Upload 7 files

app.py

@@ -89,15 +89,15 @@ sparse_scores = np.argsort(bm25.get_scores(tokenized_query), axis=0)[::-1]
 indices = get_bm25_search_hits(corpus, sparse_scores, 50)
 
 
-dense_embedding_output = literal_eval(
+dense_embedding = literal_eval(
     instructor_model.predict(
         query_embedding_instruction,
         query_text,
         api_name="/predict",
     )
-)
+).tolist()
 
-dense_embedding = [float(x) for x in dense_embedding_output[0]]
+#dense_embedding = [float(x) for x in dense_embedding_output[0]]
 
 text_embedding_instructions_choice = [
     "Represent the financial statement for retrieval:",