|
import gradio as gr |
|
import plotly.graph_objects as go |
|
import requests |
|
from datetime import datetime, timedelta |
|
import logging |
|
import random |
|
from transformers import pipeline |
|
|
|
|
|
|
|
|
|
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s') |
|
|
|
|
|
|
|
|
|
try: |
|
summarizer = pipeline("summarization", model="myorg/inhouse-summarizer") |
|
logging.info("Loaded in-house summarizer.") |
|
except Exception as e: |
|
logging.error("In-house summarizer not found, falling back: %s", e) |
|
summarizer = pipeline("summarization", model="facebook/bart-large-cnn") |
|
|
|
try: |
|
research_generator = pipeline("text-generation", model="myorg/inhouse-research", max_length=100) |
|
logging.info("Loaded in-house research generator.") |
|
except Exception as e: |
|
logging.error("In-house research generator not found, falling back: %s", e) |
|
research_generator = pipeline("text-generation", model="gpt2", max_length=100) |
|
|
|
try: |
|
planner_generator = pipeline("text-generation", model="myorg/inhouse-planner", max_length=150) |
|
logging.info("Loaded in-house planner generator.") |
|
except Exception as e: |
|
logging.error("In-house planner generator not found, falling back: %s", e) |
|
planner_generator = pipeline("text-generation", model="gpt2", max_length=150) |
|
|
|
|
|
|
|
|
|
def report_agent(data): |
|
""" |
|
Generates a summary report using the in-house summarizer model. |
|
""" |
|
if not data or len(data.strip()) == 0: |
|
return "Please provide input text for summarization." |
|
try: |
|
summary = summarizer(data, max_length=130, min_length=30, do_sample=False) |
|
logging.debug("Summary generated using in-house summarizer.") |
|
return summary[0]['summary_text'] |
|
except Exception as e: |
|
logging.error("Error generating summary: %s", e) |
|
return "Error generating summary." |
|
|
|
def planning_agent(goal): |
|
""" |
|
Generates a detailed action plan based on the provided goal using the in-house planner model. |
|
""" |
|
if not goal or len(goal.strip()) == 0: |
|
return "Please provide a goal for planning." |
|
try: |
|
plan = planner_generator(goal, max_length=150, num_return_sequences=1) |
|
logging.debug("Plan generated using in-house planner.") |
|
return plan[0]['generated_text'] |
|
except Exception as e: |
|
logging.error("Error generating plan: %s", e) |
|
return "Error generating plan." |
|
|
|
def research_agent(query): |
|
""" |
|
Generates research insights based on the provided query using the in-house research generator. |
|
""" |
|
if not query or len(query.strip()) == 0: |
|
return "Please provide a research query." |
|
try: |
|
result = research_generator(query, max_length=100, num_return_sequences=1) |
|
logging.debug("Research output generated using in-house research model.") |
|
return result[0]['generated_text'] |
|
except Exception as e: |
|
logging.error("Error generating research output: %s", e) |
|
return "Error generating research output." |
|
|
|
|
|
|
|
|
|
def create_performance_comparison(): |
|
""" |
|
Creates a performance comparison chart showing current (2GB VRAM) capabilities |
|
versus potential performance with a GPU upgrade. |
|
""" |
|
categories = [ |
|
'AI Model Loading', |
|
'Local AI Assistants', |
|
'VS Code Extensions', |
|
'Image Processing', |
|
'Multi-tasking', |
|
'Large Dataset Analysis' |
|
] |
|
current_values = [20, 15, 10, 18, 25, 12] |
|
potential_values = [100, 100, 100, 100, 100, 100] |
|
|
|
fig = go.Figure(data=[ |
|
go.Bar(name='Current Setup (2GB VRAM)', x=categories, y=current_values, marker_color='#94A3B8'), |
|
go.Bar(name='With GPU Upgrade', x=categories, y=potential_values, marker_color='#2563EB') |
|
]) |
|
|
|
fig.update_layout( |
|
title={'text': 'What I Can Do vs What I Could Do', 'font': {'size': 24}}, |
|
barmode='group', |
|
yaxis_title='Capability (%)', |
|
plot_bgcolor='white', |
|
font={'family': 'Arial', 'size': 14} |
|
) |
|
logging.debug("Performance comparison chart created.") |
|
return fig |
|
|
|
def create_roi_projection(): |
|
""" |
|
Creates a 6-month ROI projection chart showing the current revenue path versus |
|
the projected revenue path with a GPU upgrade. |
|
""" |
|
months = ['Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug'] |
|
current_revenue = [1000, 1200, 1400, 1600, 1800, 2000] |
|
projected_revenue = [1000, 1500, 2250, 3400, 5100, 7650] |
|
|
|
fig = go.Figure() |
|
fig.add_trace(go.Scatter( |
|
x=months, |
|
y=current_revenue, |
|
name='Current Path', |
|
line={'color': '#94A3B8', 'width': 3} |
|
)) |
|
fig.add_trace(go.Scatter( |
|
x=months, |
|
y=projected_revenue, |
|
name='With GPU Upgrade', |
|
line={'color': '#2563EB', 'width': 3} |
|
)) |
|
|
|
fig.update_layout( |
|
title={'text': '6-Month Revenue Projection', 'font': {'size': 24}}, |
|
xaxis_title='Month', |
|
yaxis_title='Revenue (USD)', |
|
plot_bgcolor='white', |
|
font={'family': 'Arial', 'size': 14} |
|
) |
|
logging.debug("ROI projection chart created.") |
|
return fig |
|
|
|
def create_earnings_history(): |
|
""" |
|
Creates an earnings history visualization using personal pay data. |
|
""" |
|
dates = ["2024-12-10", "2024-12-17", "2024-12-24", "2024-12-31", "2025-01-07", |
|
"2025-01-14", "2025-01-21", "2025-01-28", "2025-02-04", "2025-02-11"] |
|
earnings = [156.02, 73.10, 97.07, 116.11, 79.05, 86.62, 54.57, 86.36, 61.50, 79.18] |
|
|
|
fig = go.Figure(data=go.Scatter( |
|
x=dates, |
|
y=earnings, |
|
mode='lines+markers', |
|
line={'color': '#2563EB', 'width': 3}, |
|
name='Earnings' |
|
)) |
|
|
|
fig.update_layout( |
|
title={'text': 'Recent Earnings History', 'font': {'size': 24}}, |
|
xaxis_title='Date', |
|
yaxis_title='Amount (USD)', |
|
plot_bgcolor='white', |
|
font={'family': 'Arial', 'size': 14} |
|
) |
|
logging.debug("Earnings history chart created.") |
|
return fig |
|
|
|
def calculate_loan_schedule(loan_amount=3000, interest_rate=5.0): |
|
""" |
|
Calculates the loan repayment schedule given an investment amount and interest rate. |
|
Returns a formatted string detailing monthly payments and timelines. |
|
""" |
|
try: |
|
amount = float(loan_amount) |
|
annual_rate = float(interest_rate) / 100 |
|
monthly_rate = annual_rate / 12 |
|
grace_period = 2 |
|
repayment_period = 12 |
|
|
|
monthly_payment = amount * (monthly_rate * (1 + monthly_rate) ** repayment_period) / ((1 + monthly_rate) ** repayment_period - 1) |
|
|
|
schedule = "💰 **Investment Breakdown & Repayment Plan**\n\n" |
|
schedule += f"**Initial Investment:** ${amount:,.2f}\n" |
|
schedule += f"**Grace Period:** {grace_period} months to set everything up\n" |
|
schedule += f"**Monthly Payment:** ${monthly_payment:,.2f} (starting month {grace_period + 1})\n\n" |
|
|
|
remaining_balance = amount |
|
total_interest = 0 |
|
current_date = datetime.now() |
|
|
|
schedule += "**Monthly Timeline:**\n" |
|
for month in range(1, repayment_period + grace_period + 1): |
|
date = current_date + timedelta(days=30 * month) |
|
if month <= grace_period: |
|
schedule += f"- {date.strftime('%B %Y')}: Setup period (No payment required)\n" |
|
else: |
|
interest = remaining_balance * monthly_rate |
|
principal = monthly_payment - interest |
|
remaining_balance -= principal |
|
total_interest += interest |
|
schedule += f"- {date.strftime('%B %Y')}: ${monthly_payment:,.2f}\n" |
|
|
|
schedule += f"\n**Total Interest Paid:** ${total_interest:,.2f}" |
|
logging.debug("Loan repayment schedule calculated.") |
|
return schedule |
|
except ValueError: |
|
return "Please enter valid numbers for the loan calculation." |
|
|
|
def create_detailed_financial_projection(): |
|
""" |
|
Creates a detailed 12-month financial projection chart with three scenarios: |
|
worst-case, expected, and best-case revenue paths. |
|
""" |
|
months = ['Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec', 'Jan', 'Feb'] |
|
base_revenue = 1000 |
|
worst_case = [base_revenue * (1 + 0.05) ** i for i in range(len(months))] |
|
expected = [base_revenue * (1 + 0.10) ** i for i in range(len(months))] |
|
best_case = [base_revenue * (1 + 0.20) ** i for i in range(len(months))] |
|
|
|
fig = go.Figure() |
|
fig.add_trace(go.Scatter( |
|
x=months, y=worst_case, name='Worst Case', |
|
line={'color': '#FF6B6B', 'width': 2, 'dash': 'dot'} |
|
)) |
|
fig.add_trace(go.Scatter( |
|
x=months, y=expected, name='Expected', |
|
line={'color': '#94A3B8', 'width': 3} |
|
)) |
|
fig.add_trace(go.Scatter( |
|
x=months, y=best_case, name='Best Case', |
|
line={'color': '#2563EB', 'width': 3, 'dash': 'dash'} |
|
)) |
|
|
|
fig.update_layout( |
|
title={'text': '12-Month Financial Projection', 'font': {'size': 24}}, |
|
xaxis_title='Month', |
|
yaxis_title='Revenue (USD)', |
|
plot_bgcolor='white', |
|
font={'family': 'Arial', 'size': 14}, |
|
legend={'orientation': 'h', 'x': 0.3, 'y': 1.1} |
|
) |
|
logging.debug("Detailed financial projection chart created.") |
|
return fig |
|
|
|
def create_project_timeline(): |
|
""" |
|
Creates a timeline chart showing key project milestones. |
|
""" |
|
milestones = ["Concept", "Prototype", "Beta Launch", "Full Launch", "Growth", "Expansion"] |
|
dates = ["2025-03-01", "2025-04-15", "2025-06-01", "2025-08-01", "2025-10-01", "2025-12-01"] |
|
|
|
fig = go.Figure(data=go.Scatter( |
|
x=dates, y=list(range(len(milestones))), mode="markers+text", |
|
text=milestones, textposition="top center", marker=dict(size=12, color="#2563EB") |
|
)) |
|
fig.update_layout( |
|
title="Project Timeline & Milestones", |
|
xaxis_title="Date", |
|
yaxis_title="Milestone Stage", |
|
yaxis=dict(tickvals=list(range(len(milestones))), ticktext=milestones), |
|
plot_bgcolor='white', |
|
font={'family': 'Arial', 'size': 14} |
|
) |
|
logging.debug("Project timeline chart created.") |
|
return fig |
|
|
|
|
|
|
|
|
|
def display_tech_stack(): |
|
""" |
|
Returns a Markdown string detailing the technical stack and tools used. |
|
""" |
|
tech_info = """ |
|
### Technical Stack & Tools |
|
- **Languages:** Python, JavaScript, Solidity, Rust, Go, Swift, C++, HTML |
|
- **Frameworks:** Next.js, React, Gradio, Langchain, LlamaIndex, StreamLit |
|
- **AI/ML:** TensorFlow, PyTorch, LangChain, Transformers, Embeddings models, VLM |
|
- **RAG Systems:** Microsoft Nano Graph RAG, Multimodel RAGs, In-house systems |
|
- **Development Tools:** VS Code extensions, UNSLOTH, Ollama, TensorBoard, YOLO |
|
- **Databases:** PostgreSQL (with pgvector), MongoDB, SQL |
|
- **Cloud Infrastructure:** AWS, Huggingface Spaces, Google Colab (free T100s) |
|
""" |
|
return tech_info |
|
|
|
def display_business_plan(): |
|
""" |
|
Returns a Markdown string with a comprehensive business plan. |
|
""" |
|
business_plan = """ |
|
### Comprehensive Business Plan |
|
#### Executive Summary |
|
Our mission is to revolutionize AI with secure, innovative solutions based on Retrieval Augmented Generation (RAG). |
|
|
|
#### Company Description |
|
**Sletcher Systems** designs systems that transform free open source tools into scalable, inhouse AI solutions. |
|
We build proprietary RAG systems to sell alongside open source versions. |
|
|
|
#### Market Analysis |
|
- **Local Focus:** Tailored for unique regulatory landscapes. |
|
- **Growth Opportunity:** Huge potential in both enterprise and consumer markets. |
|
|
|
#### Product Offerings |
|
- **AI Assistants:** 24/7, offline, and secure. |
|
- **SaaS Platforms:** End-to-end solutions for image/document processing. |
|
- **Developer Tools:** Custom VS Code extensions. |
|
- **Advertising Agents:** Automated marketing and advertising solutions. |
|
|
|
#### Financial Projections |
|
- **Initial Investment:** $3,000 for GPU upgrade. |
|
- **Break-even:** Expected within 4-6 months. |
|
- **ROI:** 5x revenue increase potential. |
|
|
|
#### Marketing & Sales Strategy |
|
- Digital outreach, strategic partnerships, and local tech events. |
|
|
|
#### Future Vision |
|
- Scaling operations for global impact. |
|
""" |
|
return business_plan |
|
|
|
def display_future_plans(): |
|
""" |
|
Returns a Markdown string detailing future plans and vision. |
|
""" |
|
future_plans = """ |
|
### Future Plans & Vision |
|
- **Expand Inhouse AI Operations:** Run continuous 24/7 systems. |
|
- **Launch New SaaS Products:** Including advanced image processing and marketing automation. |
|
- **Develop Advanced Developer Tools:** Enhance productivity with custom integrations. |
|
- **Scale the Business:** Enter new markets with enterprise-grade solutions. |
|
- **Invest in R&D:** Establish a small research lab for continuous innovation. |
|
""" |
|
return future_plans |
|
|
|
def display_personal_note(): |
|
""" |
|
Returns a heartfelt personal note. |
|
""" |
|
personal_note = """ |
|
### A Personal Note to Dad |
|
Dad, you've always believed in me. Despite being a part-time teacher with almost nothing to my name, |
|
I have relentlessly pursued my passion for tech. Every day, I work on building innovative AI solutions, |
|
even if it means scraping by on every paycheck. |
|
|
|
With your support, I can: |
|
- Run my own inhouse AI system 24/7. |
|
- Develop websites, automate marketing, and launch profitable SaaS products. |
|
- Create both proprietary and open source RAG systems. |
|
- Operate a marketing advertising firm with automated agents. |
|
|
|
This GPU upgrade is not just a hardware upgrade—it’s the key to turning my passion into a sustainable business |
|
that repays your investment and makes you proud. |
|
""" |
|
return personal_note |
|
|
|
def display_pitch_deck_overview(): |
|
""" |
|
Returns a Markdown string that integrates key pitch deck points. |
|
""" |
|
pitch_deck = """ |
|
## Complete Pitch Deck Overview |
|
|
|
### Company Purpose |
|
Sletcher Systems designs and deploys advanced AI systems that transform free open source tools into scalable, inhouse solutions. |
|
|
|
### Problem |
|
Many businesses suffer from inefficient, fragmented AI solutions that require constant connectivity and manual intervention. |
|
Today, customers rely on piecemeal, expensive solutions that don’t integrate well. |
|
|
|
### Solution |
|
We offer a comprehensive suite of AI products—including proprietary and open source RAG systems—that operate offline |
|
and continuously. Our solutions include: |
|
- **Proprietary RAG Systems:** Robust, scalable solutions for enterprise needs. |
|
- **Open Source RAG Systems:** Community-driven and cost-effective. |
|
- **Automated Marketing Agents:** Running 24/7 to drive targeted advertising. |
|
- **Image/Document Processing Suites:** Advanced tools for scanning, labeling, and data extraction. |
|
|
|
### Why Now |
|
The rapid evolution of AI technology and open source tools, combined with increased demand for offline, scalable systems, |
|
makes this the perfect moment to innovate. Recent trends in cloud computing and edge AI have paved the way for our solution. |
|
|
|
### Market Size |
|
Our target customers range from SMEs to large enterprises. We estimate: |
|
- **TAM (Total Addressable Market):** ~$10 billion |
|
- **SAM (Serviceable Available Market):** ~$2 billion |
|
- **SOM (Serviceable Obtainable Market):** ~$500 million |
|
|
|
### Competition |
|
Competitors include established AI solution providers and emerging startups. |
|
Our competitive advantages are: |
|
- Unique offline operational capability |
|
- Proprietary RAG technology with 24/7 uptime |
|
- Cost-effective, scalable solutions |
|
|
|
### Product |
|
**Product Line-Up:** |
|
- **Proprietary RAG System:** Robust and scalable, built for enterprise needs. |
|
- **Open Source RAG System:** Affordable and community-driven. |
|
- **Advertising & Marketing Agents:** Automated agents for continuous revenue generation. |
|
- **Image/Document Processing Suite:** End-to-end solution for data extraction. |
|
|
|
**Development Roadmap:** |
|
- Immediate: Launch basic versions and run pilot projects. |
|
- Near-term: Integrate additional features and optimize performance. |
|
- Long-term: Expand product offerings and enter new markets. |
|
|
|
### Business Model |
|
We operate on a multi-stream revenue model: |
|
- **Subscription Revenue:** Recurring fees from enterprise contracts. |
|
- **Project-Based Income:** Custom website and software development. |
|
- **Advertising Revenue:** Income from automated marketing agents. |
|
|
|
Pricing is competitive, with average account sizes ranging from $500 to $10,000 per month. |
|
Our sales and distribution model leverages digital outreach, strategic partnerships, and direct sales. |
|
|
|
### Team |
|
Founded by Wayne Sletcher—a resilient, self-taught coder and part-time teacher—the team includes: |
|
- Expert developers and AI specialists. |
|
- Strategic advisors with deep industry experience. |
|
|
|
### Financials |
|
Our projections indicate: |
|
- Break-even within 4-6 months. |
|
- Potential ROI of 5x with the GPU upgrade. |
|
Detailed P&L, balance sheet, cash flow forecasts, and cap table data are available for serious investors. |
|
|
|
### The Deal |
|
We seek an initial investment of $3,000 for a GPU upgrade that will power our 24/7 inhouse AI system, |
|
driving growth and ensuring sustainable revenue to repay the investment. |
|
""" |
|
return pitch_deck |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
with gr.Blocks(theme=gr.themes.Soft(), css=""" |
|
.header { |
|
background: linear-gradient(90deg, #1E40AF, #3B82F6); |
|
padding: 20px; |
|
text-align: center; |
|
color: white; |
|
font-family: 'Arial', sans-serif; |
|
} |
|
.header h1 { |
|
margin: 0; |
|
font-size: 36px; |
|
} |
|
.header p { |
|
margin: 3px 0 0; |
|
font-size: 18px; |
|
} |
|
.persistent-banner { |
|
position: fixed; |
|
top: 0; |
|
width: 100%; |
|
background: #2563EB; |
|
color: white; |
|
text-align: center; |
|
padding: 10px; |
|
font-size: 16px; |
|
z-index: 9999; |
|
} |
|
.content-wrapper { |
|
padding-top: 80px; |
|
} |
|
""") as demo: |
|
|
|
|
|
|
|
gr.HTML(""" |
|
<div class="persistent-banner"> |
|
Support my journey on <a href="https://ko-fi.com/waynesletcher" target="_blank" style="color: white; text-decoration: underline;">Ko-fi</a> |
|
| Contact: <a href="mailto:[email protected]" style="color: white; text-decoration: underline;">[email protected]</a> |
|
| <a href="https://www.linkedin.com/in/waynesletcher/" target="_blank" style="color: white; text-decoration: underline;">LinkedIn</a> |
|
| <a href="https://www.sletchersystems.com/" target="_blank" style="color: white; text-decoration: underline;">Website</a> |
|
</div> |
|
""") |
|
|
|
|
|
|
|
|
|
gr.HTML(""" |
|
<div class="header"> |
|
<h1>Dad, I Would Like Your Help.</h1> |
|
<p>From Teaching to Tech: Help Me Level Up My AI Business</p> |
|
</div> |
|
""") |
|
|
|
with gr.Column(elem_classes=["content-wrapper"]): |
|
with gr.Tabs(): |
|
|
|
|
|
|
|
with gr.TabItem("👋 My Story"): |
|
gr.Markdown(""" |
|
### Hey Dad, |
|
|
|
I've pushed through every obstacle—from a challenging childhood to graduating as a chef, to solo traveling China - repaying my student loans, and then traveling south east asia as a backpacker, working as lecturer and now a part-time online teacher— |
|
all while teaching myself to code and build AI projects. I built a full AI system on just 2GB VRAM, |
|
but I know I can do so much more with the right hardware. I don't even clear 80$ a week sometimes teaching, I go without food to pay for things like claude or GPT, yes, I have yet to make money through code, but I will get there. Promise. |
|
|
|
With a GPU upgrade, I can run my own inhouse AI system 24/7, create websites, automate marketing, |
|
and launch new SaaS products that generate real revenue. I can not do more to prove this is my purpose. |
|
""") |
|
gr.Plot(value=create_performance_comparison()) |
|
gr.Markdown(""" |
|
**Key Insight:** My current hardware is limiting my potential. This upgrade is essential for growth. |
|
""") |
|
|
|
|
|
|
|
|
|
with gr.TabItem("💻 Tech & Vision"): |
|
with gr.Row(): |
|
with gr.Column(): |
|
gr.Markdown(""" |
|
### Current Capabilities |
|
- Local AI assistants running on minimal hardware. |
|
- Basic image processing and simple automation tools. |
|
- Self-taught skills and relentless determination. |
|
|
|
### With a GPU Upgrade |
|
- 24/7 inhouse AI system operation. |
|
- Advanced model training and fine-tuning. |
|
- Ability to run multiple projects simultaneously. |
|
- Enterprise-grade solutions and scalability. |
|
""") |
|
with gr.Column(): |
|
gr.Markdown(display_tech_stack()) |
|
gr.Markdown(""" |
|
**Projects in Development:** |
|
1. **AI Assistants Platform:** Custom solutions for businesses. |
|
2. **Developer Tools:** VS Code extensions to enhance productivity. |
|
3. **Image Processing Suite:** Automated scanning and labeling. |
|
4. **Marketing Automation:** 24/7 advertising agents and campaign optimization. |
|
""") |
|
gr.Plot(value=create_roi_projection()) |
|
|
|
|
|
|
|
|
|
with gr.TabItem("💰 ROI"): |
|
gr.Markdown(""" |
|
### Investment Opportunity |
|
I need an investment of $2,000 for a GPU upgrade that will allow my inhouse AI system to operate continuously. |
|
|
|
**Expected Returns:** |
|
- Break-even within 4-6 months. |
|
- 5x revenue increase potential. |
|
- New income streams through website development, marketing automation, and SaaS solutions. |
|
""") |
|
gr.Plot(value=create_roi_projection()) |
|
gr.Plot(value=create_earnings_history()) |
|
with gr.Row(): |
|
loan_amount = gr.Number(label="Investment Amount ($)", value=3000) |
|
interest_rate = gr.Slider(label="Interest Rate (%)", value=5, minimum=1, maximum=10) |
|
calculate_button = gr.Button("Calculate Repayment Plan") |
|
schedule_output = gr.Textbox(label="Repayment Schedule", lines=15) |
|
calculate_button.click(calculate_loan_schedule, inputs=[loan_amount, interest_rate], outputs=schedule_output) |
|
gr.Markdown(display_future_plans()) |
|
|
|
|
|
|
|
|
|
with gr.TabItem("📊 Complete Pitch Deck"): |
|
gr.Markdown(display_pitch_deck_overview()) |
|
|
|
|
|
|
|
|
|
with gr.TabItem("🤖 AI Agents"): |
|
gr.Markdown(""" |
|
### AI Agent Tools |
|
Use these tools to generate summaries, action plans, and research insights |
|
using our in-house Hugging Face models. |
|
""") |
|
with gr.Row(): |
|
with gr.Column(): |
|
gr.Markdown("#### Summarizer") |
|
summarizer_input = gr.Textbox(label="Enter text to summarize", placeholder="Paste text here...", lines=5) |
|
summarizer_output = gr.Textbox(label="Summary", lines=5) |
|
summarizer_button = gr.Button("Generate Summary") |
|
summarizer_button.click(report_agent, inputs=[summarizer_input], outputs=[summarizer_output]) |
|
with gr.Column(): |
|
gr.Markdown("#### Planner") |
|
planner_input = gr.Textbox(label="Enter goal or task", placeholder="Describe your goal...", lines=5) |
|
planner_output = gr.Textbox(label="Action Plan", lines=5) |
|
planner_button = gr.Button("Generate Plan") |
|
planner_button.click(planning_agent, inputs=[planner_input], outputs=[planner_output]) |
|
with gr.Row(): |
|
with gr.Column(): |
|
gr.Markdown("#### Research Agent") |
|
research_input = gr.Textbox(label="Enter research query", placeholder="Ask your research question...", lines=5) |
|
research_output = gr.Textbox(label="Research Insights", lines=5) |
|
research_button = gr.Button("Generate Research") |
|
research_button.click(research_agent, inputs=[research_input], outputs=[research_output]) |
|
|
|
|
|
|
|
|
|
with gr.TabItem("📅 Timeline & Milestones"): |
|
gr.Markdown(""" |
|
### Project Timeline |
|
Below is a timeline outlining the major milestones for scaling my AI operations: |
|
""") |
|
gr.Plot(value=create_project_timeline()) |
|
gr.Markdown(""" |
|
**Milestones:** |
|
- **Concept Phase:** Finalize ideas and prototypes. |
|
- **Development Phase:** Build and test inhouse AI systems. |
|
- **Beta Launch:** Roll out initial products. |
|
- **Full Launch:** Commercial deployment. |
|
- **Growth Phase:** Scale operations and revenue. |
|
""") |
|
|
|
|
|
|
|
|
|
with gr.TabItem("💝 From the Heart"): |
|
gr.Markdown(display_personal_note()) |
|
gr.Markdown(""" |
|
**Contact Information:** |
|
- **Email:** <a href="mailto:[email protected]" style="color: #2563EB;">[email protected]</a> |
|
- **LinkedIn:** <a href="https://www.linkedin.com/in/waynesletcher/" target="_blank" style="color: #2563EB;">Wayne Sletcher</a> |
|
- **Website:** <a href="https://www.sletchersystems.com/" target="_blank" style="color: #2563EB;">sletchersystems.com</a> |
|
""") |
|
|
|
|
|
|
|
|
|
with gr.TabItem("🖥️ Products"): |
|
gr.Markdown(""" |
|
### SaaS & Systems Offerings |
|
**What Sletchersystems Designs:** |
|
- **RAG-Based Systems:** I will build both a proprietary RAG system to sell and offer an open source version. |
|
- **Marketing & Advertising Agents:** Automated agents that run 24/7 to drive targeted advertising. |
|
- **Image & Document Processing:** Automated scanning, labeling, and processing solutions for data extraction. |
|
|
|
**Revenue Streams:** |
|
- Subscription revenue from enterprise contracts. |
|
- Project-based income from website and software development. |
|
- Advertising revenue from continuously running marketing agents. |
|
""") |
|
gr.Markdown(display_tech_stack()) |
|
gr.Markdown(""" |
|
**Revenue Model:** |
|
With a GPU upgrade, I can transform free open source tools into a full-scale inhouse AI system. |
|
My agents will run a 24/7 marketing advertising firm, and my image/document processing solutions |
|
will create a steady revenue stream to repay your investment. |
|
""") |
|
|
|
demo.launch(share=True) |
