Update pages/type_text.py

pages/type_text.py

@@ -5,7 +5,6 @@ import json
 import torch
 from transformers import pipeline # AutoTokenizer, AutoModelForCausalLM, AutoModelForTokenClassification
 from sentence_transformers import SentenceTransformer, util 
-#from "/home/user/app/pages/chapter_index.py" import selected_chapters_list
 
 import os
 os.getenv("HF_TOKEN") 
@@ -14,6 +13,7 @@ for k, v in st.session_state.items():
     st.session_state[k] = v
 selected_chapters_floatlist =  list(st.session_state.items())[0][1]
 selected_chapters_list = [int(i) for i in selected_chapters_floatlist]
+st.write("SELECTED CHAPTERS: ", selected_chapters_list)
 
 def get_device_map() -> str:
     return 'cuda' if torch.cuda.is_available() else 'cpu'
@@ -44,8 +44,6 @@ numMAPPINGS_input = 5
 #numMAPPINGS_input = st.text_input("Type number of mappings and hit Enter", key="user_input_numMAPPINGS")
 #st.button("Clear text", on_click=on_click)
 
-st.write("SELECTED CHAPTERS: ", selected_chapters_list)
-
 @st.cache_resource
 def load_model():
     model = SentenceTransformer('all-MiniLM-L6-v2') # fastest
@@ -62,11 +60,9 @@ INTdesc_embedding = model.encode(INTdesc_input)
 
 # Semantic search, Compute cosine similarity between all pairs of SBS descriptions
 
-#df_chapters = filter_chapters_env(df_chapters, "chapter_name")
-
 #df_SBS = pd.read_csv("SBS_V2_Table.csv", index_col="SBS_Code", usecols=["Long_Description"]) # na_values=['NA']
 #df_SBS = pd.read_csv("SBS_V2_Table.csv", usecols=["SBS_Code_Hyphenated","Long_Description"]) 
-from_line = 7727 # Imaging services chapter start, adjust as needed
+from_line = 7726 # Imaging services chapter start, adjust as needed
 to_line = 8239 # Imaging services chapter end, adjust as needed
 nrows = to_line - from_line + 1
 skiprows = list(range(1,from_line - 1))