| from streamlit_webrtc import webrtc_streamer, WebRtcMode, AudioProcessorBase |
| from sentiment_analysis import analyze_sentiment, transcribe_with_chunks |
| from product_recommender import ProductRecommender |
| from objection_handler import ObjectionHandler |
| from google_sheets import fetch_call_data, store_data_in_sheet |
| from sentence_transformers import SentenceTransformer |
| from env_setup import config |
| import re |
| import uuid |
| import pandas as pd |
| import plotly.express as px |
| import streamlit as st |
| import numpy as np |
| import queue |
| import threading |
|
|
| |
| objection_handler = ObjectionHandler("objections.csv") |
| product_recommender = ProductRecommender("recommendations.csv") |
| model = SentenceTransformer('all-MiniLM-L6-v2') |
|
|
| |
| transcription_queue = queue.Queue() |
|
|
| def generate_comprehensive_summary(chunks): |
| |
| pass |
|
|
| def is_valid_input(text): |
| |
| pass |
|
|
| def is_relevant_sentiment(sentiment_score): |
| |
| pass |
|
|
| def calculate_overall_sentiment(sentiment_scores): |
| |
| pass |
|
|
| def handle_objection(text): |
| query_embedding = model.encode([text]) |
| distances, indices = objection_handler.index.search(query_embedding, 1) |
| if distances[0][0] < 1.5: |
| responses = objection_handler.handle_objection(text) |
| return "\n".join(responses) if responses else "No objection response found." |
| return "No objection response found." |
|
|
| class AudioProcessor(AudioProcessorBase): |
| def __init__(self): |
| self.sr = 16000 |
| self.q = transcription_queue |
|
|
| def recv(self, frame): |
| audio_data = frame.to_ndarray() |
| audio_bytes = (audio_data * 32767).astype(np.int16).tobytes() |
| |
| print(f"Audio data shape: {audio_data.shape}") |
| print(f"Audio data sample: {audio_data[:10]}") |
| |
| text = self.transcribe_audio(audio_bytes) |
| if text: |
| self.q.put(text) |
|
|
| return frame |
|
|
| def transcribe_audio(self, audio_bytes): |
| try: |
| chunks = transcribe_with_chunks({}) |
| if chunks: |
| return chunks[-1][0] |
| except Exception as e: |
| print(f"Error transcribing audio: {e}") |
| return None |
|
|
| def real_time_analysis(): |
| st.info("Listening... Say 'stop' to end the process.") |
|
|
| webrtc_ctx = webrtc_streamer( |
| key="real-time-audio", |
| mode=WebRtcMode.SENDONLY, |
| audio_processor_factory=AudioProcessor, |
| media_stream_constraints={"audio": True, "video": False}, |
| ) |
|
|
| if webrtc_ctx.state.playing: |
| while not transcription_queue.empty(): |
| text = transcription_queue.get() |
| st.write(f"*Recognized Text:* {text}") |
|
|
| sentiment, score = analyze_sentiment(text) |
| st.write(f"*Sentiment:* {sentiment} (Score: {score})") |
|
|
| objection_response = handle_objection(text) |
| st.write(f"*Objection Response:* {objection_response}") |
|
|
| recommendations = [] |
| if is_valid_input(text) and is_relevant_sentiment(score): |
| query_embedding = model.encode([text]) |
| distances, indices = product_recommender.index.search(query_embedding, 1) |
|
|
| if distances[0][0] < 1.5: |
| recommendations = product_recommender.get_recommendations(text) |
|
|
| if recommendations: |
| st.write("*Product Recommendations:*") |
| for rec in recommendations: |
| st.write(rec) |
|
|
| def fetch_data_and_display(): |
| try: |
| st.header("Call Summaries and Sentiment Analysis") |
| data = fetch_call_data(config["google_sheet_id"]) |
| |
| print(f"Fetched data: {data}") |
| |
| if data.empty: |
| st.warning("No data available in the Google Sheet.") |
| else: |
| sentiment_counts = data['Sentiment'].value_counts() |
| |
| col1, col2 = st.columns(2) |
| with col1: |
| st.subheader("Sentiment Distribution") |
| fig_pie = px.pie( |
| values=sentiment_counts.values, |
| names=sentiment_counts.index, |
| title='Call Sentiment Breakdown', |
| color_discrete_map={ |
| 'POSITIVE': 'green', |
| 'NEGATIVE': 'red', |
| 'NEUTRAL': 'blue' |
| } |
| ) |
| st.plotly_chart(fig_pie) |
|
|
| with col2: |
| st.subheader("Sentiment Counts") |
| fig_bar = px.bar( |
| x=sentiment_counts.index, |
| y=sentiment_counts.values, |
| title='Number of Calls by Sentiment', |
| labels={'x': 'Sentiment', 'y': 'Number of Calls'}, |
| color=sentiment_counts.index, |
| color_discrete_map={ |
| 'POSITIVE': 'green', |
| 'NEGATIVE': 'red', |
| 'NEUTRAL': 'blue' |
| } |
| ) |
| st.plotly_chart(fig_bar) |
|
|
| st.subheader("All Calls") |
| display_data = data.copy() |
| display_data['Summary Preview'] = display_data['Summary'].str[:100] + '...' |
| st.dataframe(display_data[['Call ID', 'Chunk', 'Sentiment', 'Summary Preview', 'Overall Sentiment']]) |
|
|
| unique_call_ids = data[data['Call ID'] != '']['Call ID'].unique() |
| call_id = st.selectbox("Select a Call ID to view details:", unique_call_ids) |
|
|
| call_details = data[data['Call ID'] == call_id] |
| if not call_details.empty: |
| st.subheader("Detailed Call Information") |
| st.write(f"**Call ID:** {call_id}") |
| st.write(f"**Overall Sentiment:** {call_details.iloc[0]['Overall Sentiment']}") |
|
|
| st.subheader("Full Call Summary") |
| st.text_area("Summary:", |
| value=call_details.iloc[0]['Summary'], |
| height=200, |
| disabled=True) |
|
|
| st.subheader("Conversation Chunks") |
| for _, row in call_details.iterrows(): |
| if pd.notna(row['Chunk']): |
| st.write(f"**Chunk:** {row['Chunk']}") |
| st.write(f"**Sentiment:** {row['Sentiment']}") |
| st.write("---") |
| else: |
| st.error("No details available for the selected Call ID.") |
| except Exception as e: |
| st.error(f"Error loading dashboard: {e}") |
|
|
| def run_app(): |
| st.set_page_config(page_title="Sales Call Assistant", layout="wide") |
| st.title("AI Sales Call Assistant") |
| st.warning("The space is currently not working due to issues with real-time transcription and data fetching from Google Sheets. We are working on resolving these issues.") |
|
|
| st.markdown(""" |
| <style> |
| /* Header Container Styling */ |
| .header-container { |
| background: linear-gradient(135deg, #F8F9FA 0%, #E9ECEF 100%); |
| padding: 20px; |
| border-radius: 15px; |
| margin-bottom: 30px; |
| box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1); |
| } |
| |
| /* Section Container Styling */ |
| .section { |
| background: linear-gradient(135deg, #FFFFFF 0%, #F8F9FA 100%); |
| padding: 25px; |
| border-radius: 15px; |
| margin-bottom: 30px; |
| box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1); |
| } |
| |
| /* Header Text Styling */ |
| .header { |
| font-size: 2.5em; |
| font-weight: 800; |
| text-align: center; |
| background: linear-gradient(120deg, #0D6EFD 0%, #0B5ED7 100%); |
| -webkit-background-clip: text; |
| -webkit-text-fill-color: transparent; |
| margin: 0; |
| padding: 10px; |
| letter-spacing: 1px; |
| } |
| |
| /* Subheader Styling */ |
| .subheader { |
| font-size: 1.8em; |
| font-weight: 600; |
| background: linear-gradient(120deg, #0D6EFD 0%, #0B5ED7 100%); |
| -webkit-background-clip: text; |
| -webkit-text-fill-color: transparent; |
| margin-top: 20px; |
| margin-bottom: 10px; |
| text-align: left; |
| } |
| |
| /* Table Container Styling */ |
| .table-container { |
| background: linear-gradient(135deg, #FFFFFF 0%, #F8F9FA 100%); |
| padding: 20px; |
| border-radius: 10px; |
| margin: 20px 0; |
| box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1); |
| } |
| |
| /* Dark mode adjustments */ |
| @media (prefers-color-scheme: dark) { |
| .header-container { |
| background: linear-gradient(135deg, #212529 0%, #343A40 100%); |
| } |
| |
| .section { |
| background: linear-gradient(135deg, #212529 0%, #2B3035 100%); |
| } |
| |
| .table-container { |
| background: linear-gradient(135deg, #212529 0%, #2B3035 100%); |
| } |
| |
| .header { |
| background: linear-gradient(120deg, #6EA8FE 0%, #9EC5FE 100%); |
| -webkit-background-clip: text; |
| -webkit-text-fill-color: transparent; |
| } |
| |
| .subheader { |
| background: linear-gradient(120deg, #6EA8FE 0%, #9EC5FE 100%); |
| -webkit-background-clip: text; |
| -webkit-text-fill-color: transparent; |
| } |
| } |
| |
| /* Button Styling */ |
| .stButton > button { |
| background: linear-gradient(135deg, #2196F3 0%, #1976D2 100%); |
| color: white; |
| border: none; |
| padding: 10px 20px; |
| border-radius: 5px; |
| transition: all 0.3s ease; |
| } |
| |
| .stButton > button:hover { |
| background: linear-gradient(135deg, #1976D2 0%, #1565C0 100%); |
| box-shadow: 0 4px 6px rgba(0, 0, 0, 0.2); |
| } |
| |
| /* Tab Styling */ |
| .stTabs [data-baseweb="tab-list"] { |
| gap: 24px; |
| background: linear-gradient(135deg, #F8F9FA 0%, #E9ECEF 100%); |
| padding: 10px; |
| border-radius: 10px; |
| } |
| |
| .stTabs [data-baseweb="tab"] { |
| background-color: transparent; |
| border-radius: 4px; |
| color: #1976D2; |
| font-weight: 600; |
| padding: 10px 16px; |
| } |
| |
| .stTabs [aria-selected="true"] { |
| background: linear-gradient(120deg, #2196F3 0%, #1976D2 100%); |
| color: white; |
| } |
| |
| /* Dark mode tab adjustments */ |
| @media (prefers-color-scheme: dark) { |
| .stTabs [data-baseweb="tab-list"] { |
| background: linear-gradient(135deg, #212529 0%, #343A40 100%); |
| } |
| |
| .stTabs [data-baseweb="tab"] { |
| color: #82B1FF; |
| } |
| |
| .stTabs [aria-selected="true"] { |
| background: linear-gradient(120deg, #448AFF 0%, #2979FF 100%); |
| } |
| } |
| |
| /* Message Styling */ |
| .success { |
| background: linear-gradient(135deg, #43A047 0%, #2E7D32 100%); |
| color: white; |
| padding: 10px; |
| border-radius: 5px; |
| margin: 10px 0; |
| } |
| |
| .error { |
| background: linear-gradient(135deg, #E53935 0%, #C62828 100%); |
| color: white; |
| padding: 10px; |
| border-radius: 5px; |
| margin: 10px 0; |
| } |
| |
| .warning { |
| background: linear-gradient(135deg, #FB8C00 0%, #F57C00 100%); |
| color: white; |
| padding: 10px; |
| border-radius: 5px; |
| margin: 10px 0; |
| } |
| </style> |
| """, unsafe_allow_html=True) |
| |
|
|
|
|
| st.sidebar.title("Navigation") |
| app_mode = st.sidebar.radio("Choose a mode:", ["Real-Time Call Analysis", "Dashboard"]) |
|
|
| if app_mode == "Real-Time Call Analysis": |
| st.header("Real-Time Sales Call Analysis") |
| if st.button("Start Listening"): |
| real_time_analysis() |
|
|
| elif app_mode == "Dashboard": |
| st.header("Call Summaries and Sentiment Analysis") |
| try: |
| data = fetch_call_data(config["google_sheet_id"]) |
| if data.empty: |
| st.warning("No data available in the Google Sheet.") |
| else: |
| sentiment_counts = data['Sentiment'].value_counts() |
|
|
| product_mentions = filter_product_mentions(data[['Chunk']].values.tolist(), product_titles) |
| product_mentions_df = pd.DataFrame(list(product_mentions.items()), columns=['Product', 'Count']) |
|
|
| col1, col2 = st.columns(2) |
| with col1: |
| st.subheader("Sentiment Distribution") |
| fig_bar = px.bar( |
| x=sentiment_counts.index, |
| y=sentiment_counts.values, |
| title='Number of Calls by Sentiment', |
| labels={'x': 'Sentiment', 'y': 'Number of Calls'}, |
| color=sentiment_counts.index, |
| color_discrete_map={ |
| 'POSITIVE': 'green', |
| 'NEGATIVE': 'red', |
| 'NEUTRAL': 'blue' |
| } |
| ) |
| st.plotly_chart(fig_bar) |
|
|
| with col2: |
| st.subheader("Most Mentioned Products") |
| fig_products = px.pie( |
| values=product_mentions_df['Count'], |
| names=product_mentions_df['Product'], |
| title='Most Mentioned Products' |
| ) |
| st.plotly_chart(fig_products) |
|
|
| st.subheader("All Calls") |
| display_data = data.copy() |
| display_data['Summary Preview'] = display_data['Summary'].str[:100] + '...' |
| st.dataframe(display_data[['Call ID', 'Chunk', 'Sentiment', 'Summary Preview', 'Overall Sentiment']]) |
|
|
| unique_call_ids = data[data['Call ID'] != '']['Call ID'].unique() |
| call_id = st.selectbox("Select a Call ID to view details:", unique_call_ids) |
|
|
| call_details = data[data['Call ID'] == call_id] |
| if not call_details.empty: |
| st.subheader("Detailed Call Information") |
| st.write(f"**Call ID:** {call_id}") |
| st.write(f"**Overall Sentiment:** {call_details.iloc[0]['Overall Sentiment']}") |
| |
| st.subheader("Full Call Summary") |
| st.text_area("Summary:", |
| value=call_details.iloc[0]['Summary'], |
| height=200, |
| disabled=True) |
| |
| else: |
| st.error("No details available for the selected Call ID.") |
| except Exception as e: |
| st.error(f"Error loading dashboard: {e}") |
|
|
| if __name__ == "__main__": |
| run_app() |
