Upload app.py

app.py

@@ -0,0 +1,51 @@
+import streamlit as st
+import pandas as pd
+from sentence_transformers import SentenceTransformer,util
+import torch
+import numpy as np
+from os.path import exists
+
+
+st.sidebar.image("./NarrativaLogoBlanco.png")
+topK = st.sidebar.slider("Number of results: ", 1, 20, 5, 1)
+
+st.write("# Semantic News Search 🔍📰")
+
+model = SentenceTransformer('all-MiniLM-L6-v2', device='cpu')
+
+df = pd.read_csv('data/financial-sentences.csv')
+sentences = df['sentences'].to_list()
+
+# check if embedding is available
+
+if exists('data/embeddings.npy'):
+    corpus_embeddings = np.load('data/embeddings.npy')
+else:
+    corpus_embeddings = model.encode(sentences, batch_size=23, show_progress_bar=False, convert_to_tensor=True)
+    np.save('data/embeddings.npy',  np.array(corpus_embeddings.cpu()))
+
+
+sentence = st.text_input('Enter a sentence:')
+
+if sentence:
+
+    embedding = model.encode(sentences=[sentence], convert_to_tensor=True)
+    cosine_scores = util.cos_sim(embedding, corpus_embeddings)[0]
+    top_results = torch.topk(cosine_scores, k=topK)
+    st.write()
+    st.write(" **Query:**", sentence)
+    st.write(f"\n **Top {topK} most similar sentences in corpus:**\n")
+
+    for score, idx in zip(top_results[0], top_results[1]):
+        st.write(sentences[idx])
+        st.write(f"*Score:* {score:.4f}")
+        st.write()
+        st.write()
+
+
+
+
+
+
+
+