Spaces:
Running
Running
| import os | |
| import mimetypes | |
| import requests | |
| import tempfile | |
| import gradio as gr | |
| from openai import AzureOpenAI | |
| import re | |
| import json | |
| from transformers import pipeline | |
| import matplotlib.pyplot as plt | |
| import plotly.express as px | |
| client = AzureOpenAI() | |
| class SentimentAnalyzer: | |
| def __init__(self): | |
| self.model="facebook/bart-large-mnli" | |
| def analyze_sentiment(self, text): | |
| pipe = pipeline("zero-shot-classification", model=self.model) | |
| label=["positive","negative","neutral"] | |
| result = pipe(text, label) | |
| sentiment_scores= {result['labels'][0]:result['scores'][0],result['labels'][1]:result['scores'][1],result['labels'][2]:result['scores'][2]} | |
| sentiment_scores_str = f"Positive: {sentiment_scores['positive']:.2f}, Neutral: {sentiment_scores['neutral']:.2f}, Negative: {sentiment_scores['negative']:.2f}" | |
| return sentiment_scores_str | |
| def emotion_analysis(self,text): | |
| 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", | |
| messages=conversation, | |
| temperature=1, | |
| max_tokens=60 | |
| ) | |
| message = response.choices[0].message.content | |
| print("sen",message) | |
| return message | |
| def analyze_sentiment_for_graph(self, text): | |
| pipe = pipeline("zero-shot-classification", model=self.model) | |
| label=["positive", "negative", "neutral"] | |
| result = pipe(text, label) | |
| sentiment_scores = { | |
| result['labels'][0]: result['scores'][0], | |
| result['labels'][1]: result['scores'][1], | |
| result['labels'][2]: result['scores'][2] | |
| } | |
| return sentiment_scores | |
| def emotion_analysis_for_graph(self,text): | |
| list_of_emotion=text.split(":") | |
| label=list_of_emotion[1] | |
| score=list_of_emotion[2] | |
| score_dict={ | |
| label:float(score) | |
| } | |
| print(score_dict) | |
| return score_dict | |
| class Summarizer: | |
| def __init__(self): | |
| # self.client = OpenAI() | |
| pass | |
| def generate_summary(self, text): | |
| 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}``` | |
| """} | |
| ] | |
| response = client.chat.completions.create( | |
| model="GPT-3", | |
| messages=conversation, | |
| temperature=1, | |
| max_tokens=100 | |
| ) | |
| message = response.choices[0].message.content | |
| return message | |
| history_state = gr.State() | |
| summarizer = Summarizer() | |
| sentiment = SentimentAnalyzer() | |
| class LangChain_Document_QA: | |
| def __init__(self): | |
| pass | |
| def _add_text(self,history, text): | |
| history = history + [(text, None)] | |
| history_state.value = history | |
| return history, gr.Textbox(value="", interactive=False) | |
| def _agent_text(self,text,history): | |
| history[-1][1] = text | |
| history_state.value = history | |
| return history | |
| def _chat_history(self): | |
| print("chat history",history_state.value) | |
| history = history_state.value | |
| formatted_history = " " | |
| for entry in history: | |
| customer_text, agent_text = entry | |
| formatted_history += f"Customer: {customer_text}\n" | |
| if agent_text: | |
| formatted_history += f"Agent: {agent_text}\n" | |
| return formatted_history | |
| def _display_history(self): | |
| formatted_history=self._chat_history() | |
| summary=summarizer.generate_summary(formatted_history) | |
| return summary | |
| def _display_graph(self,sentiment_scores): | |
| labels = sentiment_scores.keys() | |
| scores = sentiment_scores.values() | |
| fig = px.bar(x=scores, y=labels, orientation='h', color=labels, color_discrete_map={"Negative": "red", "Positive": "green", "Neutral": "gray"}) | |
| fig.update_traces(texttemplate='%{x:.2f}%', textposition='outside') | |
| fig.update_layout(height=500, width=200) | |
| return fig | |
| def _history_of_chat(self): | |
| history = history_state.value | |
| formatted_history = "" | |
| client="" | |
| agent="" | |
| for entry in history: | |
| customer_text, agent_text = entry | |
| client+=customer_text | |
| formatted_history += f"Customer: {customer_text}\n" | |
| if agent_text: | |
| agent+=agent_text | |
| formatted_history += f"Agent: {agent_text}\n" | |
| return client,agent | |
| def _suggested_answer(self,history,text): | |
| self._add_text(history,text) | |
| text_history = self._chat_history() | |
| file_path = "vodafone_customer_details.json" | |
| with open(file_path) as file: | |
| 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", | |
| messages=conversation, | |
| temperature=0, | |
| max_tokens=100 | |
| ) | |
| message = response.choices[0].message.content | |
| print("message",message) | |
| if ":" in message: | |
| message = re.sub(r'^.*:', '', message) | |
| history.append((text, message)) | |
| else: | |
| history.append((text, message)) | |
| return "",message | |
| def _text_box(self,customer_emotion,agent_emotion,agent_sentiment_score,customer_sentiment_score): | |
| agent_score = ", ".join([f"{key}: {value:.2f}" for key, value in agent_sentiment_score.items()]) | |
| customer_score = ", ".join([f"{key}: {value:.2f}" for key, value in customer_sentiment_score.items()]) | |
| return f"customer_emotion:{customer_emotion}\nagent_emotion:{agent_emotion}\nAgent_Sentiment_score:{agent_score}\nCustomer_sentiment_score:{customer_score}" | |
| def _on_sentiment_btn_click(self): | |
| client,agent=self._history_of_chat() | |
| customer_emotion=sentiment.emotion_analysis(client) | |
| customer_sentiment_score = sentiment.analyze_sentiment_for_graph(client) | |
| agent_emotion=sentiment.emotion_analysis(agent) | |
| agent_sentiment_score = sentiment.analyze_sentiment_for_graph(agent) | |
| scores=self._text_box(customer_emotion,agent_emotion,agent_sentiment_score,customer_sentiment_score) | |
| customer_fig=self._display_graph(customer_sentiment_score) | |
| customer_fig.update_layout(title="Sentiment Analysis",width=800) | |
| agent_fig=self._display_graph(agent_sentiment_score) | |
| agent_fig.update_layout(title="Sentiment Analysis",width=800) | |
| agent_emotion_score = sentiment.emotion_analysis_for_graph(agent_emotion) | |
| agent_emotion_fig=self._display_graph(agent_emotion_score) | |
| agent_emotion_fig.update_layout(title="Emotion Analysis",width=800) | |
| customer_emotion_score = sentiment.emotion_analysis_for_graph(customer_emotion) | |
| customer_emotion_fig=self._display_graph(customer_emotion_score) | |
| customer_emotion_fig.update_layout(title="Emotion Analysis",width=800) | |
| return scores,customer_fig,agent_fig,customer_emotion_fig,agent_emotion_fig | |
| def clear_func(self): | |
| history_state = gr.State([]) | |
| def gradio_interface(self): | |
| with gr.Blocks(css="style.css",theme="snehilsanyal/scikit-learn") as demo: | |
| with gr.Row(): | |
| gr.HTML("""<center><img src="https://hakunamatatatech.com/wp-content/uploads/2019/06/logohms-160x4.png" alt="Image"></center>""") | |
| with gr.Row(): | |
| gr.HTML("""<center><h1 style="color:#f26d25">Generative AI CRM ChatBot</h1></center>""") | |
| with gr.Row(): | |
| gr.HTML("<br>") | |
| chatbot = gr.Chatbot().style(height=300) | |
| with gr.Row(): | |
| with gr.Column(scale=0.50): | |
| txt = gr.Textbox( | |
| show_label=False, | |
| placeholder="Customer", | |
| ).style(container=False) | |
| with gr.Column(scale=0.50): | |
| txt2 = gr.Textbox( | |
| show_label=False, | |
| placeholder="Agent", | |
| ).style(container=False) | |
| with gr.Column(scale=0.40): | |
| txt3 =gr.Textbox( | |
| show_label=False, | |
| placeholder="Chatbot_Suggestion", | |
| ).style(container=False) | |
| with gr.Column(scale=0.10, min_width=0): | |
| button=gr.Button( | |
| value="🚀" | |
| ) | |
| with gr.Row(scale=0.50): | |
| emptyBtn = gr.Button( | |
| "🧹 New Conversation", | |
| ) | |
| with gr.Row(): | |
| with gr.Column(scale=0.40): | |
| txt4 =gr.Textbox( | |
| show_label=False, | |
| lines=4, | |
| placeholder="Summary", | |
| ).style(container=False) | |
| with gr.Column(scale=0.10, min_width=0): | |
| end_btn=gr.Button( | |
| value="End" | |
| ) | |
| with gr.Column(scale=0.40): | |
| txt5 =gr.Textbox( | |
| show_label=False, | |
| lines=4, | |
| placeholder="Sentiment", | |
| ).style(container=False) | |
| with gr.Column(scale=0.10, min_width=0): | |
| Sentiment_btn=gr.Button( | |
| value="📊",callback=self._on_sentiment_btn_click | |
| ) | |
| with gr.Row(): | |
| gr.HTML("""<center><h1 style="color:#fff">Sentiment and Emotion Score Graph</h1></center>""") | |
| with gr.Row(): | |
| with gr.Column(scale=0.70, min_width=0): | |
| plot =gr.Plot(label="Customer", size=(500, 600)) | |
| with gr.Row(): | |
| with gr.Column(scale=0.70, min_width=0): | |
| plot_2 =gr.Plot(label="Agent", size=(500, 600)) | |
| with gr.Row(): | |
| with gr.Column(scale=0.70, min_width=0): | |
| plot_3 =gr.Plot(label="Customer_Emotion", size=(500, 600)) | |
| with gr.Row(): | |
| 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, [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,[],[]) | |
| emptyBtn.click(lambda: None, None, chatbot, queue=False) | |
| Sentiment_btn.click(self._on_sentiment_btn_click,[],[txt5,plot,plot_2,plot_3,plot_4]) | |
| demo.launch(debug = True) | |
| document_qa =LangChain_Document_QA() | |
| document_qa.gradio_interface() |