Orchestration and Tool Use

Auto-generated from data/terms.json. Do not edit this file manually.

Orchestration

Orchestration is the coordination and management of multiple systems, models, tools, and services to carry out tasks in a structured and reliable way. In the context of AI, orchestration ensures that prompts, workflows, external tools, memory, and control flow work together so the overall system behaves predictably and achieves its intended goals.

Also known as: LLM orchestration

Sources:

• https://www.ibm.com/think/topics/ai-orchestration
• https://www.databricks.com/glossary/orchestration

Tool Calling

Tool calling (also known as function calling) is the capability for an AI model to invoke external tools, APIs, or systems in order to extend what it can do. It allows the model to access, retrieve, and manipulate data or perform actions outside its training data by passing structured arguments to defined functions or custom tools. This makes it possible to build applications where the model not only reasons and generates language, but also interacts with databases, services, and other software components provided by your application.

Also known as: function calling, open functions, actions

Sources:

• https://www.ibm.com/think/topics/tool-calling
• https://blog.langchain.com/tool-calling-with-langchain/
• https://platform.openai.com/docs/guides/function-calling