Update app.py

app.py

@@ -12,12 +12,13 @@ from transformers import pipeline
 import matplotlib.pyplot as plt
 import plotly.express as px
 
+# client = OpenAI()
+
 class SentimentAnalyzer:
     def __init__(self):
-        
         self.model="facebook/bart-large-mnli" 
 
-        self.client = OpenAI()
+        # self.client = OpenAI()
         
     def analyze_sentiment(self, text):
         pipe = pipeline("zero-shot-classification", model=self.model)
@@ -28,17 +29,24 @@ class SentimentAnalyzer:
         return sentiment_scores_str
         
     def emotion_analysis(self,text):
-        prompt = f""" Your task is to analyze {text} and predict the emotion using scores. Emotions are categorized into the following list: Sadness, Happiness, Joy, Fear, Disgust, and Anger. You need to provide the emotion with the highest score. The scores should be in the range of 0.0 to 1.0, where 1.0 represents the highest intensity of the emotion.
-Please analyze the text and provide the output in the following format: emotion: score [with one result having the highest score]."""
-        response = self.client.completions.create(
-            model="text-davinci-003",
-            prompt=prompt,
+        client = OpenAI()
+        print(text,"lkdjrglk") 
+        conversation = [
+          {"role": "system", "content": """You are a Emotion Analyser.Your task is to analyze and predict the emotion using scores. Emotions are categorized into the following list: Sadness, Happiness, Joy, Fear, Disgust, and Anger. You need to provide the emotion with the highest score. The scores should be in the range of 0.0 to 1.0, where 1.0 represents the highest intensity of the emotion.
+            Please analyze the text and provide the output in the following format: emotion: score [with one result having the highest score]."""},
+          {"role": "user", "content": f"""
+            input text{text}
+            """}
+            ]
+        response = client.chat.completions.create(
+            model="gpt-3.5-turbo",
+            messages=conversation,
             temperature=1,
             max_tokens=60
         )
 
-        message = response.choices[0].text.strip().replace("\n","")
-        print(message)
+        message = response.choices[0].message.content
+        print("sen",message)
         return message
 
     def analyze_sentiment_for_graph(self, text):
@@ -55,8 +63,8 @@ Please analyze the text and provide the output in the following format: emotion:
     def emotion_analysis_for_graph(self,text):
 
         list_of_emotion=text.split(":")
-        label=list_of_emotion[0]
-        score=list_of_emotion[1]
+        label=list_of_emotion[1]
+        score=list_of_emotion[2]
         score_dict={
           label:float(score)
         }
@@ -67,21 +75,26 @@ Please analyze the text and provide the output in the following format: emotion:
 class Summarizer:
     
     def __init__(self):
-        self.client = OpenAI()       
+        # self.client = OpenAI()      
+        pass 
         
     def generate_summary(self, text):
-        model_engine = "text-davinci-003"
-        prompt = f"""summarize the following conversation delimited by triple backticks.
+        client = OpenAI() 
+        conversation = [
+          {"role": "system", "content": "You are a Summarizer"},
+          {"role": "user", "content": f"""summarize the following conversation delimited by triple backticks.
                      write within 30 words.
-                     ```{text}``` """
-        completions = self.client.completions.create(
-            model=model_engine,
-            prompt=prompt,
-            max_tokens=60,
-            n=1,
-            temperature=0
+                     ```{text}```
+            """}
+            ]
+        response = client.chat.completions.create(
+            model="gpt-3.5-turbo",
+            messages=conversation,
+            temperature=1,
+            max_tokens=100
         )
-        message = completions.choices[0].text.strip()
+
+        message = response.choices[0].message.content
         return message
 
 history_state = gr.State()
@@ -91,20 +104,33 @@ sentiment = SentimentAnalyzer()
 class LangChain_Document_QA:
 
     def __init__(self):
-        self.client = OpenAI() 
+        # self.client = OpenAI()
+        pass 
         
     def _add_text(self,history, text):
+
         history = history + [(text, None)]
         history_state.value = history
-        return history,gr.update(value="", interactive=False)
 
-    def _agent_text(self,history, text):
-        response = text
-        history[-1][1] = response
+        return history, gr.Textbox(value="", interactive=False)
+
+    def _agent_text(self,text,history):
+        # respond = []
+        # print("history",history)
+        # print(type(history))
+        # text = [text for _, text in history][-1]
+        # print("agent",history_state.value)
+        
+        history[-1][1] = text
         history_state.value = history
+        # message = [tup[-1] for tup in history]
+        # respond.append(("", message))
+        # print(respond)
         return history
 
+
     def _chat_history(self):
+        print("chat history",history_state.value)
         history = history_state.value
         formatted_history = " "
         for entry in history:
@@ -142,31 +168,39 @@ class LangChain_Document_QA:
         return client,agent
 
 
-    def _suggested_answer(self,text):
-        try:
-            history = self._chat_history()
-            start_sequence = "\nCustomer:"
-            restart_sequence = "\nVodafone Customer Relationship Manager:"
-            prompt = 'your task is make a conversation between a customer and vodafone telecom customer relationship manager.'
+    def _suggested_answer(self,history,text):
+        # try:
+            client = OpenAI()
+            self._add_text(history,text)
+            text_history = self._chat_history()
+            # start_sequence = "\nCustomer:"
+            # restart_sequence = "\nVodafone Customer Care:"
             file_path = "vodafone_customer_details.json"
             with open(file_path) as file:
-                customer_details = json.load(file)
-            prompt = f"""{history}{start_sequence}{text}{restart_sequence} if customer ask any information take it from {customer_details}.
-                      if customer say thanks or thankyou tone related messages You should not ask anything to end the conversation with greetings tone.
-            """
-            response = self.client.completions.create(
-                model="text-davinci-003",
-                prompt=prompt,
+                context = json.load(file)
+            conversation = [
+              {"role": "system", "content": f"You Are Vodafone Sim AI Chatbot. Use the following pieces of context{context} to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. Use three sentences maximum. Keep the answer as concise as possible. if user say hi, hello you say welcome greetings like hi, hello. if user say thankyou, thanks tone you say thanking Greetings like You're welcome!.conversation history{context}"},
+              {"role": "user", "content": f""" this is the user question:{text}..
+                """}
+                ]
+            response = client.chat.completions.create(
+                model="gpt-3.5-turbo",
+                messages=conversation,
                 temperature=0,
-                max_tokens=500
+                max_tokens=100
             )
-
-            message = response.choices[0].text.strip()
+            
+            message = response.choices[0].message.content
+            print("message",message)
+            
             if  ":" in message:
               message = re.sub(r'^.*:', '', message)
-            return message.strip()
-        except:
-            return "Hi, How can I help you?"
+              history.append((text, message))
+            else:
+              history.append((text, message))
+            return "",message
+        # except:
+        #     return "Hi, How can I help you?"
     
 
     def _text_box(self,customer_emotion,agent_emotion,agent_sentiment_score,customer_sentiment_score):
@@ -205,7 +239,7 @@ class LangChain_Document_QA:
 
 
     def clear_func(self):
-      history_state.clear()
+      history_state = gr.State([])
 
 
     def gradio_interface(self):
@@ -217,7 +251,7 @@ class LangChain_Document_QA:
             gr.HTML("""<center><h1 style="color:#f26d25">Generative AI CRM ChatBot</h1></center>""")
           with gr.Row():
             gr.HTML("<br>")
-          chatbot = gr.Chatbot([], elem_id="chatbot").style(height=300)
+          chatbot = gr.Chatbot().style(height=300)
           with gr.Row():
               with gr.Column(scale=0.50):
                   txt = gr.Textbox(
@@ -280,13 +314,12 @@ class LangChain_Document_QA:
               with gr.Column(scale=0.70, min_width=0):
                   plot_4 =gr.Plot(label="Agent_Emotion", size=(500, 600))
 
-
           txt_msg = txt.submit(self._add_text, [chatbot, txt], [chatbot, txt])
-          txt_msg.then(lambda: gr.update(interactive=True), None, [txt])
-          txt.submit(self._suggested_answer,txt,txt3)
-          button.click(self._agent_text, [chatbot,txt3], chatbot)
-          txt2.submit(self._agent_text, [chatbot, txt2], chatbot).then(
-              self._agent_text, [chatbot, txt2], chatbot
+          # txt_msg.then(lambda: gr.update(interactive=True), None, [txt])
+          txt.submit(self._suggested_answer, [chatbot, txt], [txt,txt3])
+          button.click(self._agent_text, [txt3,chatbot], chatbot)
+          txt2.submit(self._agent_text, [txt2,chatbot ], chatbot).then(
+              self._agent_text, [txt2,chatbot], chatbot
           )
           end_btn.click(self._display_history, [], txt4)
           emptyBtn.click(self.clear_func,[],[])