InstructorLite.Adapters.Gemini (instructor_lite v1.3.0)

Gemini adapter.

This adapter is implemented using Text generation endpoint configured for structured output

Params

params argument should be shaped as a models.GenerateBody request body

Example

InstructorLite.instruct(
  %{contents: [%{role: "user", parts: [%{text: "John is 25yo"}]}]},
  response_model: %{name: :string, age: :integer},
  json_schema: %{
    type: "object",
    required: [:age, :name],
    properties: %{name: %{type: "string"}, age: %{type: "integer"}}
  },
  adapter: InstructorLite.Adapters.Gemini,
  adapter_context: [
    model: "gemini-1.5-flash-8b",
    api_key: Application.fetch_env!(:instructor_lite, :gemini_key)
  ]
)
{:ok, %{name: "John", age: 25}}

Specifying model

Note how, unlike other adapters, the Gemini adapter expects model under adapter_context.

JSON Schema

The adapter uses Gemini's responseJsonSchema field which accepts standard JSON Schema, including features like $ref, $defs, title, and additionalProperties that Gemini's older responseSchema field does not support.

Chat Completions Compatible

If any of the limitations above are important to you, know that Gemini also provides a chat completion endpoint. You can use it with the InstructorLite.Adapters.ChatCompletionsCompatible adapter.

Summary

Functions

find_output(response, opts)

Parse text generation endpoint response in search of plain text output.

initial_prompt(params, opts)

Puts systemInstruction and updates generationConfig in params with prompt based on json_schema and notes.

parse_response(response, opts)

Parse text generation endpoint response.

retry_prompt(params, resp_params, errors, response, opts)

Updates params with prompt for retrying a request.

send_request(params, opts)

Make request to Gemini API

Functions

find_output(response, opts)

Parse text generation endpoint response in search of plain text output.

Can return:

{:ok, text_output} on success.
{:error, :refusal, prompt_feedback} if request was blocked.
{:error, :unexpected_response, response} if response is of unexpected shape.

initial_prompt(params, opts)

Puts systemInstruction and updates generationConfig in params with prompt based on json_schema and notes.

parse_response(response, opts)

Parse text generation endpoint response.

Can return:

{:ok, parsed_json} on success.
{:error, :refusal, prompt_feedback} if request was blocked.
{:error, :unexpected_response, response} if response is of unexpected shape.

retry_prompt(params, resp_params, errors, response, opts)

Updates params with prompt for retrying a request.

send_request(params, opts)

Make request to Gemini API

Options

:api_key (String.t/0) - Required. Gemini API key
:http_client (atom/0) - Any module that follows Req.post/2 interface The default value is Req.
:http_options (keyword/0) - Options passed to http_client.post/2 The default value is [receive_timeout: 60000].
:url (String.t/0) - API endpoint to use for sending requests The default value is "https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent".
:model (String.t/0) - Gemini model The default value is "gemini-3.5-flash-lite".