Week #6 #

Links #

Specify here all the necessary links to your website, application installer, final demo, etc.

• Deployment: skillsnavigator.ru
• API Docs: GitHub
• Design: Figma

Final deliverables #

Project Overview #

SkillsNavigator.ai is a platform designed to help users build a personalized learning journey, tailored to their current skills, career goals, and budget. Whether you’re aiming to become a developer or pursuing a different path, SkillsNavigator.ai recommends the most effective and affordable online courses to achieve your objectives. The platform provides step-by-step guidance, cost-aware resources, and a clear view of your progress at every stage.

Problems Solved #

1. Too Many Courses, Not Enough Guidance

Problem: Users often struggle to choose the best courses from a vast sea of online options.

Solution: SkillsNavigator.ai uses advanced vector search and AI-powered recommendations to match you with the most relevant and effective courses, eliminating the guesswork.

2. Lack of Personalized Learning Paths

Problem: Most existing platforms rarely tailor recommendations to your unique skill level, goals, available time, or budget.

Solution: SkillsNavigator.ai creates a fully personalized learning journey based on your current skills, career aspirations, time constraints, and budget—so every step is relevant and achievable.

3. Difficulty Tracking Progress and Next Steps

Problem: It’s hard to keep track of your learning progress and plan what to do next.

Solution: SkillsNavigator.ai provides a clear, interactive roadmap and real-time progress tracking, making it easy to monitor your achievements and see exactly what to learn next.

Key Features #

Advanced Vector Search #

• Free-form chat input—just describe your goals or skills, and get instant recommendations.
• Quick processing: Recommendations are provided in real-time.
• Course details at a glance: View each course’s image, rating, difficulty, duration (hours), number of enrolled students, name, author, and price.
• Direct course access: One click to open the course in Stepik.
• Chat history: Keeps a record of all your chats for easy reference.
• Multiple chat sessions: Support for managing several learning chats at once.
• One-click roadmap: Instantly generate a learning roadmap from your chat.

Сonvenient Roadmap #

• Automatic roadmap generation: Forms a clear learning path using courses found via advanced vector search, prioritized logically by AI (LLM) based on your skill level and needs.
• Sequential display: All recommended courses are shown in the suggested learning order.
• Minimalistic, clear roadmap: Easy to follow and visually clean.
• Rich course info on hover: See detailed course info (image, rating, difficulty, hours, students enrolled, name, author, price) by pointing at any node.
• Progress tracking: Monitor your advancement directly through Stepik.
• Easy access: Go straight to any course from the roadmap.
• Roadmap history: Track and revisit previous roadmaps.
• Multiple roadmaps: Manage several learning journeys at the same time.

Stepik Integration #

• Login with Stepik: Sign in using your Stepik account for a seamless experience.
• Persistent history: View your chat and roadmap history at any time.
• Progress synchronization: See your progress on each roadmap and course, updated in real time.

Tech stack #

• React - Frontend;
• FastAPI - Backend;
• qdrant (vector DB) - Vector Embeddings and Search;
• Deepseek - course selection;
• Docker - Deploy.
• PostgreSQL - DataBase for users, chats, roadmaps.

Setup instructions #

1. Clone the Repository #

git clone <your-repo-url>
cd <your-repo-directory>

2. Set Up Environment Variables #

Copy the example .env file to create your actual .env file, then edit as needed:

cp .env.example .env
# Open .env in your preferred editor to adjust values:
# nano .env

3. Build and Launch with Docker Compose #

Use the provided Docker Compose file for your local environment:

docker compose -f docker-compose.local.yml up --build

4. Access the Application #

• Check the terminal output for which ports the services are running on.
• Open the application in your web browser.

Presentation draft #

Link to GitHub

Weekly commitments #

Individual contribution of each participant #

Plan for Next Week #

Check if the service handles the load, prepare the presentation design, successfully defend the project.

Confirmation of the code’s operability #

We confirm that the code in the main branch:

• [✔] In working condition.
• [✔] Run via docker-compose (or another alternative described in the README.md).