Update app.py

app.py

@@ -19,7 +19,7 @@ class SentimentAnalyzer:
         # self.model="facebook/bart-large-mnli"
         openai.api_key=os.getenv("OPENAI_API_KEY")
     def emotion_analysis(self,text):
-        prompt = f""" Your task is find the top 3 emotion for this converstion {text}: <Sadness, Happiness, Fear, Disgust, Anger> and it's emotion score for the Mental Healthcare Doctor Chatbot and patient conversation text.\
+        prompt = f""" Your task is find the top 3 emotion for this converstion {text}: <Sadness, Happiness, Fear, Disgust, Anger> and it's emotion score for the Human Resource Assistant Chatbot and Job Seeker conversation text.\
         you are analyze the text and provide the output in the following list format heigher to lower order: ["emotion1","emotion2","emotion3"][score1,score2,score3]''' [with top 3 result having 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.
         """
@@ -36,7 +36,7 @@ class SentimentAnalyzer:
         return message
 
     def analyze_sentiment_for_graph(self, text):
-        prompt = f""" Your task is find the setiments for this converstion {text} : <labels = positive, negative, neutral> and it's sentiment score for the Mental Healthcare Doctor Chatbot and patient conversation text.\
+        prompt = f""" Your task is find the setiments for this converstion {text} : <labels = positive, negative, neutral> and it's sentiment score for the Human Resource Assistant Chatbot and Job Seeker conversation text.\
         you are analyze the text and provide the output in the following json format heigher to lower order: '''["label1","label2","label3"][score1,score2,score3]'''
         """
         response = openai.Completion.create(
@@ -115,9 +115,9 @@ class LangChain_Document_QA:
         formatted_history = " "
         for entry in history:
             customer_text, agent_text = entry
-            formatted_history += f"Patient: {customer_text}\n"
+            formatted_history += f"Job Seeker: {customer_text}\n"
             if agent_text:
-                formatted_history += f"Mental Healthcare Doctor Chatbot: {agent_text}\n"
+                formatted_history += f"Human Resource Assistant Chatbot: {agent_text}\n"
         return formatted_history
 
     def _display_history(self):
@@ -144,32 +144,28 @@ class LangChain_Document_QA:
         for entry in history:
             customer_text, agent_text = entry
             client+=customer_text
-            formatted_history += f"Patient: {customer_text}\n"
+            formatted_history += f"Job Seeker: {customer_text}\n"
             if agent_text:
                 agent+=agent_text
-                formatted_history += f"Mental Healthcare Doctor Chatbot: {agent_text}\n"
+                formatted_history += f"Human Resource Assistant Chatbot: {agent_text}\n"
         return client,agent
 
 
     def _suggested_answer(self,text):
       try:
         history = self._chat_history()
-        try:
-          file_path = "patient_details.json"
-          with open(file_path) as file:
-              patient_details = json.load(file)
-        except:
-          pass
-
-        prompt = f"""Analyse the patient json If asked for information take it from {patient_details} \
-            you first get patient details : <get name,age,gender,contact,address from patient> if not match patient json information start new chat else match patient \
-            json information ask previous: <description,symptoms,diagnosis,treatment talk about patient> As an empathic AI Mental Healthcare Doctor Chatbot, provide effective solutions to patients' mental health concerns. \
-            first start the conversation ask existing patient or new patient. if new patient get name,age,gender,contact,address from the patient and start. \
-            if existing customer get name,age,gender,contact,address details and start the chat about existing issues and current issues. \
-            if patient say thanking tone message to end the conversation with a thanking greeting when the patient expresses gratitude. \
+        prompt = f"""
+            Task: conversation between Human resource assistant and job seeker
+            In this roleplay scenario, you are an AI-powered Human Resource (HR) assistant that's been developed to assist job seekers of all backgrounds, skills, and experiences. Your primary function is to guide these individuals through various aspects of their job search process, help them prepare for interviews, and enhance their academic and personal qualifications. \
+            As a participant in the dialogue, you'll:
+            Respond to job-related queries and provide useful information about the job market, potential companies, and the interview process.
+            Offer tips on how to approach companies and how to understand the basics of HR interviews. This includes advice on how to communicate effectively, demonstrate relevant skills, and present oneself professionally.
+            Develop a plan to help job seekers improve their academic qualifications and personal skills that may boost their chances of getting hired.
+            The conversation will continue until the job seeker expresses their gratitude and wishes to end the conversation. At that point, you as the HR assistant will close the interaction with a warm and appreciative response.
+            Remember, your objective is to build confidence in job seekers, guide them towards their career goals, and help them navigate the often daunting world of job searching and interviewing. Be empathetic, informative, and supportive.
             Chat History:['''{history}'''] 
-            Patient: ['''{text}''']
-            Perform as Mental Healthcare Doctor Chatbot
+            Job Seeker: ['''{text}''']
+            Perform as Human Resource Assistant Chatbot
                  """
         response = openai.Completion.create(
             model="text-davinci-003",
@@ -217,26 +213,26 @@ class LangChain_Document_QA:
       history_state.clear()
 
     def gradio_interface(self):
-      with gr.Blocks(css="style.css",theme=gr.themes.Glass()) as demo:
+      with gr.Blocks(css="style.css",theme=gr.themes.Soft()) as demo:
           with gr.Row():
-            gr.HTML("""<center><img class="image" src="https://www.syrahealth.com/images/SyraHealth_Logo_Dark.svg" alt="Image" width="210" height="210"></center>
-            """)
+            gr.HTML("""<img class="leftimage" align="left" src="https://upload.wikimedia.org/wikipedia/commons/thumb/1/10/Randstad_Logo.svg/2560px-Randstad_Logo.svg.png" alt="Image" width="210" height="210">
+            <img align="right" class="rightimage brightness" src="https://workllama.com/wp-content/uploads/2022/05/WL_Logo.svg" alt="Image" width="230" height="230" >
+            <br>""")
           with gr.Row():
-            gr.HTML("""<center><h1>AI Mental Healthcare ChatBot</h1></center>""")
+            gr.HTML("""<center><h1>HR Assistant ChatBot</h1></center>""")
           chatbot = gr.Chatbot([], elem_id="chatbot").style(height=360)
           with gr.Row():
               with gr.Column(scale=0.8):
                   txt = gr.Textbox(
                       show_label=False,
-                      placeholder="Patient").style(container=False)
-            
+                      placeholder="Job_Seeker").style(container=False)
               with gr.Column(scale=0.2):
                   emptyBtn = gr.Button("🧹 Clear")
           with gr.Row():
             with gr.Column(scale=0.80):
                 txt3 =gr.Textbox(
                       show_label=False,
-                      placeholder="AI Healthcare Suggesstion").style(container=False)
+                      placeholder="HR Assistant Suggesstion").style(container=False)
             with gr.Column(scale=0.20, min_width=0):
                 button=gr.Button(value="🚀send")
           with gr.Row():
@@ -259,10 +255,10 @@ class LangChain_Document_QA:
               gr.HTML("""<center><h1>Sentiment and Emotion Score Graph</h1></center>""")
           with gr.Row():
               with gr.Column(scale=1, min_width=0):
-                  plot =gr.Plot(label="Patient", size=(500, 600))
+                  plot =gr.Plot(label="Job_Seeker", size=(500, 600))
           with gr.Row():
               with gr.Column(scale=1, min_width=0):
-                  plot_3 =gr.Plot(label="Patient_Emotion", size=(500, 600))
+                  plot_3 =gr.Plot(label="Job_Seeker_Emotion", size=(500, 600))
 
 
           txt_msg = txt.submit(self._add_text, [chatbot, txt], [chatbot, txt])
@@ -275,7 +271,7 @@ class LangChain_Document_QA:
 
           Sentiment_btn.click(self._on_sentiment_btn_click,[],[txt5,plot,plot_3])
  
-      demo.title = "AI Mental Healthcare ChatBot"
+      demo.title = "AI HR ChatBot"
       demo.launch()
 document_qa =LangChain_Document_QA()
 document_qa.gradio_interface()