Skip to content

Commit 8c5e117

Browse files
raishsraishs
authored
Merge branch 'main' into main
2 parents e03bbae + 909c9b4 commit 8c5e117

File tree

4 files changed

+256
-1
lines changed

4 files changed

+256
-1
lines changed

‎docs/showcase/citypulse-ai-search.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
11
---
2-
title: CityPulse - AI-Powered Geospatial Discovery Search
2+
title: CityPulse | AI-Powered Geospatial Discovery Search
33
description: Real-time local discovery search using Perplexity AI for personalized location insights and recommendations
44
sidebar_position: 2
55
keywords: [perplexity, geospatial, location, real-time, maps, local-discovery, sonar]

‎docs/showcase/cycle-sync-ai.mdx

Lines changed: 97 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,97 @@
1+
---
2+
title: CycleSyncAI | Personalized Health Plans Powered by Sonar API
3+
description: iOS app that delivers personalized diet and workout recommendations for women, powered by Apple HealthKit and Perplexity's Sonar Pro API.
4+
sidebar_position: 7
5+
keywords: [CycleSyncAI, Sonar API, Perplexity, HealthKit, iOS, menstrual cycle, fitness, nutrition, LLM, AI, wellness, personalized, app]
6+
---
7+
8+
**CycleSyncAI** is an iOS app designed to provide personalized **diet and workout recommendations** tailored to a woman's **menstrual cycle phase**.
9+
10+
By integrating menstrual data from Apple **HealthKit** and optional user profile inputs (age, weight, height, medical conditions, dietary restrictions, goals, and preferences), the app generates dynamic, phase-aware suggestions to support holistic wellness.
11+
12+
Unlike static wellness tools, **CycleSyncAI** leverages **Perplexity's Sonar Pro API** to deliver **expert-informed**, LLM-generated guidance — including a daily grocery list and motivational feedback — customized to the user's cycle and lifestyle.
13+
14+
## Problem & Solution
15+
16+
> **Why it matters:**
17+
Most apps overlook the hormonal changes that affect women's fitness and nutrition needs across their cycle, leaving users with generic advice.
18+
19+
**CycleSyncAI** bridges this gap by combining Apple HealthKit data with Sonar Pro's LLM to generate **adaptive, cycle-aware recommendations** for better health outcomes.
20+
21+
## Features
22+
23+
* **Personalized diet & workout suggestions** per cycle phase
24+
* Syncs with Apple HealthKit for real-time cycle tracking
25+
* User profile inputs for advanced personalization (age, goals, restrictions, etc.)
26+
* **Auto-generated daily grocery list**
27+
* Smooth, modern UI with gradients and subtle animations
28+
* **Motivational AI feedback** tailored to user preferences
29+
* Local data storage and private processing
30+
31+
## Motivation
32+
33+
> "I wanted a tailored regime for myself and couldn't find it all in one place."
34+
35+
**CycleSyncAI** was born from the need for a science-backed, easy-to-use app that adapts wellness guidance to women's natural hormonal rhythms, something missing in most mainstream fitness and nutrition platforms.
36+
37+
## Repository Structure
38+
39+
```
40+
CycleSyncAI.xcodeproj → Xcode project file
41+
CycleSyncAI/ → Source code
42+
├── EatPlanViewController.swift → Diet plan generation & display
43+
├── WorkoutPlanViewController.swift → Workout plan generation & display
44+
├── HomepageViewController.swift → Navigation & main screen
45+
├── UserProfileViewController.swift → Input & storage of user data
46+
├── HealthManager.swift → Apple HealthKit menstrual data
47+
├── UserProfile.swift → Local profile model
48+
Main.storyboard → App UI & layout
49+
Assets.xcassets → Images & app icons
50+
Info.plist → Permissions & configurations
51+
```
52+
53+
## Setup Instructions
54+
55+
1. Clone the repo
56+
2. Open in **Xcode**
57+
3. Ensure Apple HealthKit is enabled on your device
58+
4. Insert your **Sonar Pro API key**
59+
5. Run the app on a physical device (recommended)
60+
61+
## Sonar API Usage
62+
63+
The app sends structured prompts to the **Sonar Pro API** including:
64+
65+
* Cycle phase (from HealthKit)
66+
* User profile info (age, weight, goals, etc.)
67+
* Meal preferences & restrictions
68+
69+
In return, it receives:
70+
71+
* **Personalized diet plan**
72+
* **Custom workout plan**
73+
* **Daily grocery list**
74+
* **Motivational feedback**
75+
76+
These are parsed and rendered as styled HTML inside the app using WebViews.
77+
78+
## Demo Video
79+
80+
Watch the full app walkthrough here: https://www.youtube.com/watch?v=R558uRLNvUM&t=2s.
81+
82+
> *Note: The LLM takes ~30–60 seconds per request. This wait time was trimmed in the video for brevity.*
83+
84+
## Impact
85+
86+
**CycleSyncAI** empowers women to make informed, body-aware decisions in daily life. The app supports better:
87+
88+
* Energy management
89+
* Fitness results
90+
* Mental well-being
91+
* Motivation and confidence
92+
93+
It also reduces decision fatigue with automatically prepared grocery lists and uplifting guidance.
94+
95+
## Links
96+
97+
* [GitHub Repository](https://github.com/medhini98/cyclesyncai-api-cookbook)

‎docs/showcase/flameguardai.mdx

Lines changed: 99 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,99 @@
1+
---
2+
title: FlameGuardAI | AI-powered wildfire prevention
3+
description: AI-powered wildfire prevention using OpenAI Vision + Perplexity Sonar API
4+
sidebar_position: 8
5+
keywords: [FlameGuardAI, MCP, External Fire ,AI Home Safety, Home Inspection]
6+
---
7+
8+
## 🧠 What it does
9+
10+
**FlameGuard AI™** helps homeowners, buyers, and property professionals detect and act on **external fire vulnerabilities** like wildfires or neighboring structure fires. It's more than a scan — it's a personalized research assistant for your home.
11+
12+
### Demo
13+
14+
[![Watch Live video](https://img.youtube.com/vi/EI5yT7_aD6U/0.jpg)](https://www.youtube.com/watch?v=EI5yT7_aD6U)
15+
16+
### Try it out
17+
18+
- [FlameGuard AI](https://flameguardai.dlyog.com)
19+
- [FlameGuard AI MCP](https://flameguardai-mcp.dlyog.com)
20+
- [GitHub Repo](https://github.com/dlyog/fire-risk-assessor-drone-ai)
21+
22+
### Key Features:
23+
- 📸 Upload a home photo
24+
- 👁️ Analyze visible fire risks via **OpenAI Vision API**
25+
- 📚 Trigger deep research using the **Perplexity Sonar API**
26+
- 📄 Get a detailed, AI-generated report with:
27+
- Risk summary
28+
- Prevention strategies
29+
- Regional best practices
30+
- 🛠️ Optional contractor referrals for mitigation
31+
- 💬 Claude (MCP) chatbot integration for conversational analysis
32+
- 🧾 GDPR-compliant data controls
33+
34+
Whether you're protecting your home, buying a new one, or just want peace of mind — **FlameGuard AI™ turns a photo into a plan**.
35+
36+
## ⚙️ How it works
37+
38+
### The FlameGuard AI™ Process
39+
40+
1. **📸 Upload**: User uploads a photo of their property
41+
2. **👁️ AI Vision Analysis**: OpenAI Vision API identifies specific vulnerabilities (e.g., flammable roof, dry brush nearby)
42+
3. **🔍 Deep Research**: For each risk, we generate a **custom research plan** and run **iterative agentic-style calls** to Perplexity Sonar
43+
4. **📄 Report Generation**: Research is **aggregated, organized, and formatted** into an actionable HTML report — complete with citations, links, and visual guidance
44+
5. **📧 Delivery**: Detailed report sent via email with DIY solutions and professional recommendations
45+
46+
### 🔍 Deep Research with Perplexity Sonar API
47+
48+
The real innovation is how we use the **Perplexity Sonar API**:
49+
50+
- We treat it like a research assistant gathering the best available information
51+
- Each vulnerability triggers multiple queries covering severity, mitigation strategies, and localized insights
52+
- Results include regional fire codes, weather patterns, and local contractor availability
53+
54+
This kind of **structured, trustworthy, AI-powered research would not be possible without Perplexity**.
55+
56+
### Technical Stack
57+
58+
FlameGuard AI™ is powered by a modern GenAI stack and built to scale:
59+
60+
- **Frontend**: Lightweight HTML dashboard with user account control, photo upload, and report access
61+
- **Backend**: Python (Flask) with RESTful APIs
62+
- **Database**: PostgreSQL (local) with **Azure SQL-ready** schema
63+
- **AI Integration**: OpenAI Vision API + Perplexity Sonar API
64+
- **Cloud-ready**: Built for **Azure App Service** with Dockerized deployment
65+
66+
## 🏆 Accomplishments that we're proud of
67+
68+
- Successfully used **OpenAI Vision + Perplexity Sonar API** together in a meaningful, real-world workflow
69+
- Built a functioning **MCP server** that integrates seamlessly with Claude for desktop users
70+
- Created a product that is **genuinely useful for homeowners today** — not just a demo
71+
- Kept the experience simple, affordable, and scalable from the ground up
72+
- Made structured deep research feel accessible and trustworthy
73+
74+
## 📚 What we learned
75+
76+
- The **Perplexity Sonar API** is incredibly powerful when used agentically — not just for answers, but for reasoning.
77+
- Combining **multimodal AI (image + research)** opens up powerful decision-support tools.
78+
- Users want **actionable insights**, not just data — pairing research with guidance makes all the difference.
79+
- Trust and clarity are key: our design had to communicate complex information simply and helpfully.
80+
81+
## 🚀 What's next for FlameGuard AI™ - Prevention is Better Than Cure
82+
83+
We're just getting started.
84+
85+
### Next Steps:
86+
- 🌐 Deploy to **Azure App Services** with production-ready database
87+
- 📱 Launch mobile version with location-based scanning
88+
- 🏡 Partner with **home inspection services** and **homeowners associations**
89+
- 💬 Enhance Claude/MCP integration with voice-activated AI reporting
90+
- 💸 Introduce B2B plans for real estate firms and home safety consultants
91+
- 🛡️ Expand database of **local contractor networks** and regional fire codes
92+
93+
We're proud to stand with homeowners — not just to raise awareness, but to enable action.
94+
95+
**FlameGuard AI™ – Because some homes survive when others don't.**
96+
97+
---
98+
99+
**Contact us to know more: [email protected]**

‎docs/showcase/valetudo-ai.mdx

Lines changed: 59 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
1+
---
2+
title: Valetudo AI | Trusted Medical Answer Assistant
3+
description: Sonar-powered medical assistant for fast, science-backed answers.
4+
sidebar_position: 6
5+
keywords: [medical, AI assistant, Perplexity Sonar]
6+
---
7+
8+
# Valetudo AI
9+
10+
**Valetudo AI** is a science-backed medical assistant powered by the Perplexity Sonar API. It provides fast, clear, and well-cited answers to health questions — helping users cut through misinformation with filters, image analysis, and ready-made prompt templates.
11+
12+
Designed for conscious users — like parents, patients, and medical students — seeking reliable information.
13+
14+
## Features
15+
16+
- **Cited Answers** — sourced from a curated list of 10 trusted medical domains
17+
- **Smart Filters** — by date and country for localized, up-to-date insights
18+
- **Image Upload** — analyze photos of medication, conditions, or packaging
19+
- **Prompt Templates** — 7 categories for symptom checks, drug safety, research, and more
20+
- **Simple UI** — built with React and Tailwind CSS
21+
22+
## How It Uses the Sonar API
23+
24+
Valetudo AI integrates with [Perplexity Sonar Pro](https://docs.perplexity.ai), leveraging advanced features for domain-specific search and rich responses:
25+
26+
| Feature | API Field | Purpose |
27+
|-----------------------|------------------------------------|----------------------------------------------------|
28+
| Context Control | `search_context_size: medium` | Balances speed and depth for focused medical Q&A |
29+
| Trusted Domains | `search_domain_filter` | Restricts results to vetted health sources |
30+
| Visual Input | `image_url` | Enables image-based medical queries |
31+
| Freshness Filter | `search_after/before_date_filter` | Helps surface recent and relevant findings |
32+
| Local Relevance | `user_location` | Tailors answers based on user’s region |
33+
34+
## Links
35+
36+
- [GitHub Repository](https://github.com/vero-code/valetudo-ai)
37+
- [Devpost Submission](https://devpost.com/software/valetudo-ai)
38+
- [View All Screenshots](https://github.com/vero-code/valetudo-ai/tree/master/screenshots)
39+
40+
## Demo Video
41+
42+
See Valetudo AI in action:
43+
[![Watch the demo](https://img.youtube.com/vi/AX3nOh9LbTc/0.jpg)](https://www.youtube.com/watch?v=AX3nOh9LbTc)
44+
45+
## Screenshots
46+
47+
### Home Interface
48+
<img src="https://github.com/vero-code/valetudo-ai/blob/master/screenshots/1-home.png" alt="Home screen" width="800" />
49+
50+
### Prompt Templates
51+
<img src="https://github.com/vero-code/valetudo-ai/blob/master/screenshots/10-prompts.png" alt="Prompt templates" width="800" />
52+
53+
### Image Upload
54+
<img src="https://github.com/vero-code/valetudo-ai/blob/master/screenshots/8-image-upload.png" alt="Image upload" width="800" />
55+
56+
### Date & Location Filters
57+
<img src="https://github.com/vero-code/valetudo-ai/blob/master/screenshots/7-date-filter.png" alt="Date filter" width="800" />
58+
59+
<img src="https://github.com/vero-code/valetudo-ai/blob/master/screenshots/9-location-filter.png" alt="Location filter" width="800" />

0 commit comments

Comments
 (0)