Create app.py

app.py

@@ -0,0 +1,32 @@
+import streamlit as st
+import os
+from streamlit_chat import message
+
+
+from datasets import load_dataset
+
+dataset = load_dataset("wikipedia", "20220301.en", split="train[240000:290000]")
+
+
+wikidata = []
+
+for record in dataset:
+    wikidata.append(record["text"])
+
+wikidata = list(set(wikidata))
+# print("\n".join(wikidata[:5]))
+# print(len(wikidata))
+
+from sentence_transformers import SentenceTransformer
+import torch
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+if device != 'cuda':
+    print(f"you are using {device}. This is much slower than using "
+    "a CUDA-enabled GPU. If on colab you can chnage this by "
+    "clicking Runtime > change runtime type > GPU.")
+
+model = SentenceTransformer("all-MiniLM-L6-v2", device=device)
+
+# Creating a Index(Pinecone Vector Database)