Upload 7 files

app.py

@@ -89,7 +89,7 @@ sparse_scores = np.argsort(bm25.get_scores(tokenized_query), axis=0)[::-1]
 indices = get_bm25_search_hits(corpus, sparse_scores, 50)
 
 
-dense_embedding = literal_eval(
+dense_embedding_output = literal_eval(
     instructor_model.predict(
         query_embedding_instruction,
         query_text,
@@ -97,6 +97,7 @@ dense_embedding = literal_eval(
     )
 )
 
+dense_embedding = [int(x) for x in dense_embedding_output]
 
 text_embedding_instructions_choice = [
     "Represent the financial statement for retrieval:",