This track equips learners to proficiently create, integrate, test, and deploy AI-driven applications and prompt engineering solutions, leveraging modern AI models and real-life cloud environments. This is a back-end oriented project.
Project Definition
- Chatbot inside school that answers parents questions. The chatbot has access to a knowledge base of educational pdfs and is able to answer parents’ questions as an in-house psychologist for the children.
MVP
Timeline
Week | Topic | Project Tasks | Learning (Read/Watch/Exercise) | Completed |
1-2 | Define project idea and get it approved by Role Expert by EOW. | Done | ||
3 | Backend | - setup a server
- setup a database
- setup a GitHub repository and connect the project to it. add Git Ignore.
- Create an ENV file to store sensitive data (database API Key)
- connect server to database
- create first API endpoints to test all CRUD operations for one collection in the database.
- Use PyLint to ensure a high level of code quality.
- Use prettier to ensure alignment in code formatting. | FastAPI
SQLite
| Done |
4 | AI | - Proof of Concept with LLM
- Create a comparison table between the LLMs in our case study and reach a recommendation of what to use.
- Define a UML/diagram of the flow of prompts.
- Choosing the Gen stack (frameworks, libraries). | Gemini API
LLM Models Integration
Prompting techniques
| Done |
5-7 | AI | - Enchance with RAG | Vector DB
Text splitting
Chunking
Retrieving | Done |
MVP requirements
- AI Model Integration: Integrate pre-trained models (e.g., GPT-3) via LangChain.
- Data Handling: Create a pipeline for data preprocessing, cleaning, and preparation.
- Prompt Engineering: Design effective prompts for various use cases using LangChain.
- API Development: Build APIs to integrate AI models (FastAPI / Flask).
- Database: Use a database (e.g., PostgreSQL) to store prompts, user data, and responses.
- Validation and Security: Validate inputs and sanitize data to prevent injection attacks.
- Deployment: Deploy the app on cloud platforms (Vercel / Render) with ENV variables, repo, git, build pipeline.
- No UI: Focus on backend functionalities only.
- Authentication - Minimal version (Firebase).
- Langchain usage.
V2
V2 optional requirements
- Testing
- Data Preprocessing, Embeddings.
- Integrations
- Connect GPT with external end-point that we created
- Connect GPT to Database
- Authentication: Implement authentication using JWT. (Moved here by Alon)
- Caching, Token Optimization
- UI