Building LLM Applications with APIs and Frameworks

Build LLM applications with leading APIs and frameworks

Generative AI becomes truly useful when you can turn prompts and models into working applications. On this three-week course, you’ll learn how to build LLM applications using leading APIs and frameworks, developing practical skills for modern generative AI development.

You’ll work with LLM APIs from OpenAI, Anthropic, Gemini, and Mistral, as well as open-source models. By the end of the course, you’ll have the expertise to build LLM-powered applications using commercial APIs and leading frameworks, preparing you for roles in LLM application development and generative AI.

Develop applications with LangChain and LlamaIndex

Explore the frameworks that support modern LLM application development. You’ll use LangChain to build chains, tools, and memory, while using LangChain Expression Language to structure application logic.

You’ll also work with LlamaIndex to ingest documents, build indexes, and query information. By combining these frameworks, you’ll learn how to connect LLMs with data and tools to create more capable AI applications.

Build reliable and production-ready AI applications

Develop the skills needed to move beyond experimentation and build more dependable LLM applications. You’ll learn how to select models by balancing cost, latency, and capability, while applying caching, retries, logging, and observability to improve reliability.

Through hands-on API integration, parameter tuning, and multi-step chains, you’ll put your learning into practice. The course culminates in a project where you’ll build a working LLM application with tool integration.

This course is designed for learners who understand how LLMs work and can design effective prompts and who now want to develop working GenAI applications in Python.

It is ideal for developers building AI features, data professionals creating LLM-powered tools, and engineers preparing for LLM application developer roles. Learners should be comfortable with Python and prompt engineering before starting. By the end, they will be able to build LLM-powered applications using commercial APIs and orchestration frameworks.

This course is designed for learners who understand how LLMs work and can design effective prompts and who now want to develop working GenAI applications in Python.

It is ideal for developers building AI features, data professionals creating LLM-powered tools, and engineers preparing for LLM application developer roles. Learners should be comfortable with Python and prompt engineering before starting. By the end, they will be able to build LLM-powered applications using commercial APIs and orchestration frameworks.

• Explain how LLM APIs, generation parameters, structured outputs, and tool calling support application development.
• Apply API integration techniques to configure model behaviour, stream responses, and manage token usage and cost.
• Develop LLM workflows using LangChain and LlamaIndex with chains, tools, memory, document ingestion, and querying.
• Evaluate models and application approaches based on cost, latency, capability, reliability, and output quality.
• Create an end-to-end LLM application that integrates models, tools, reliability mechanisms, and observability practices.