Computing cosine distance to topics

app.py

@@ -23,12 +23,29 @@ st.write('The embedding of', '"' + input_sentence + '"', 'at position',x,'is',em
 uploaded_file1 = st.file_uploader("Choose a file: sentence list")
 if uploaded_file1 is not None:
     #read csv
-    df1=pd.read_csv(uploaded_file1)
+    df1=pd.read_csv(uploaded_file1.head())
     st.write(df1)
 
 uploaded_file2 = st.file_uploader("Choose a file: topic list")
 if uploaded_file2 is not None:
     #read csv
-    df2=pd.read_csv(uploaded_file2)
+    df2=pd.read_csv(uploaded_file2.head())
     st.write(df2)
 
+if uploaded_file1 is not None and uploaded_file2 is not None:
+    from sentence_transformers import SentenceTransformer, util
+    import torch
+
+    embedder = SentenceTransformer('all-MiniLM-L6-v2')
+    corpus = df1['sentence']
+    topics = df2['topics']
+
+    corpus_embeddings = embedder.encode(corpus, convert_to_tensor=True)
+    for topic in topics:
+        topic_embedding = embedder.encode(topic, convert_to_tensor=True)
+        cos_scores = util.cos_sim(query_embedding, corpus_embeddings)[0]
+        df1[str(topic)] = cos_scores
+
+    st.write(df1)
+
+