Update pages/type_text.py

pages/type_text.py

@@ -74,14 +74,11 @@ HF_model_results = util.semantic_search(INTdesc_embedding, SBScorpus_embeddings)
 HF_model_results_sorted = sorted(HF_model_results, key=lambda x: x[1], reverse=True)
 HF_model_results_displayed = HF_model_results_sorted[0:numMAPPINGS_input]
 
-model_id = "meta-llama/Llama-3.2-1B-Instruct"
-pipe = pipeline("text-generation", model=model_id, device_map=device,) # device_map="auto", torch_dtype=torch.bfloat16
-
-
-#col1, col2, col3 = st.columns([1,1,2.5])
-#col1.subheader("Score")
-#col2.subheader("SBS code")
-#col3.subheader("SBS description V2.0")
+@st.cache_resource
+def load_model_pipe():
+    pipe = pipeline("text-generation", model="meta-llama/Llama-3.2-1B-Instruct", device_map=device,) # device_map="auto", torch_dtype=torch.bfloat16 
+    return pipe
+load_model_pipe()
 
 dictA = {"Score": [], "SBS Code": [], "SBS Description V2.0": []}
 dfALL = pd.DataFrame.from_dict(dictA)
@@ -89,45 +86,20 @@ dfALL = pd.DataFrame.from_dict(dictA)
 if INTdesc_input is not None and createSBScodes_clicked == True: 
     #for i, result in enumerate(HF_model_results_displayed):
     for result in HF_model_results_displayed:
-        #col1.write("%.4f" % result[0]["score"])
-        #col2.write(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[0]["corpus_id"]],"SBS_Code_Hyphenated"].values[0])
-        #col3.write(SBScorpus[result[0]["corpus_id"]])
-        #dictA["Score"].append("%.4f" % result[0]["score"]), dictA["SBS Code"].append(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[0]["corpus_id"]],"SBS_Code_Hyphenated"].values[0]), dictA["SBS Description V2.0"].append(SBScorpus[result[0]["corpus_id"]])
         dictA.update({"Score": "%.4f" % result[0]["score"], "SBS Code": df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[0]["corpus_id"]],"SBS_Code_Hyphenated"].values[0], "SBS Description V2.0": SBScorpus[result[0]["corpus_id"]]})
         dfALL = pd.concat([dfALL, pd.DataFrame([dictA])], ignore_index=True)
-            
-        #col1.write("%.4f" % result[1]["score"])
-        #col2.write(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[1]["corpus_id"]],"SBS_Code_Hyphenated"].values[0])
-        #col3.write(SBScorpus[result[1]["corpus_id"]])
-        #dictA["Score"].append("%.4f" % result[1]["score"]), dictA["SBS Code"].append(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[1]["corpus_id"]],"SBS_Code_Hyphenated"].values[0]), dictA["SBS Description V2.0"].append(SBScorpus[result[1]["corpus_id"]])
         dictA.update({"Score": "%.4f" % result[1]["score"], "SBS Code": df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[1]["corpus_id"]],"SBS_Code_Hyphenated"].values[0], "SBS Description V2.0": SBScorpus[result[1]["corpus_id"]]})
         dfALL = pd.concat([dfALL, pd.DataFrame([dictA])], ignore_index=True)
-            
-        #col1.write("%.4f" % result[2]["score"])
-        #col2.write(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[2]["corpus_id"]],"SBS_Code_Hyphenated"].values[0])
-        #col3.write(SBScorpus[result[2]["corpus_id"]])
-        #dictA["Score"].append("%.4f" % result[2]["score"]), dictA["SBS Code"].append(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[2]["corpus_id"]],"SBS_Code_Hyphenated"].values[0]), dictA["SBS Description V2.0"].append(SBScorpus[result[2]["corpus_id"]])
         dictA.update({"Score": "%.4f" % result[2]["score"], "SBS Code": df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[2]["corpus_id"]],"SBS_Code_Hyphenated"].values[0], "SBS Description V2.0": SBScorpus[result[2]["corpus_id"]]})
         dfALL = pd.concat([dfALL, pd.DataFrame([dictA])], ignore_index=True)
-            
-        #col1.write("%.4f" % result[3]["score"])
-        #col2.write(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[3]["corpus_id"]],"SBS_Code_Hyphenated"].values[0])
-        #col3.write(SBScorpus[result[3]["corpus_id"]])
-        #dictA["Score"].append("%.4f" % result[3]["score"]), dictA["SBS Code"].append(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[3]["corpus_id"]],"SBS_Code_Hyphenated"].values[0]), dictA["SBS Description V2.0"].append(SBScorpus[result[3]["corpus_id"]])
         dictA.update({"Score": "%.4f" % result[3]["score"], "SBS Code": df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[3]["corpus_id"]],"SBS_Code_Hyphenated"].values[0], "SBS Description V2.0": SBScorpus[result[3]["corpus_id"]]})
         dfALL = pd.concat([dfALL, pd.DataFrame([dictA])], ignore_index=True)
-            
-        #col1.write("%.4f" % result[4]["score"])
-        #col2.write(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[4]["corpus_id"]],"SBS_Code_Hyphenated"].values[0])
-        #col3.write(SBScorpus[result[4]["corpus_id"]])
-        #dictA["Score"].append("%.4f" % result[4]["score"]), dictA["SBS Code"].append(df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[4]["corpus_id"]],"SBS_Code_Hyphenated"].values[0]), dictA["SBS Description V2.0"].append(SBScorpus[result[4]["corpus_id"]])
         dictA.update({"Score": "%.4f" % result[4]["score"], "SBS Code": df_SBS.loc[df_SBS["Long_Description"] == SBScorpus[result[4]["corpus_id"]],"SBS_Code_Hyphenated"].values[0], "SBS Description V2.0": SBScorpus[result[4]["corpus_id"]]})
         dfALL = pd.concat([dfALL, pd.DataFrame([dictA])], ignore_index=True)
-
+        
         st.dataframe(data=dfALL, hide_index=True)
-        #st.write(dfALL)
 
-    display_format = "ask REASONING MODEL: Which, if any, of the above Saudi Billing System descriptions corresponds best to " + INTdesc_input +"? " 
+    display_format = "ask REASONING MODEL: Which, if any, of the above SBS descriptions corresponds best to " + INTdesc_input +"? " 
     st.write(display_format)
     question = "Which, if any, of the below Saudi Billing System descriptions corresponds best to " + INTdesc_input +"? " 
     shortlist = [SBScorpus[result[0]["corpus_id"]], SBScorpus[result[1]["corpus_id"]], SBScorpus[result[2]["corpus_id"]], SBScorpus[result[3]["corpus_id"]], SBScorpus[result[4]["corpus_id"]]]