API Reference Noizu Labs, GenAI Wrapper v#0.3.2

This module implements the GenAI provider for Groq AI.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

Defines some common Anthropic models.

Module for interacting with the Cerebras inference API.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

Module for interacting with the OpenAI API.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

This module implements the GenAI provider for Mistral AI.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

Gemini Imagen image-generation provider — a SYNC media provider (ADR-016 / ede43647).

This module implements the GenAI provider for Groq AI.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

Defines some common Groq models.

Module for interacting with a LiteLLM proxy.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

LiteLLM media-generation provider (ADR-016) — the proxy can host many media model types, so this declares the full set and dispatches by output modality

Shared OpenAI-compatible media-generation calls (ADR-016), parameterized by base_url + API key so the OpenAI providers and the LiteLLM proxy providers share ONE definition of each endpoint's request build + response decode (dmitri's "one definition" principle)

Shared helpers for the sync media-generation providers (ADR-016 / ede43647): API-key resolution (request -> env, fast-fail when absent), prompt-text extraction, and the base64-image decode into the {:ok, %{data, mime, meta}} return contract. One definition reused by the OpenAI + Gemini image providers (and future media providers).

This module implements the GenAI provider for Mistral AI.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

Defines some common Mistral models.

Module for interacting with the Ollama API. Ollama provides local LLM inference with various open-source models.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

Module for interacting with the OpenAI API.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

OpenAI image-generation provider (gpt-image-1) — a SYNC media provider (ADR-016 / ede43647).

OpenAI text-to-speech provider — a SYNC media provider (ADR-016).

OpenAI speech-to-text (transcription) provider — a SYNC media provider (ADR-016).

Suno music / sound generation provider (ADR-016). NOT an LLM — media only.

Module for interacting with the XAI API.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.

Module for interacting with the Z.AI (Zhipu GLM) API.

Encoders use their module's EncoderProtocol to prep messages and tool definitions To make future extensibility for third parties straight forward. If a new message type, or tool type is added one simply needs to implement a EncoderProtocol for it and most cases you can simply cast it to generic known type and then invoke the protocol again.