head(n))
+  
+  resultlist = []
+
+  hlist = []
+  for r in results.index:
+      if results.name[r] not in hlist:
+          smalldf = results.loc[results.name == results.name[r]]
+          smallarr = smalldf.similarity[r].max()
+          sm =smalldf.rating[r].mean()
+          
+          if smalldf.shape[1] > 3:
+            smalldf = smalldf[:3]
+
+          resultlist.append(
+          {
+            "name":results.name[r],
+            "relevance score": smallarr.tolist(),
+           "priceRange": smalldf.priceRange[r],
+            "rating": sm.tolist(),
+           "title": [ smalldf.title[s] for s in smalldf.index],
+            "relevant_reviews": [ smalldf.review[s] for s in smalldf.index]
+          })
+          hlist.append(results.name[r])
+  return resultlist
+
+def greet(query):
+    bm25 = search(query)
+    return bm25
+examples = [
+    ["The Best LGBTQ+ Friendly Hotels in Miami"],
+    ["The Best Nightlife Hotels in Miami"],
+    ["The Best Miami Hotels with Stunning Pools"],
+    ["The Most Romantic Hotels in Miami"],
+    ["Eco-Friendly Hotels"]
+ ]
+
+demo = gr.Interface(fn=greet, outputs="json",title="miami-hotel-search", 
+                     inputs=gr.inputs.Textbox(lines=5, label="Tell us what you like in a hotel?"),examples=examples)
+
+demo.launch(share=True)