Update app.py

app.py

@@ -5,7 +5,7 @@ import pandas as pd
 
 from classifier import classify
 from statistics import mean
-from genra_incremental import GenraPipeline
+# from genra_incremental import GenraPipeline
 from qa_summary import generate_answer
 
 
@@ -88,51 +88,51 @@ def add_query(to_add, history):
         history.append(to_add)
     return gr.CheckboxGroup(choices=history), history
 
-def qa_process(selected_queries, qa_llm_model, aggregator,
-               batch_size, topk, text_field, data_df):
+# def qa_process(selected_queries, qa_llm_model, aggregator,
+#                batch_size, topk, text_field, data_df):
     
-    emb_model = 'multi-qa-mpnet-base-dot-v1'
-    contexts = []
+#     emb_model = 'multi-qa-mpnet-base-dot-v1'
+#     contexts = []
 
-    queries_df = pd.DataFrame({'id':[j for j in range(len(selected_queries))],'query': selected_queries})
-    qa_input_df = data_df[data_df["model_label"] != "none"].reset_index()
+#     queries_df = pd.DataFrame({'id':[j for j in range(len(selected_queries))],'query': selected_queries})
+#     qa_input_df = data_df[data_df["model_label"] != "none"].reset_index()
     
-    tweets_df = qa_input_df[[text_field]]
-    tweets_df.reset_index(inplace=True)
-    tweets_df.rename(columns={"index": "order", text_field: "text"},inplace=True)
+#     tweets_df = qa_input_df[[text_field]]
+#     tweets_df.reset_index(inplace=True)
+#     tweets_df.rename(columns={"index": "order", text_field: "text"},inplace=True)
 
-    gr.Info("Loading GENRA pipeline....")
-    genra = GenraPipeline(qa_llm_model, emb_model, aggregator, contexts)
-    gr.Info("Waiting for data...")
-    batches = [tweets_df[i:i+batch_size] for i in range(0,len(tweets_df),batch_size)]
+#     gr.Info("Loading GENRA pipeline....")
+#     genra = GenraPipeline(qa_llm_model, emb_model, aggregator, contexts)
+#     gr.Info("Waiting for data...")
+#     batches = [tweets_df[i:i+batch_size] for i in range(0,len(tweets_df),batch_size)]
     
-    genra_answers = []
-    summarize_batch = True
-    for batch_number, tweets in enumerate(batches):
-        gr.Info(f"Populating index for batch {batch_number}")
-        genra.qa_indexer.index_dataframe(tweets)
-        gr.Info(f"Performing retrieval for batch {batch_number}")
-        genra.retrieval(batch_number, queries_df, topk, summarize_batch) 
+#     genra_answers = []
+#     summarize_batch = True
+#     for batch_number, tweets in enumerate(batches):
+#         gr.Info(f"Populating index for batch {batch_number}")
+#         genra.qa_indexer.index_dataframe(tweets)
+#         gr.Info(f"Performing retrieval for batch {batch_number}")
+#         genra.retrieval(batch_number, queries_df, topk, summarize_batch) 
     
-    gr.Info("Processed all batches!")
+#     gr.Info("Processed all batches!")
     
-    gr.Info("Getting summary...")
-    summary = genra.summarize_history(queries_df)
+#     gr.Info("Getting summary...")
+#     summary = genra.summarize_history(queries_df)
     
-    gr.Info("Preparing results...")
-    results = genra.answers_store
-    final_answers, q_a = [], []
-    for q, g_answers in results.items():
-        for answer in g_answers:
-            final_answers.append({'question':q, "tweets":answer['tweets'], "batch":answer['batch_number'], "summary":answer['summary'] })
-            for t in answer['tweets']:
-                q_a.append((q,t))
-    answers_df = pd.DataFrame.from_dict(final_answers)
-    q_a = list(set(q_a))
-    q_a_df = pd.DataFrame(q_a, columns =['question', 'tweet'])
-    q_a_df = q_a_df.sort_values(by=["question"], ascending=False)
+#     gr.Info("Preparing results...")
+#     results = genra.answers_store
+#     final_answers, q_a = [], []
+#     for q, g_answers in results.items():
+#         for answer in g_answers:
+#             final_answers.append({'question':q, "tweets":answer['tweets'], "batch":answer['batch_number'], "summary":answer['summary'] })
+#             for t in answer['tweets']:
+#                 q_a.append((q,t))
+#     answers_df = pd.DataFrame.from_dict(final_answers)
+#     q_a = list(set(q_a))
+#     q_a_df = pd.DataFrame(q_a, columns =['question', 'tweet'])
+#     q_a_df = q_a_df.sort_values(by=["question"], ascending=False)
     
-    return q_a_df, answers_df, summary
+#     return q_a_df, answers_df, summary
 
 def qa_summarise(selected_queries, qa_llm_model, text_field, data_df):