Upload app.py
Browse files
app.py
ADDED
@@ -0,0 +1,811 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
import numpy as np
|
4 |
+
import plotly.express as px
|
5 |
+
import plotly.graph_objects as go
|
6 |
+
from datetime import datetime, timedelta, date
|
7 |
+
import requests
|
8 |
+
import google.generativeai as genai
|
9 |
+
|
10 |
+
# Constants
|
11 |
+
ENGINEER_SALARY = 10000 # Monthly cost per engineer ($120K/year)
|
12 |
+
|
13 |
+
# Initialize session state variables
|
14 |
+
if 'startups' not in st.session_state:
|
15 |
+
st.session_state.startups = {} # Dictionary to store startup data
|
16 |
+
if 'current_startup' not in st.session_state:
|
17 |
+
st.session_state.current_startup = None # Currently selected startup
|
18 |
+
if 'current_page' not in st.session_state:
|
19 |
+
st.session_state.current_page = 'upload' # Default page
|
20 |
+
if 'insights_cache' not in st.session_state:
|
21 |
+
st.session_state.insights_cache = {}
|
22 |
+
if 'chat_history' not in st.session_state:
|
23 |
+
st.session_state.chat_history = [
|
24 |
+
{"role": "assistant", "content": "Hi! I'm your AI financial advisor. How can I help with your startup's finances?"}
|
25 |
+
]
|
26 |
+
|
27 |
+
# Setup page config and styling
|
28 |
+
st.set_page_config(page_title="StartupFinancePilot", page_icon="💰", layout="wide")
|
29 |
+
|
30 |
+
# Apply custom styling
|
31 |
+
st.markdown("""
|
32 |
+
<style>
|
33 |
+
.main-header {font-size: 2.5rem; color: #0066cc; margin-bottom: 0.5rem;}
|
34 |
+
.sub-header {font-size: 1.5rem; color: #5c5c5c; margin-bottom: 1.5rem;}
|
35 |
+
.metric-card {background-color: #f8f9fa; border-radius: 10px; padding: 20px; box-shadow: 0 4px 6px rgba(0,0,0,0.1);}
|
36 |
+
.metric-label {font-size: 1rem; color: #5c5c5c;}
|
37 |
+
.metric-value {font-size: 1.8rem; color: #0066cc; font-weight: bold;}
|
38 |
+
.good-metric {color: #28a745;}
|
39 |
+
.warning-metric {color: #ffc107;}
|
40 |
+
.danger-metric {color: #dc3545;}
|
41 |
+
.title-box {background: linear-gradient(45deg, #0066cc, #66b3ff); padding: 20px; border-radius: 10px;
|
42 |
+
margin-bottom: 20px; text-align: center; color: white;}
|
43 |
+
.ai-badge {display: inline-block; background-color: #0066cc; color: white; border-radius: 4px;
|
44 |
+
padding: 2px 6px; font-size: 0.7rem; font-weight: bold; margin-bottom: 8px;}
|
45 |
+
.insight-card, .advisor-card {background-color: #f8f9fa; border-radius: 10px; padding: 15px;
|
46 |
+
margin-bottom: 20px; box-shadow: 0 2px 4px rgba(0,0,0,0.05);}
|
47 |
+
div.stButton > button {width: 100%; padding: 10px; border: none; background-color: #E6F3FF;
|
48 |
+
color: #0066cc; border-radius: 10px; text-align: left; font-weight: bold;}
|
49 |
+
div.stButton > button:hover {background-color: #CCE5FF; color: #004080;}
|
50 |
+
</style>
|
51 |
+
""", unsafe_allow_html=True)
|
52 |
+
|
53 |
+
# AI Integration Functions
|
54 |
+
def initialize_gemini():
|
55 |
+
"""Initialize Google's Gemini AI with API key"""
|
56 |
+
try:
|
57 |
+
api_key = st.secrets.get("GEMINI_API_KEY", None)
|
58 |
+
if api_key:
|
59 |
+
genai.configure(api_key=api_key)
|
60 |
+
return True
|
61 |
+
else:
|
62 |
+
st.warning("Gemini API key not found. Using simulated responses.")
|
63 |
+
return False
|
64 |
+
except Exception as e:
|
65 |
+
st.error(f"Failed to initialize Gemini AI: {e}")
|
66 |
+
return False
|
67 |
+
|
68 |
+
def generate_ai_response(prompt, simulate=True):
|
69 |
+
"""Generate text using Google's Gemini AI"""
|
70 |
+
if simulate:
|
71 |
+
return "AI response simulation: Based on your financial data, I recommend focusing on extending runway, accelerating revenue growth, and preparing for your next funding round."
|
72 |
+
else:
|
73 |
+
try:
|
74 |
+
model = genai.GenerativeModel('gemini-pro')
|
75 |
+
response = model.generate_content(prompt)
|
76 |
+
return response.text
|
77 |
+
except Exception as e:
|
78 |
+
st.error(f"Error generating AI response: {e}")
|
79 |
+
return "Sorry, I couldn't generate a response at this time."
|
80 |
+
|
81 |
+
def generate_voice_response(text, simulate=True):
|
82 |
+
"""Generate voice response using ElevenLabs API"""
|
83 |
+
if simulate:
|
84 |
+
return None
|
85 |
+
else:
|
86 |
+
try:
|
87 |
+
api_key = st.secrets.get("ELEVENLABS_API_KEY", None)
|
88 |
+
if not api_key:
|
89 |
+
return None
|
90 |
+
|
91 |
+
url = "https://api.elevenlabs.io/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM" # Rachel voice
|
92 |
+
|
93 |
+
headers = {
|
94 |
+
"Accept": "audio/mpeg",
|
95 |
+
"Content-Type": "application/json",
|
96 |
+
"xi-api-key": api_key
|
97 |
+
}
|
98 |
+
|
99 |
+
data = {
|
100 |
+
"text": text,
|
101 |
+
"model_id": "eleven_monolingual_v1",
|
102 |
+
"voice_settings": {
|
103 |
+
"stability": 0.5,
|
104 |
+
"similarity_boost": 0.5
|
105 |
+
}
|
106 |
+
}
|
107 |
+
|
108 |
+
response = requests.post(url, json=data, headers=headers)
|
109 |
+
|
110 |
+
if response.status_code == 200:
|
111 |
+
return response.content
|
112 |
+
else:
|
113 |
+
st.error(f"Error with ElevenLabs API: {response.status_code}")
|
114 |
+
return None
|
115 |
+
|
116 |
+
except Exception as e:
|
117 |
+
st.error(f"Error generating voice response: {e}")
|
118 |
+
return None
|
119 |
+
|
120 |
+
# Utility Functions
|
121 |
+
def switch_page(page_name):
|
122 |
+
"""Function to switch between pages"""
|
123 |
+
st.session_state.current_page = page_name
|
124 |
+
st.rerun()
|
125 |
+
|
126 |
+
def calculate_runway(cash, burn_rate, revenue, growth_rate, months=24):
|
127 |
+
"""Calculate runway based on cash, burn, revenue and growth"""
|
128 |
+
current_date = datetime.now()
|
129 |
+
date_range = [current_date + timedelta(days=30*i) for i in range(months)]
|
130 |
+
|
131 |
+
cash_flow = []
|
132 |
+
monthly_revenue = revenue
|
133 |
+
|
134 |
+
for i in range(months):
|
135 |
+
net_burn = burn_rate - monthly_revenue
|
136 |
+
cash_flow.append(net_burn)
|
137 |
+
monthly_revenue *= (1 + growth_rate)
|
138 |
+
|
139 |
+
df = pd.DataFrame({
|
140 |
+
'Net_Burn': cash_flow,
|
141 |
+
'Cumulative_Cash': [cash - sum(cash_flow[:i+1]) for i in range(len(cash_flow))]
|
142 |
+
}, index=date_range)
|
143 |
+
|
144 |
+
negative_cash = df[df['Cumulative_Cash'] < 0]
|
145 |
+
runway_months = (negative_cash.index[0] - current_date).days // 30 if len(negative_cash) > 0 else months
|
146 |
+
|
147 |
+
return runway_months, df
|
148 |
+
|
149 |
+
def simulate_decision(cash, burn_rate, revenue, growth_rate,
|
150 |
+
additional_expenses, new_hires, marketing_increase, growth_impact):
|
151 |
+
"""Simulate the financial impact of a business decision"""
|
152 |
+
current_runway, current_df = calculate_runway(cash, burn_rate, revenue, growth_rate)
|
153 |
+
|
154 |
+
new_burn_rate = burn_rate + additional_expenses + (new_hires * ENGINEER_SALARY) + marketing_increase
|
155 |
+
new_growth_rate = growth_rate + growth_impact
|
156 |
+
|
157 |
+
new_runway, new_df = calculate_runway(cash, new_burn_rate, revenue, new_growth_rate)
|
158 |
+
|
159 |
+
return current_runway, new_runway, current_df, new_df
|
160 |
+
|
161 |
+
def detect_suspicious_transactions(transactions_df):
|
162 |
+
"""AI-enhanced suspicious transaction detection"""
|
163 |
+
df = transactions_df.copy()
|
164 |
+
|
165 |
+
# Define thresholds for each category
|
166 |
+
category_thresholds = {
|
167 |
+
"Travel": 3000, "Marketing": 10000, "Office": 7000,
|
168 |
+
"Software": 6000, "Consulting": 5000, "Legal": 6000
|
169 |
+
}
|
170 |
+
|
171 |
+
suspicious_terms = ['luxury', 'cruise', 'premium', 'personal', 'gift']
|
172 |
+
|
173 |
+
# Add analysis columns
|
174 |
+
df['Suspicious'] = False
|
175 |
+
df['Reason'] = ""
|
176 |
+
df['Risk_Score'] = 0
|
177 |
+
|
178 |
+
for idx, row in df.iterrows():
|
179 |
+
reasons = []
|
180 |
+
risk_score = 0
|
181 |
+
|
182 |
+
# Check category thresholds
|
183 |
+
if row['Category'] in category_thresholds and row['Amount'] > category_thresholds[row['Category']]:
|
184 |
+
reasons.append(f"Amount exceeds typical spending for {row['Category']}")
|
185 |
+
risk_score += 30
|
186 |
+
|
187 |
+
# Check for suspicious terms
|
188 |
+
for field in ['Vendor', 'Description']:
|
189 |
+
if any(term in str(row[field]).lower() for term in suspicious_terms):
|
190 |
+
reasons.append(f"{field} contains suspicious term")
|
191 |
+
risk_score += 20
|
192 |
+
|
193 |
+
# Check for round amounts
|
194 |
+
if row['Amount'] % 1000 == 0 and row['Amount'] > 3000:
|
195 |
+
reasons.append(f"Suspiciously round amount")
|
196 |
+
risk_score += 15
|
197 |
+
|
198 |
+
# Mark as suspicious if risk score is high enough
|
199 |
+
if risk_score >= 30:
|
200 |
+
df.at[idx, 'Suspicious'] = True
|
201 |
+
df.at[idx, 'Reason'] = "; ".join(reasons)
|
202 |
+
df.at[idx, 'Risk_Score'] = risk_score
|
203 |
+
|
204 |
+
return df.sort_values(by='Risk_Score', ascending=False)
|
205 |
+
|
206 |
+
def parse_csv_to_df(file):
|
207 |
+
"""Parse uploaded CSV file to DataFrame"""
|
208 |
+
try:
|
209 |
+
df = pd.read_csv(file)
|
210 |
+
return df, None
|
211 |
+
except Exception as e:
|
212 |
+
return None, f"Error parsing CSV: {e}"
|
213 |
+
|
214 |
+
# Navigation
|
215 |
+
def create_sidebar():
|
216 |
+
with st.sidebar:
|
217 |
+
st.markdown("""
|
218 |
+
<div class="title-box">
|
219 |
+
<h1>💰 StartupFinancePilot</h1>
|
220 |
+
<p>AI-powered financial assistant for startups</p>
|
221 |
+
</div>
|
222 |
+
""", unsafe_allow_html=True)
|
223 |
+
|
224 |
+
# Startup selector
|
225 |
+
if st.session_state.startups:
|
226 |
+
st.subheader("Selected Startup")
|
227 |
+
startup_names = list(st.session_state.startups.keys())
|
228 |
+
selected_startup = st.selectbox(
|
229 |
+
"Choose Startup",
|
230 |
+
startup_names,
|
231 |
+
index=startup_names.index(st.session_state.current_startup) if st.session_state.current_startup in startup_names else 0
|
232 |
+
)
|
233 |
+
st.session_state.current_startup = selected_startup
|
234 |
+
|
235 |
+
# Show basic startup info
|
236 |
+
if selected_startup in st.session_state.startups:
|
237 |
+
startup_data = st.session_state.startups[selected_startup]['profile']
|
238 |
+
st.markdown(f"""
|
239 |
+
**Stage:** {startup_data['stage']}
|
240 |
+
**Cash:** ${startup_data['cash']:,}
|
241 |
+
**Monthly Burn:** ${startup_data['burn_rate']:,}
|
242 |
+
**Monthly Revenue:** ${startup_data['revenue']:,}
|
243 |
+
""")
|
244 |
+
|
245 |
+
st.markdown("<hr>", unsafe_allow_html=True)
|
246 |
+
|
247 |
+
# Navigation buttons
|
248 |
+
if st.button("📤 Upload Startup Data", use_container_width=True):
|
249 |
+
switch_page('upload')
|
250 |
+
if st.button("📊 Financial Dashboard", use_container_width=True):
|
251 |
+
switch_page('dashboard')
|
252 |
+
if st.button("🔮 Decision Simulator", use_container_width=True):
|
253 |
+
switch_page('simulator')
|
254 |
+
if st.button("🕵️ Fund Monitoring", use_container_width=True):
|
255 |
+
switch_page('monitoring')
|
256 |
+
if st.button("🤖 AI Financial Advisor", use_container_width=True):
|
257 |
+
switch_page('advisor')
|
258 |
+
|
259 |
+
# Page Renderers
|
260 |
+
def render_upload_page():
|
261 |
+
"""Render the upload page for startup data"""
|
262 |
+
st.markdown("<h1 class='main-header'>Upload Your Startup Data</h1>", unsafe_allow_html=True)
|
263 |
+
st.markdown("<p class='sub-header'>Upload CSV files to get started</p>", unsafe_allow_html=True)
|
264 |
+
|
265 |
+
with st.expander("Upload Instructions", expanded=False):
|
266 |
+
st.markdown("""
|
267 |
+
### How to Upload Your Startup Data
|
268 |
+
|
269 |
+
You can upload three types of files:
|
270 |
+
|
271 |
+
1. **Company Profile** - A CSV with basic information about your startup including:
|
272 |
+
- name, stage, founded, employees, last_funding, cash, burn_rate, revenue, growth_rate
|
273 |
+
|
274 |
+
2. **Cash Flow Data** - A CSV with monthly cash flow data with columns:
|
275 |
+
- Month, Revenue, Payroll, Marketing, Office, Software, Travel, Legal, Misc
|
276 |
+
|
277 |
+
3. **Transaction Data** - A CSV with transaction details:
|
278 |
+
- Date, Category, Vendor, Amount, Description, Flag
|
279 |
+
""")
|
280 |
+
|
281 |
+
startup_name = st.text_input("Startup Name", value="My Startup")
|
282 |
+
|
283 |
+
col1, col2, col3 = st.columns(3)
|
284 |
+
|
285 |
+
with col1:
|
286 |
+
profile_file = st.file_uploader("Upload Company Profile (CSV)", type=['csv'])
|
287 |
+
with col2:
|
288 |
+
cash_flow_file = st.file_uploader("Upload Cash Flow Data (CSV)", type=['csv'])
|
289 |
+
with col3:
|
290 |
+
transactions_file = st.file_uploader("Upload Transactions Data (CSV)", type=['csv'])
|
291 |
+
|
292 |
+
# Process the files if uploaded
|
293 |
+
if st.button("Process Data"):
|
294 |
+
# Initialize with default values
|
295 |
+
startup_data = {
|
296 |
+
"name": startup_name,
|
297 |
+
"stage": "Seed",
|
298 |
+
"founded": "12 months ago",
|
299 |
+
"employees": 5,
|
300 |
+
"last_funding": "Not specified",
|
301 |
+
"cash": 100000,
|
302 |
+
"burn_rate": 20000,
|
303 |
+
"revenue": 5000,
|
304 |
+
"growth_rate": 0.05
|
305 |
+
}
|
306 |
+
|
307 |
+
cash_flow_df = None
|
308 |
+
transactions_df = None
|
309 |
+
|
310 |
+
# Parse company profile
|
311 |
+
if profile_file:
|
312 |
+
profile_df, error = parse_csv_to_df(profile_file)
|
313 |
+
if error:
|
314 |
+
st.error(error)
|
315 |
+
elif len(profile_df) > 0:
|
316 |
+
startup_data.update(profile_df.iloc[0].to_dict())
|
317 |
+
st.success(f"Successfully loaded company profile")
|
318 |
+
|
319 |
+
# Parse cash flow data
|
320 |
+
if cash_flow_file:
|
321 |
+
cash_flow_df, error = parse_csv_to_df(cash_flow_file)
|
322 |
+
if error:
|
323 |
+
st.error(error)
|
324 |
+
else:
|
325 |
+
if "Total_Expenses" not in cash_flow_df.columns:
|
326 |
+
expense_columns = [col for col in cash_flow_df.columns if col not in ["Month", "Revenue", "Total_Expenses", "Net_Burn"]]
|
327 |
+
cash_flow_df["Total_Expenses"] = cash_flow_df[expense_columns].sum(axis=1)
|
328 |
+
|
329 |
+
if "Net_Burn" not in cash_flow_df.columns:
|
330 |
+
cash_flow_df["Net_Burn"] = cash_flow_df["Total_Expenses"] - cash_flow_df["Revenue"]
|
331 |
+
|
332 |
+
st.success("Successfully loaded cash flow data")
|
333 |
+
|
334 |
+
# Parse transactions data
|
335 |
+
if transactions_file:
|
336 |
+
transactions_df, error = parse_csv_to_df(transactions_file)
|
337 |
+
if error:
|
338 |
+
st.error(error)
|
339 |
+
else:
|
340 |
+
# Ensure transactions data has required columns
|
341 |
+
required_columns = ["Date", "Category", "Vendor", "Amount", "Description"]
|
342 |
+
if all(col in transactions_df.columns for col in required_columns):
|
343 |
+
if "Flag" not in transactions_df.columns:
|
344 |
+
transactions_df["Flag"] = "Normal"
|
345 |
+
st.success("Successfully loaded transactions data")
|
346 |
+
else:
|
347 |
+
st.error("Transactions file is missing required columns")
|
348 |
+
|
349 |
+
# Save to session state if we have at least some data
|
350 |
+
if profile_file:
|
351 |
+
# Store in session state
|
352 |
+
st.session_state.startups[startup_data['name']] = {
|
353 |
+
'profile': startup_data,
|
354 |
+
'cash_flow': cash_flow_df,
|
355 |
+
'transactions': transactions_df
|
356 |
+
}
|
357 |
+
|
358 |
+
# Set as current startup
|
359 |
+
st.session_state.current_startup = startup_data['name']
|
360 |
+
|
361 |
+
st.success(f"Successfully added {startup_data['name']} to your startups")
|
362 |
+
switch_page('dashboard')
|
363 |
+
else:
|
364 |
+
st.error("Please upload at least a company profile file")
|
365 |
+
|
366 |
+
def render_financial_dashboard():
|
367 |
+
"""Render the AI-powered financial dashboard page"""
|
368 |
+
if not st.session_state.current_startup or st.session_state.current_startup not in st.session_state.startups:
|
369 |
+
st.warning("No startup selected. Please upload data first.")
|
370 |
+
render_upload_page()
|
371 |
+
return
|
372 |
+
|
373 |
+
# Get the selected startup data
|
374 |
+
startup_data = st.session_state.startups[st.session_state.current_startup]['profile']
|
375 |
+
cash_flow_df = st.session_state.startups[st.session_state.current_startup]['cash_flow']
|
376 |
+
|
377 |
+
st.markdown("<h1 class='main-header'>Financial Dashboard</h1>", unsafe_allow_html=True)
|
378 |
+
|
379 |
+
# AI Insights
|
380 |
+
insights_key = f"dashboard_{date.today().isoformat()}"
|
381 |
+
if insights_key not in st.session_state.insights_cache:
|
382 |
+
insights = generate_ai_response(f"""
|
383 |
+
You are a financial advisor for startups. Based on this startup's data:
|
384 |
+
- Current cash: ${startup_data['cash']}
|
385 |
+
- Monthly burn rate: ${startup_data['burn_rate']}
|
386 |
+
- Monthly revenue: ${startup_data['revenue']}
|
387 |
+
- Monthly growth rate: {startup_data['growth_rate'] * 100}%
|
388 |
+
|
389 |
+
Provide the top 3 most important financial insights that the founder should know today.
|
390 |
+
Format each insight as a brief, action-oriented bullet point.
|
391 |
+
""")
|
392 |
+
st.session_state.insights_cache[insights_key] = insights
|
393 |
+
|
394 |
+
with st.expander("📊 AI Financial Insights", expanded=True):
|
395 |
+
st.markdown("<span class='ai-badge'>AI-Generated Insights</span>", unsafe_allow_html=True)
|
396 |
+
st.markdown(st.session_state.insights_cache[insights_key])
|
397 |
+
|
398 |
+
# Key metrics
|
399 |
+
col1, col2, col3, col4 = st.columns(4)
|
400 |
+
|
401 |
+
# Calculate runway
|
402 |
+
runway_months, runway_df = calculate_runway(
|
403 |
+
startup_data['cash'],
|
404 |
+
startup_data['burn_rate'],
|
405 |
+
startup_data['revenue'],
|
406 |
+
startup_data['growth_rate']
|
407 |
+
)
|
408 |
+
|
409 |
+
# Determine status colors
|
410 |
+
runway_status = "danger-metric" if runway_months < 6 else ("warning-metric" if runway_months < 9 else "good-metric")
|
411 |
+
burn_status = "danger-metric" if startup_data['burn_rate'] > 100000 else ("warning-metric" if startup_data['burn_rate'] > 80000 else "good-metric")
|
412 |
+
revenue_status = "good-metric" if startup_data['revenue'] > 20000 else ("warning-metric" if startup_data['revenue'] > 10000 else "danger-metric")
|
413 |
+
|
414 |
+
with col1:
|
415 |
+
st.markdown(f"""
|
416 |
+
<div class='metric-card'>
|
417 |
+
<p class='metric-label'>Current Cash</p>
|
418 |
+
<p class='metric-value'>${startup_data['cash']:,}</p>
|
419 |
+
</div>
|
420 |
+
""", unsafe_allow_html=True)
|
421 |
+
|
422 |
+
with col2:
|
423 |
+
st.markdown(f"""
|
424 |
+
<div class='metric-card'>
|
425 |
+
<p class='metric-label'>Monthly Burn</p>
|
426 |
+
<p class='metric-value {burn_status}'>${startup_data['burn_rate']:,}</p>
|
427 |
+
</div>
|
428 |
+
""", unsafe_allow_html=True)
|
429 |
+
|
430 |
+
with col3:
|
431 |
+
st.markdown(f"""
|
432 |
+
<div class='metric-card'>
|
433 |
+
<p class='metric-label'>Monthly Revenue</p>
|
434 |
+
<p class='metric-value {revenue_status}'>${startup_data['revenue']:,}</p>
|
435 |
+
</div>
|
436 |
+
""", unsafe_allow_html=True)
|
437 |
+
|
438 |
+
with col4:
|
439 |
+
st.markdown(f"""
|
440 |
+
<div class='metric-card'>
|
441 |
+
<p class='metric-label'>Runway</p>
|
442 |
+
<p class='metric-value {runway_status}'>{runway_months} months</p>
|
443 |
+
</div>
|
444 |
+
""", unsafe_allow_html=True)
|
445 |
+
|
446 |
+
# Financial charts
|
447 |
+
st.subheader("Financial Overview")
|
448 |
+
|
449 |
+
# Display only if we have cash flow data
|
450 |
+
if cash_flow_df is not None:
|
451 |
+
# Runway chart
|
452 |
+
fig = px.line(runway_df.reset_index(), x='index', y='Cumulative_Cash',
|
453 |
+
title="Cash Runway Projection",
|
454 |
+
labels={'index': 'Date', 'Cumulative_Cash': 'Remaining Cash ($)'},
|
455 |
+
color_discrete_sequence=['#0066cc'])
|
456 |
+
fig.add_hline(y=0, line_dash="dash", line_color="red", annotation_text="Out of Cash")
|
457 |
+
fig.update_layout(height=400)
|
458 |
+
st.plotly_chart(fig, use_container_width=True)
|
459 |
+
|
460 |
+
# Revenue vs Expenses
|
461 |
+
fig = px.bar(cash_flow_df, x='Month', y=['Revenue', 'Total_Expenses'],
|
462 |
+
title="Revenue vs. Expenses",
|
463 |
+
barmode='group',
|
464 |
+
color_discrete_sequence=['#28a745', '#dc3545'])
|
465 |
+
st.plotly_chart(fig, use_container_width=True)
|
466 |
+
else:
|
467 |
+
st.info("Upload cash flow data to see detailed financial charts")
|
468 |
+
|
469 |
+
def render_decision_simulator():
|
470 |
+
"""Render the decision simulator page"""
|
471 |
+
if not st.session_state.current_startup or st.session_state.current_startup not in st.session_state.startups:
|
472 |
+
st.warning("No startup selected. Please upload data first.")
|
473 |
+
render_upload_page()
|
474 |
+
return
|
475 |
+
|
476 |
+
startup_data = st.session_state.startups[st.session_state.current_startup]['profile']
|
477 |
+
|
478 |
+
st.markdown("<h1 class='main-header'>Decision Simulator</h1>", unsafe_allow_html=True)
|
479 |
+
st.markdown("<p class='sub-header'>Test the financial impact of business decisions</p>", unsafe_allow_html=True)
|
480 |
+
|
481 |
+
# Decision input form
|
482 |
+
with st.form("decision_form"):
|
483 |
+
st.subheader("Scenario Parameters")
|
484 |
+
|
485 |
+
col1, col2 = st.columns(2)
|
486 |
+
|
487 |
+
with col1:
|
488 |
+
new_hires = st.number_input("New Engineering Hires", min_value=0, max_value=10, value=0)
|
489 |
+
st.caption(f"Monthly Cost: ${new_hires * ENGINEER_SALARY:,}")
|
490 |
+
|
491 |
+
new_marketing = st.number_input("Additional Monthly Marketing Budget",
|
492 |
+
min_value=0, max_value=50000, value=0, step=1000)
|
493 |
+
|
494 |
+
with col2:
|
495 |
+
other_expenses = st.number_input("Other Additional Monthly Expenses",
|
496 |
+
min_value=0, max_value=50000, value=0, step=1000)
|
497 |
+
|
498 |
+
growth_impact = st.slider("Estimated Impact on Monthly Growth Rate",
|
499 |
+
min_value=0.0, max_value=0.10, value=0.0, step=0.01,
|
500 |
+
format="%.2f")
|
501 |
+
|
502 |
+
question = st.text_area("Describe your decision scenario", height=100)
|
503 |
+
|
504 |
+
decision_summary = f"""
|
505 |
+
- {new_hires} new engineers: ${new_hires * ENGINEER_SALARY:,}/month
|
506 |
+
- Marketing increase: ${new_marketing:,}/month
|
507 |
+
- Other expenses: ${other_expenses:,}/month
|
508 |
+
- Total additional burn: ${new_hires * ENGINEER_SALARY + new_marketing + other_expenses:,}/month
|
509 |
+
- Growth impact: +{growth_impact * 100:.1f}% monthly growth
|
510 |
+
"""
|
511 |
+
|
512 |
+
st.markdown(f"**Decision Summary:**\n{decision_summary}")
|
513 |
+
|
514 |
+
submitted = st.form_submit_button("Simulate Decision")
|
515 |
+
|
516 |
+
if submitted:
|
517 |
+
# Calculate current and new runway
|
518 |
+
current_runway, new_runway, current_df, new_df = simulate_decision(
|
519 |
+
startup_data['cash'],
|
520 |
+
startup_data['burn_rate'],
|
521 |
+
startup_data['revenue'],
|
522 |
+
startup_data['growth_rate'],
|
523 |
+
other_expenses,
|
524 |
+
new_hires,
|
525 |
+
new_marketing,
|
526 |
+
growth_impact
|
527 |
+
)
|
528 |
+
|
529 |
+
# Display results
|
530 |
+
st.markdown("<h3>Decision Impact Analysis</h3>", unsafe_allow_html=True)
|
531 |
+
|
532 |
+
# Summary metrics
|
533 |
+
col1, col2, col3 = st.columns(3)
|
534 |
+
|
535 |
+
with col1:
|
536 |
+
st.metric("Current Runway", f"{current_runway} months")
|
537 |
+
with col2:
|
538 |
+
runway_change = new_runway - current_runway
|
539 |
+
st.metric("New Runway", f"{new_runway} months",
|
540 |
+
delta=f"{runway_change} months",
|
541 |
+
delta_color="off" if runway_change == 0 else ("normal" if runway_change > 0 else "inverse"))
|
542 |
+
with col3:
|
543 |
+
new_burn = startup_data['burn_rate'] + other_expenses + (new_hires * ENGINEER_SALARY) + new_marketing
|
544 |
+
burn_change = new_burn - startup_data['burn_rate']
|
545 |
+
burn_percentage = burn_change / startup_data['burn_rate'] * 100
|
546 |
+
st.metric("New Monthly Burn", f"${new_burn:,}",
|
547 |
+
delta=f"${burn_change:,} ({burn_percentage:.1f}%)",
|
548 |
+
delta_color="inverse")
|
549 |
+
|
550 |
+
# Cash projection comparison
|
551 |
+
st.subheader("Cash Projection Comparison")
|
552 |
+
|
553 |
+
# Combine dataframes for comparison
|
554 |
+
current_df['Scenario'] = 'Current'
|
555 |
+
new_df['Scenario'] = 'After Decision'
|
556 |
+
|
557 |
+
combined_df = pd.concat([current_df, new_df])
|
558 |
+
combined_df = combined_df.reset_index()
|
559 |
+
combined_df = combined_df.rename(columns={'index': 'Date'})
|
560 |
+
|
561 |
+
# Plot comparison
|
562 |
+
fig = px.line(combined_df, x='Date', y='Cumulative_Cash', color='Scenario',
|
563 |
+
title="Cash Runway Comparison",
|
564 |
+
labels={'Cumulative_Cash': 'Remaining Cash'},
|
565 |
+
color_discrete_sequence=['#4c78a8', '#f58518'])
|
566 |
+
|
567 |
+
fig.add_hline(y=0, line_dash="dash", line_color="red", annotation_text="Out of Cash")
|
568 |
+
fig.update_layout(height=400)
|
569 |
+
|
570 |
+
st.plotly_chart(fig, use_container_width=True)
|
571 |
+
|
572 |
+
# Get AI analysis
|
573 |
+
if question:
|
574 |
+
analysis_key = f"decision_analysis_{new_hires}_{new_marketing}_{other_expenses}_{growth_impact}"
|
575 |
+
if analysis_key not in st.session_state.insights_cache:
|
576 |
+
analysis = generate_ai_response(f"""
|
577 |
+
You are a financial advisor for startups. A founder asks:
|
578 |
+
"{question}"
|
579 |
+
|
580 |
+
Here's their current financial situation:
|
581 |
+
- Current cash: ${startup_data['cash']}
|
582 |
+
- Monthly burn rate: ${startup_data['burn_rate']}
|
583 |
+
- Monthly revenue: ${startup_data['revenue']}
|
584 |
+
- Monthly growth rate: {startup_data['growth_rate'] * 100}%
|
585 |
+
|
586 |
+
They're considering these changes:
|
587 |
+
- Adding {new_hires} new engineers (${ENGINEER_SALARY}/month each)
|
588 |
+
- Increasing marketing budget by ${new_marketing}/month
|
589 |
+
- Adding ${other_expenses}/month in other expenses
|
590 |
+
- Expecting {growth_impact * 100}% additional monthly growth
|
591 |
+
|
592 |
+
Analyze this decision thoroughly:
|
593 |
+
1. Quantify the impact on runway
|
594 |
+
2. Assess the risk level (low, medium, high)
|
595 |
+
3. Compare the ROI potential
|
596 |
+
4. Provide recommendations
|
597 |
+
|
598 |
+
Be direct and specific with numbers and timeframes.
|
599 |
+
""")
|
600 |
+
st.session_state.insights_cache[analysis_key] = analysis
|
601 |
+
|
602 |
+
st.markdown("<div class='advisor-card'>", unsafe_allow_html=True)
|
603 |
+
st.markdown("<span class='ai-badge'>AI Decision Analysis</span>", unsafe_allow_html=True)
|
604 |
+
st.markdown(f"<p class='advice-text'>{st.session_state.insights_cache[analysis_key]}</p>", unsafe_allow_html=True)
|
605 |
+
st.markdown("</div>", unsafe_allow_html=True)
|
606 |
+
|
607 |
+
def render_fund_monitoring():
|
608 |
+
"""Render the fund monitoring page"""
|
609 |
+
if not st.session_state.current_startup or st.session_state.current_startup not in st.session_state.startups:
|
610 |
+
st.warning("No startup selected. Please upload data first.")
|
611 |
+
render_upload_page()
|
612 |
+
return
|
613 |
+
|
614 |
+
# Get the selected startup data
|
615 |
+
transactions_df = st.session_state.startups[st.session_state.current_startup]['transactions']
|
616 |
+
|
617 |
+
st.markdown("<h1 class='main-header'>Fund Monitoring</h1>", unsafe_allow_html=True)
|
618 |
+
st.markdown("<p class='sub-header'>AI-powered fraud detection and spending analysis</p>", unsafe_allow_html=True)
|
619 |
+
|
620 |
+
if transactions_df is None:
|
621 |
+
st.warning("No transaction data available. Please upload transaction data.")
|
622 |
+
return
|
623 |
+
|
624 |
+
# Process transactions to detect suspicious ones
|
625 |
+
processed_df = detect_suspicious_transactions(transactions_df)
|
626 |
+
|
627 |
+
# Summary metrics
|
628 |
+
total_transactions = len(processed_df)
|
629 |
+
suspicious_transactions = processed_df[processed_df['Suspicious']].copy()
|
630 |
+
suspicious_count = len(suspicious_transactions)
|
631 |
+
suspicious_amount = suspicious_transactions['Amount'].sum() if not suspicious_transactions.empty else 0
|
632 |
+
total_amount = processed_df['Amount'].sum()
|
633 |
+
|
634 |
+
col1, col2 = st.columns(2)
|
635 |
+
|
636 |
+
with col1:
|
637 |
+
st.markdown(f"""
|
638 |
+
<div class='metric-card'>
|
639 |
+
<p class='metric-label'>Total Transactions</p>
|
640 |
+
<p class='metric-value'>{total_transactions}</p>
|
641 |
+
</div>
|
642 |
+
""", unsafe_allow_html=True)
|
643 |
+
|
644 |
+
with col2:
|
645 |
+
flagged_percent = suspicious_count/total_transactions*100 if total_transactions > 0 else 0
|
646 |
+
status = "danger-metric" if flagged_percent > 10 else ("warning-metric" if flagged_percent > 5 else "good-metric")
|
647 |
+
st.markdown(f"""
|
648 |
+
<div class='metric-card'>
|
649 |
+
<p class='metric-label'>Flagged Transactions</p>
|
650 |
+
<p class='metric-value {status}'>{suspicious_count} ({flagged_percent:.1f}%)</p>
|
651 |
+
</div>
|
652 |
+
""", unsafe_allow_html=True)
|
653 |
+
|
654 |
+
# Tabs for different views
|
655 |
+
tab1, tab2 = st.tabs(["Flagged Transactions", "All Transactions"])
|
656 |
+
|
657 |
+
with tab1:
|
658 |
+
if suspicious_count > 0:
|
659 |
+
st.dataframe(
|
660 |
+
suspicious_transactions[['Date', 'Category', 'Vendor', 'Amount', 'Description', 'Risk_Score', 'Reason']],
|
661 |
+
use_container_width=True
|
662 |
+
)
|
663 |
+
|
664 |
+
# Get AI analysis of suspicious transactions
|
665 |
+
fraud_key = f"fraud_{date.today().isoformat()}"
|
666 |
+
if fraud_key not in st.session_state.insights_cache:
|
667 |
+
suspicious_text = "\n".join([
|
668 |
+
f"- {row['Vendor']} (${row['Amount']:.2f}): {row['Description']}"
|
669 |
+
for _, row in suspicious_transactions.head(5).iterrows()
|
670 |
+
])
|
671 |
+
|
672 |
+
fraud_analysis = generate_ai_response(f"""
|
673 |
+
You are a financial fraud detection expert. Review these flagged suspicious transactions:
|
674 |
+
|
675 |
+
{suspicious_text}
|
676 |
+
|
677 |
+
Provide a brief analysis and recommendations.
|
678 |
+
""")
|
679 |
+
st.session_state.insights_cache[fraud_key] = fraud_analysis
|
680 |
+
|
681 |
+
st.markdown("<div class='advisor-card'>", unsafe_allow_html=True)
|
682 |
+
st.markdown("<span class='ai-badge'>AI Fraud Analysis</span>", unsafe_allow_html=True)
|
683 |
+
st.markdown(f"<p class='advice-text'>{st.session_state.insights_cache[fraud_key]}</p>", unsafe_allow_html=True)
|
684 |
+
st.markdown("</div>", unsafe_allow_html=True)
|
685 |
+
else:
|
686 |
+
st.success("No suspicious transactions detected.")
|
687 |
+
|
688 |
+
with tab2:
|
689 |
+
st.dataframe(processed_df[['Date', 'Category', 'Vendor', 'Amount', 'Description', 'Suspicious', 'Risk_Score']],
|
690 |
+
use_container_width=True)
|
691 |
+
|
692 |
+
# Category spending
|
693 |
+
if not processed_df.empty:
|
694 |
+
st.subheader("Spending by Category")
|
695 |
+
category_spending = processed_df.groupby('Category')['Amount'].sum().reset_index()
|
696 |
+
|
697 |
+
fig = px.bar(category_spending, x='Category', y='Amount',
|
698 |
+
title="Spending by Category",
|
699 |
+
color='Amount',
|
700 |
+
color_continuous_scale='Blues')
|
701 |
+
st.plotly_chart(fig, use_container_width=True)
|
702 |
+
|
703 |
+
def render_ai_financial_advisor():
|
704 |
+
"""Render the AI financial advisor page with voice chat"""
|
705 |
+
if not st.session_state.current_startup or st.session_state.current_startup not in st.session_state.startups:
|
706 |
+
st.warning("No startup selected. Please upload data first.")
|
707 |
+
render_upload_page()
|
708 |
+
return
|
709 |
+
|
710 |
+
startup_data = st.session_state.startups[st.session_state.current_startup]['profile']
|
711 |
+
|
712 |
+
st.markdown("<h1 class='main-header'>AI Financial Advisor</h1>", unsafe_allow_html=True)
|
713 |
+
|
714 |
+
# Chat container
|
715 |
+
st.markdown("<div style='background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;'>", unsafe_allow_html=True)
|
716 |
+
|
717 |
+
# Display chat history
|
718 |
+
for message in st.session_state.chat_history:
|
719 |
+
if message["role"] == "user":
|
720 |
+
st.markdown(f"<div style='background-color: #e6f7ff; padding: 10px; border-radius: 10px; margin-bottom: 10px;'><strong>You:</strong> {message['content']}</div>", unsafe_allow_html=True)
|
721 |
+
else:
|
722 |
+
st.markdown(f"<div style='background-color: #f0f7ff; padding: 10px; border-radius: 10px; margin-bottom: 10px;'><strong>Financial Advisor:</strong> {message['content']}</div>", unsafe_allow_html=True)
|
723 |
+
|
724 |
+
# Show play button for voice if it exists
|
725 |
+
if 'audio' in message and message['audio']:
|
726 |
+
st.audio(message['audio'], format='audio/mp3')
|
727 |
+
|
728 |
+
# Input for new message
|
729 |
+
col1, col2 = st.columns([5, 1])
|
730 |
+
|
731 |
+
with col1:
|
732 |
+
user_input = st.text_input("Ask a financial question", key="user_question")
|
733 |
+
|
734 |
+
with col2:
|
735 |
+
use_voice = st.checkbox("Enable voice", value=True)
|
736 |
+
|
737 |
+
# Common financial questions
|
738 |
+
st.markdown("### Common Questions")
|
739 |
+
question_cols = st.columns(3)
|
740 |
+
|
741 |
+
common_questions = [
|
742 |
+
"How much runway do we have?",
|
743 |
+
"When should we start fundraising?",
|
744 |
+
"How can we optimize our burn rate?"
|
745 |
+
]
|
746 |
+
|
747 |
+
for i, question in enumerate(common_questions):
|
748 |
+
with question_cols[i % 3]:
|
749 |
+
if st.button(question, key=f"q_{i}"):
|
750 |
+
user_input = question
|
751 |
+
|
752 |
+
# Process user input
|
753 |
+
if user_input:
|
754 |
+
# Add user message to chat history
|
755 |
+
st.session_state.chat_history.append({"role": "user", "content": user_input})
|
756 |
+
|
757 |
+
# Get AI response
|
758 |
+
response = generate_ai_response(f"""
|
759 |
+
You are a strategic financial advisor for startups. A founder asks:
|
760 |
+
"{user_input}"
|
761 |
+
|
762 |
+
Here's their current financial situation:
|
763 |
+
- Stage: {startup_data['stage']}
|
764 |
+
- Current cash: ${startup_data['cash']}
|
765 |
+
- Monthly burn rate: ${startup_data['burn_rate']}
|
766 |
+
- Monthly revenue: ${startup_data['revenue']}
|
767 |
+
- Monthly growth rate: {startup_data['growth_rate'] * 100}%
|
768 |
+
- Last funding: {startup_data['last_funding']}
|
769 |
+
|
770 |
+
Provide concise, actionable advice.
|
771 |
+
""")
|
772 |
+
|
773 |
+
# Generate voice response if enabled
|
774 |
+
audio_data = None
|
775 |
+
if use_voice:
|
776 |
+
audio_data = generate_voice_response(response)
|
777 |
+
|
778 |
+
# Add AI response to chat history
|
779 |
+
st.session_state.chat_history.append({
|
780 |
+
"role": "assistant",
|
781 |
+
"content": response,
|
782 |
+
"audio": audio_data
|
783 |
+
})
|
784 |
+
|
785 |
+
# Rerun to display updated chat
|
786 |
+
st.rerun()
|
787 |
+
|
788 |
+
st.markdown("</div>", unsafe_allow_html=True)
|
789 |
+
|
790 |
+
# Main function
|
791 |
+
def main():
|
792 |
+
# Initialize AI
|
793 |
+
initialize_gemini()
|
794 |
+
|
795 |
+
# Create sidebar navigation
|
796 |
+
create_sidebar()
|
797 |
+
|
798 |
+
# Render the correct page based on session state
|
799 |
+
if st.session_state.current_page == 'upload':
|
800 |
+
render_upload_page()
|
801 |
+
elif st.session_state.current_page == 'dashboard':
|
802 |
+
render_financial_dashboard()
|
803 |
+
elif st.session_state.current_page == 'simulator':
|
804 |
+
render_decision_simulator()
|
805 |
+
elif st.session_state.current_page == 'monitoring':
|
806 |
+
render_fund_monitoring()
|
807 |
+
elif st.session_state.current_page == 'advisor':
|
808 |
+
render_ai_financial_advisor()
|
809 |
+
|
810 |
+
if __name__ == "__main__":
|
811 |
+
main()
|