update

app.py

@@ -21,14 +21,14 @@ def load_model_and_tokenizer():
 
 @st.cache(allow_output_mutation=True)
 def load_sentence_data():
-    sentence_df = pd.read_csv("sentence_data_789k.csv.gz")
+    sentence_df = pd.read_csv("sentence_data_2m.csv.gz")
     
     return sentence_df
 
 
 @st.cache(allow_output_mutation=True)
 def load_sentence_embeddings_and_index():
-    npz_comp = np.load("sentence_embeddings_789k.npz")
+    npz_comp = np.load("sentence_embeddings_2m.npz")
     sentence_embeddings = npz_comp["arr_0"]
 
     faiss.normalize_L2(sentence_embeddings)
@@ -102,7 +102,7 @@ if __name__ == "__main__":
     st.markdown("## AI-based Paraphrasing for Academic Writing")
 
     input_text = st.text_area("text input", "We saw difference in the results between A and B.", placeholder="Write something here...")
-    top_k = st.number_input('top_k (upperbound)', min_value=1, value=30, step=1)
+    top_k = st.number_input('top_k (upperbound)', min_value=1, value=100, step=1)
     input_words = st.text_input("exclude words (comma separated)", "see, saw")
 
     if st.button('search'):

sentence_data_789k.csv.gz → sentence_data_2m.csv.gz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6faae9262e030d114dbd7b2ce26d4e8579f32888c74d62aa632807b0bf1757d
-size 38025362
+oid sha256:63c969cf0690e217d708cf1dca54a567b3e8b32c4d1b4f8581445a5bd3a5be0a
+size 105386557

sentence_embeddings_789k.npz → sentence_embeddings_2m.npz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0765885a9dfbd4e046a870664ca6b280613d0b516553e131638e0b6058b0cf95
-size 2243900234
+oid sha256:fe2c1296e1d676df6c0fc24b748523e254222ccf19bf5116d2cca0d93237709e
+size 6219635550