Update app.py

app.py

@@ -6,6 +6,7 @@ import pandas as pd
 from classifier import classify
 from statistics import mean
 from genra_incremental import GenraPipeline
+from qa_process import generate_answer
 
 
 HFTOKEN = os.environ["HF_TOKEN"]
@@ -133,6 +134,15 @@ def qa_process(selected_queries, qa_llm_model, aggregator,
     
     return q_a_df, answers_df, summary
 
+def qa_summarise(selected_queries, qa_llm_model, text_field, data_df):
+    
+    qa_input_df = data_df[data_df["model_label"] != "none"].reset_index()
+    texts = qa_input_df[text_field].to_list()
+    
+    summary = generate_answer(qa_llm_model, texts, selected_queries[0], mode="summarize")
+    
+    return summary
+
             
 with gr.Blocks() as demo:
     event_models = ["jayebaku/distilbert-base-multilingual-cased-crexdata-relevance-classifier"]
@@ -244,13 +254,16 @@ with gr.Blocks() as demo:
         qa_button = gr.Button("Start QA")
         hsummary = gr.Textbox(label="Historical Summary")
         
-        qa_df = gr.DataFrame()
-        answers_df = gr.DataFrame()
+        # qa_df = gr.DataFrame()
+        # answers_df = gr.DataFrame()
 
         addqry_button.click(add_query, inputs=[query_inp, queries_state], outputs=[selected_queries, queries_state])
+        # qa_button.click(qa_process, 
+        #                 inputs=[selected_queries, qa_llm_model, aggregator, batch_size, topk, text_field, data], 
+        #                 outputs=[qa_df, answers_df, hsummary])
         qa_button.click(qa_process, 
-                        inputs=[selected_queries, qa_llm_model, aggregator, batch_size, topk, text_field, data], 
-                        outputs=[qa_df, answers_df, hsummary])
+                        inputs=[selected_queries, qa_llm_model, text_field, data], 
+                        outputs=hsummary)
 
 
 demo.launch()