Function Calling & Tool Use: Multi-Model Production Patterns
«Function Calling & Tool Use: Multi-Model Production Patterns» è un corso online di RAG e AI engineering di livello intermedio, tenuto da InsightLearn Curated AI su InsightLearn. Il percorso comprende 6 lezioni organizzate in 2 sezioni, per una durata complessiva di 8h 0m. Master function calling across OpenAI, Claude, and Gemini: parallel calls, tool orchestration, and error recovery.
- Docente: InsightLearn Curated AI
- Categoria: RAG e AI engineering
- Livello: intermedio
- Durata: 8h 0m
- Accesso: gratuito in questa fase di validazione, in cambio di un feedback al termine
- Certificato: certificato di completamento verificabile online
Descrizione del corso
InsightLearn è in fase di sviluppo (work in progress): i contenuti di questa pagina sono pubblicati esclusivamente a fini di verifica e test.
A comprehensive guide to function calling and tool use across major LLM providers. Covers JSON Schema tool definitions, parallel vs sequential tool calls, nested tool invocations, tool result injection, error handling and retry strategies, building tool registries, OpenAI function calling vs Claude tool use vs Gemini function calling API differences, and designing robust agentic loops with tool use.
Cosa imparerai
- Curated from public resources. Master function calling across OpenAI, Claude, and Gemini: parallel calls, tool orchestration, and error recovery.
Programma del corso
- JSON Schema for tool definitions: types, required, descriptions (25 min)
- OpenAI function calling: parallel tools and tool_choice (30 min)
- Claude tool use: input schema and tool_result blocks (22 min)
- Parallel tool calls: reducing latency in multi-step agents (32 min)
- Tool registries and dynamic tool loading (28 min)
- Error recovery in tool use agentic loops (35 min)
Dalle lezioni
Estratto della trascrizione di «JSON Schema for tool definitions: types, required, descriptions»
Welcome to this lecture of the course Function Calinganto-Luse, last of the production patterns. In this session, we will explore the definition scheme. Types, requirements, descriptions. We will start with the fundamental concepts and the theoretical principles of the base. We will then see practical applications and almost universal applications in the world of the Europe. Let's analyze them. and the best practices of the sector. At the end of this lesson, you will be able to apply autonomously the techniques of the Json Schema Fortor Definitions in your projects. We will start with the fundamental concepts and the theoretical principles of the base. We will then see practical applications and almost universal applications in the world of development. We…
Estratto della trascrizione di «OpenAI function calling: parallel tools and tool_choice»
Welcome to this lecture of the course Function Calling and Torluse, the last of the Production Patterns. In this session we will explore Open AI Function Calling, parallel torls and torchoice. We will start with the fundamental concepts and the basic theoretical principles. We will then see practical applications and almost universal applications in the world of development. We will analyze them in concrete elements. of the sector. At the end of this lesson you will be able to apply autonomously the techniques of Open AI Function Calling in your projects. We will start with the fundamental concepts and the theoretical principles of the base. We will then see practical applications and almost universal ones in the world of development…
Estratto della trascrizione di «Claude tool use: input schema and tool_result blocks»
Anthropic has introduced tool use or function calling in their LLMs as a public beta. So what is function calling in LLMs? So function calling allows LLMs basically you to create code whereby you can execute your functions locally and with this function calling you can augment the LLM to generate better outputs. That is the idea. So the user could. have some input. Now the input could be something like, you know, a simple example is a calculator, you want to create a calculator using an LLM. So the input could be a string like what is the result of multiplying two numbers. Okay, so this is your input, and this you want to give it as an input…
Altri corsi di RAG e AI engineering
- LangSmith: Tracing, Debugging, and Monitoring LLM Apps
- LLM Evals: RAGAS, DeepEval, and Automated Testing
- Local LLMs: Ollama, vLLM, and Self-Hosted AI
- Multimodal AI: Vision, Audio, and Image Generation APIs
- Advanced Prompt Engineering: Chain-of-Thought, Few-Shot, and Beyond
- RAG from Scratch: Complete Retrieval-Augmented Generation
Domande frequenti
Quanto dura il corso Function Calling & Tool Use: Multi-Model Production Patterns?
Il corso dura 8h 0m in totale, con 6 lezioni suddivise in 2 sezioni, da seguire online al proprio ritmo.
Serve esperienza pregressa?
Il corso è di livello intermedio e non indica requisiti specifici di ingresso.
Il corso rilascia un certificato?
Sì: al completamento del corso ricevi un certificato di completamento verificabile online.