Basics to AI-Agents: OpenAI API, Gemini API, Open-source LLMs, GPT-5, RAG, LangChain Apps, Colab and Prompt Engineering
InstructorArnold Oberleiter
Editorial course preview
These 4 complementary views highlight concrete, legible examples from the course presentation.
A flowchart diagram illustrating a RAG workflow with numbered steps, connecting a laptop, search process, knowledge sources, and an LLM endpoint.
A LinkedIn post by SmartBots AI featuring a flowchart that explains the role of vector databases and embeddings in processing content queries.
A code editor interface displaying Python scripts for OpenAI API integration, including GPT-4o chat completion and DALL-E image generation.
Desktop screenshot of the LM Studio interface displaying a model library with Llama 3 and Stable Code cards, alongside a small presenter video feed.
The curriculum covers a wide range of topics including Transformer architecture, scaling laws, and security considerations like prompt injections.
Instruction includes setting up local servers and running open-source models using tools like LM Studio and Ollama.
The curriculum lacks explicit coding exercises, quizzes, or structured projects. One signal from before the displayed update notes that the content consists of reading material aloud; the update may have addressed this, but the update label does not prove a correction.
One signal suggests difficulty following step-by-step workflows in Google Colab and Flowise. This signal predates the displayed course update; the update may have addressed it, but the update label does not prove that it was corrected.
The course aligns with its target of beginners, but the depth may not meet the needs of more advanced developers.