GenAI.Provider.Gemini.Image
(Noizu Labs, GenAI Wrapper v0.3.2)
Copy Markdown
Gemini Imagen image-generation provider — a SYNC media provider (ADR-016 / ede43647).
Declares text -> image (sync) and runs POST /v1beta/models/{model}:predict (the
Imagen predict endpoint, API key as a query param), returning the base64 image in the
shared {:ok, %{data, mime, meta}} contract. No-key requests fast-fail with
{:error, :missing_api_key} before any network call.
Image-INPUT (image+text -> image edits, the :generateContent inline_data path) is the
follow-up increment that introduces the per-provider encoder_protocol ImageContent
clause (dmitri N1) reused by vision + edit; this module is the text->image cut.
Summary
Functions
Callback implementation for GenAI.InferenceProviderBehaviour.chat/7.
Return config_key inference provide application config stored under :genai entry
Obtain map of effective settings: settings, model_settings, provider_settings, config_settings, etc.
Prepare endpoint and method to make inference call to
Prepare request headers
Prepare request body to be passed to inference call.
Build and run inference thread
Callback implementation for GenAI.InferenceProviderBehaviour.standardize_model/1.
Build and run inference thread in streaming mode
Functions
chat(model, messages, tools, hyper_parameters, provider_settings \\ [], context \\ nil, options \\ nil)
Callback implementation for GenAI.InferenceProviderBehaviour.chat/7.
Return config_key inference provide application config stored under :genai entry
Obtain map of effective settings: settings, model_settings, provider_settings, config_settings, etc.
Prepare endpoint and method to make inference call to
Prepare request headers
Prepare request body to be passed to inference call.
Build and run inference thread
Callback implementation for GenAI.InferenceProviderBehaviour.standardize_model/1.
Build and run inference thread in streaming mode