Vercel AI SDK

1. Introduction

   The AI SDK as a TypeScript toolkit with unified provider APIs.

2. Providers and models

   Provider abstraction, model ids, and switching between providers.

3. Generating text

   generateText and streamText with prompts, messages, and streaming.

4. Generating structured data

   Schema-based object generation with Zod.

5. Tools and tool calling

   Defining tools, multi-step calls, and tool results.

6. Agents

   Agent loops, stop conditions, and building workflows.

7. AI SDK UI and chatbots

   The useChat hook, message streaming, and building chat UIs.

8. Embeddings

   embed and embedMany for semantic search and RAG.

9. Language model middleware

   Intercepting and modifying model calls for caching, logging, or guardrails.

10. Model Context Protocol tools

    Using MCP servers as tool sources.

11. Image generation, speech, and transcription

    Multimodal generation APIs.

12. Error handling and telemetry

    Telemetry and observability for AI calls, plus error handling.

Each section links to the official page. Titles and summaries by Extra Credit; the docs belong to their authors.