Update app.py

app.py

@@ -1,22 +1,27 @@
-import gradio as gr
-from transformers import AutoTokenizer, AutoModelForTokenClassification,RobertaTokenizer
+from predict import run_prediction
+from io import StringIO
+import json
+import spacy
+from spacy import displacy
+from transformers import AutoTokenizer, AutoModelForTokenClassification,RobertaTokenizer,pipeline
 import torch
 import nltk
 from nltk.tokenize import sent_tokenize
 from fin_readability_sustainability import BERTClass, do_predict
 import pandas as pd
+import en_core_web_sm
 
-nltk.download('punkt')
 
+nlp = en_core_web_sm.load()
+nltk.download('punkt')
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-
+#SUSTAINABILITY STARTS
 tokenizer_sus = RobertaTokenizer.from_pretrained('roberta-base')
 model_sustain = BERTClass(2, "sustanability")
 model_sustain.to(device)
 model_sustain.load_state_dict(torch.load('sustainability_model.bin', map_location=device)['model_state_dict'])
 
-
 def get_sustainability(text):
   df = pd.DataFrame({'sentence':sent_tokenize(text)})
   actual_predictions_sustainability = do_predict(model_sustain, tokenizer_sus, df)
@@ -29,12 +34,70 @@ def get_sustainability(text):
     else:
       highlight.append((sent, '-'))
   return highlight
+#SUSTAINABILITY ENDS
 
+##Summarization 
+def summarize_text(text):
+    summarizer = pipeline("summarization", model="knkarthick/MEETING_SUMMARY")
+    resp = summarizer(text)
+    stext = resp[0]['summary_text']
+    return stext
 
+##Forward Looking Statement
+def fls(text):
+    fls_model = pipeline("text-classification", model="yiyanghkust/finbert-fls", tokenizer="yiyanghkust/finbert-fls")
+    results = fls_model(split_in_sentences(text))
+    return make_spans(text,results) 
+    
+##Company Extraction
+def fin_ner(text):
+    ner=pipeline('ner',model='Jean-Baptiste/camembert-ner-with-dates',tokenizer='Jean-Baptiste/camembert-ner-with-dates', aggregation_strategy="simple")
+    replaced_spans = ner(text)
+    return replaced_spans  
+    
+     
+#CUAD STARTS    
+def load_questions():
+    questions = []
+    with open('questions.txt') as f:
+        questions = f.readlines()
+    return questions
 
+
+def load_questions_short():
+    questions_short = []
+    with open('questionshort.txt') as f:
+        questions_short = f.readlines()
+    return questions_short
+
+def quad(query, paragraph):
+    questions = load_questions()
+    questions_short = load_questions_short()
+    if (not len(paragraph)==0) and not (len(question)==0):
+        print('getting predictions')
+    predictions = run_prediction([query], paragraph, 'marshmellow77/roberta-base-cuad',n_best_size=5)
+    answer = ""
+    if predictions['0'] == "":
+        answer = 'No answer found in document'
+    else:
+        with open("nbest.json") as jf:
+            data = json.load(jf)
+            for i in range(1):
+                raw_answer=data['0'][i]['text']
+                answer += f"Answer {i+1}: {data['0'][i]['text']} -- \n"
+                answer += f"Probability: {round(data['0'][i]['probability']*100,1)}%\n\n"
+    summarizer = pipeline("summarization", model="knkarthick/MEETING_SUMMARY")
+    resp = summarizer(answer)
+    stext = resp[0]['summary_text']
+    return stext,answer            
+                
+                   
 # b6 = gr.Button("Get Sustainability")
               #b6.click(get_sustainability, inputs = text, outputs = gr.HighlightedText())
               
               
-iface = gr.Interface(fn=get_sustainability, inputs="textbox", title="CONBERT",description="SUSTAINABILITY TOOL", outputs=gr.HighlightedText(), allow_flagging="never")
+#iface = gr.Interface(fn=get_sustainability, inputs="textbox", title="CONBERT",description="SUSTAINABILITY TOOL", outputs=gr.HighlightedText(), allow_flagging="never")
+#iface.launch()
+
+iface = gr.Interface(fn=get_sustainability, inputs=[gr.inputs.Textbox(label='SEARCH QUERY'),gr.inputs.file(label='TXT FILE')], title="CONBERT",description="SUSTAINABILITY TOOL",theme='hugging face',article='Article', outputs=[gr.outputs.Textbox(label='Answer'),gr.outputs.Textbox(label='Summary')], allow_flagging="never")
 iface.launch()