AI SDK Core

AI SDK Core is a set of functions that allow you to interact with language models and other AI models. These functions are designed to be easy-to-use and flexible, allowing you to generate text, structured data, and embeddings from language models and other AI models.

AI SDK Core contains the following main functions:

• generateText(): Generate text and call tools from a language model.
• streamText(): Stream text and call tools from a language model.
• Output: Structured output types for generateText and streamText.
• embed(): Generate an embedding for a single value using an embedding model.
• embedMany(): Generate embeddings for several values using an embedding model (batch embedding).
• generateImage(): Generate images based on a given prompt using an image model.
• experimental_generateVideo(): Generate videos based on a given prompt using a video model.
• experimental_startBatch(): Start an asynchronous text-generation batch.
• experimental_getBatchStatus(): Retrieve the status of an asynchronous batch.
• experimental_getBatchResults(): Retrieve terminal results from an asynchronous batch.
• experimental_cancelBatch(): Request cancellation of an asynchronous batch.
• experimental_listBatches(): List asynchronous batches and their latest statuses.
• transcribe(): Generate a transcript from an audio file.
• experimental_streamTranscribe(): Stream a transcript from live raw audio.
• experimental_streamTranslate(): Stream a speech-to-speech translation from live raw audio.
• generateSpeech(): Generate speech audio from text.
• experimental_streamSpeech(): Stream speech audio from text or a text stream.
• uploadFile(): Upload a file to a provider and get a provider reference.
• uploadSkill(): Upload a skill to a provider and get a provider reference.

It also contains the following helper functions:

• toolSearch(): Search deferred tools and load their definitions on demand.
• tool(): Type inference helper function for tools.
• experimental_getRealtimeToolDefinitions(): Convert AI SDK tools into realtime tool definitions.
• Experimental_SandboxSession: Experimental execution environment interface passed to tool execution.
• experimental_filterActiveTools(): Filters a tool set to only the currently active tools.
• createMCPClient(): Creates a client for connecting to MCP servers.
• MCP Events: Experimental event methods, webhook delivery, and subscription types.
• MCP Apps: Helpers for rendering interactive MCP tool UIs and filtering app-visible tools.
• jsonSchema(): Creates AI SDK compatible JSON schema objects.
• zodSchema(): Creates AI SDK compatible Zod schema objects.
• createProviderRegistry(): Creates a registry for using models from multiple providers.
• cosineSimilarity(): Calculates the cosine similarity between two vectors, e.g. embeddings.
• simulateReadableStream(): Creates a ReadableStream that emits values with configurable delays.
• wrapLanguageModel(): Wraps a language model with middleware.
• wrapImageModel(): Wraps an image model with middleware.
• extractReasoningMiddleware(): Extracts reasoning from the generated text and exposes it as a reasoning property on the result.
• extractJsonMiddleware(): Extracts JSON from text content by stripping markdown code fences.
• isStepCount(): Creates a stop condition that triggers after a specified number of steps.
• hasToolCall(): Creates a stop condition that triggers when any specified tool is called.
• isLoopFinished(): Creates a stop condition that lets the agent loop run until it naturally finishes.
• simulateStreamingMiddleware(): Simulates streaming behavior with responses from non-streaming language models.
• defaultSettingsMiddleware(): Applies default settings to a language model.
• defaultInstructionsMiddleware(): Applies default instructions to a language model.
• smoothStream(): Smooths text and reasoning streaming output.
• generateId(): Helper function for generating unique IDs
• createIdGenerator(): Creates an ID generator