LLM 튜토리얼

Learn how to use Google's Gemini 2.0 Flash model to develop a visual assistant capable of reading on-screen content and answering questions about it using Python.

Learn about the Qwen2.5-Coder series by building an AI code review assistant using Qwen 2.5-Coder-32B-Instruct and Gradio.

Learn about the new Amazon Nova models (Micro, Lite, Pro, Premier, Canvas, Reel), how to access them through the Bedrock Playground and API, and how to build a demo multi-agent app.

Learn how Anthropic's contextual retrieval improves the accuracy of retrieval systems and how to implement it step-by-step.

Learn how to use Microsoft’s TinyTroupe to simulate interactions between AI personas with distinct characteristics for different purposes.

Learn how to use Mistral’s Pixtral Large via Le Chat or access it programmatically through the API on La Plateforme.

Learn how to implement late chunking with Jina AI to improve context preservation and retrieval accuracy in RAG applications.

Learn what prompt caching is and how to use it with Ollama to optimize LLM interactions, reduce costs, and improve performance in AI apps.

Learn how to implement recursive retrieval in RAG systems using LlamaIndex to improve the accuracy and relevance of retrieved information, especially for large document collections.

Learn how to evaluate your LLM on code generation capabilities with the Hugging Face Evaluate library.

Learn what speculative decoding is, how it works, when to use it, and how to implement it using Gemma2 models.

Learn how to use OpenAI’s gpt-4o-audio-preview model with LangChain to build voice-enabled applications that include audio input, transcription, and generation.