Working with LLMs in Python
Certificate of Completion by Code.Hub
This hands-on lab develops the practical skills required to integrate and control large language models within applications. Participants learn how to structure effective prompts, enforce reliable outputs, implement validation and retry strategies, and build robust abstraction layers around LLM providers. The focus is on transforming experimental AI calls into secure, maintainable, and production-ready components.
By the end of this module, participants will be able to:
- Configure an application environment and successfully integrate an external LLM API
- Apply structured prompt engineering techniques to improve output quality and reliability
- Enforce strict output schemas with validation, retry, and repair strategies
- Design resilient LLM wrapper components with proper logging, timeouts, and provider abstraction
- Implement safe prompt iteration practices while mitigating prompt injection risks
Setup & First LLM Call
Project setup
First API call
Prompt response loop
Prompt Engineering Essentials
Zero-shot vs few-shot
PCTF structure (Persona/Context/Task/Format)
Quick prompt iterations
Prompt injection awareness
Rubric for prompt quality
Structured Outputs & Validation
Return valid JSON
Validation
Retries
Strict schema to reduce drift
Repair retry
Building LLM Wrappers
Request/Response schemas
Timeouts and retries
Logging and Error handling
Provider abstraction layer
- Roles: Software Engineers, Software Architects, Technical Leads
- Seniority: Junior (with backend experience), Mid-Level to Senior Professionals
- Basic Python (functions, modules, virtual environments)
- Basic HTTP concepts (request/response)
- Basic terminal commands
Sessions can be delivered via the following formats:
- Live Online – Interactive virtual sessions via video conferencing
- On-Site – At your organization’s premises
- In-Person – At Code.Hub’s training center
- Hybrid – A combination of online and in-person sessions
Interested for
