Documentation

Multimodal implements Pipeline

Implements a Google multimodal pipeline for AI models that accept both text and file inputs.

This pipeline retrieves configuration values for the Google Gemini model and API, sets up required headers and parameters (including an access token), and processes SUAprompt instances to format the request payload appropriately.

The pipeline supports output retrieval in multiple formats (text, JSON, array) and also provides streaming methods that yield output chunks.

Table of Contents

Interfaces

Pipeline
Defines the required methods for Ai Model Pipelines, which are required for compatibility with LaravelNeuro Agent Networking features.

Properties

$accessToken  : mixed
The Google Gemini API access token.
$baseApi  : mixed
The base API endpoint.
$driver  : GuzzleDriver
The driver instance for making API requests.
$model  : mixed
The model identifier used for the request.
$prompt  : mixed
The prompt data, processed from an SUAprompt instance.

Methods

__construct()  : mixed
Multimodal constructor.
array()  : array<string|int, mixed>
Retrieves the API response as an associative array.
driver()  : Driver
Accesses the injected Driver instance.
driverClass()  : string
Retrieves the class name of the default associated driver.
getDriver()  : Driver
Retrieves the current driver.
getModel()  : mixed
Retrieves the current model identifier.
getPrompt()  : mixed
Retrieves the current prompt.
json()  : string
Retrieves the API response as a JSON-formatted string.
output()  : string
Executes the API request and returns the generated text output.
promptClass()  : string
Retrieves the class name of the default associated prompt.
setApi()  : self
Sets the API endpoint for the driver.
setModel()  : self
Sets the model for the pipeline.
setPrompt()  : self
Sets the prompt for the pipeline.
stream()  : Generator
Executes a streaming API request and yields JSON-encoded output chunks.
streamArray()  : Generator
Executes a streaming API request and yields output as decoded arrays.
streamText()  : Generator
Executes a streaming API request and yields text output chunks.
text()  : string
Retrieves the text output from the API response.

Properties

$accessToken

The Google Gemini API access token.

protected mixed $accessToken

$baseApi

The base API endpoint.

protected mixed $baseApi

$model

The model identifier used for the request.

protected mixed $model

$prompt

The prompt data, processed from an SUAprompt instance.

protected mixed $prompt

Methods

__construct()

Multimodal constructor.

public __construct([Driver $driver = new GuzzleDriver() ]) : mixed

Retrieves configuration values for the Google Gemini API (model, endpoint, and access token), initializes the driver (defaulting to GuzzleDriver), sets required header entries, and validates that all required configuration values are present.

Parameters
$driver : Driver = new GuzzleDriver()

An instance implementing the Driver contract.

Tags
throws
InvalidArgumentException

if any required configuration value is missing.

array()

Retrieves the API response as an associative array.

public array() : array<string|int, mixed>
Return values
array<string|int, mixed> —

The decoded API response.

driver()

Accesses the injected Driver instance.

public driver() : Driver
Return values
Driver —

the Driver instance stored in this instance of the class.

driverClass()

Retrieves the class name of the default associated driver.

public driverClass() : string
Return values
string

getDriver()

Retrieves the current driver.

public getDriver() : Driver
Return values
Driver —

The driver instance.

getModel()

Retrieves the current model identifier.

public getModel() : mixed
Return values
mixed —

The model identifier.

getPrompt()

Retrieves the current prompt.

public getPrompt() : mixed
Return values
mixed —

The prompt data.

json()

Retrieves the API response as a JSON-formatted string.

public json() : string
Return values
string —

The JSON-encoded API response.

output()

Executes the API request and returns the generated text output.

public output() : string

This method is an alias for text().

Return values
string —

The generated text output.

promptClass()

Retrieves the class name of the default associated prompt.

public promptClass() : string
Return values
string

setApi()

Sets the API endpoint for the driver.

public setApi(string $address[, bool $stream = false ]) : self

Builds the full API URL by appending the model identifier, generate endpoint (or stream endpoint), and the access token to the provided base address. Updates the driver's API endpoint and the base API.

Parameters
$address : string

The base API address.

$stream : bool = false

Optional. If true, sets up the endpoint for streaming.

Tags
throws
InvalidArgumentException

If the access token is missing.

Return values
self

setModel()

Sets the model for the pipeline.

public setModel(mixed $model) : self

Stores the model identifier and updates the API endpoint accordingly.

Parameters
$model : mixed

The model identifier.

Return values
self

setPrompt()

Sets the prompt for the pipeline.

public setPrompt(SUAprompt $prompt) : self

Expects a SUAprompt instance. Processes each element in the prompt:

  • If the element contains a file pattern and is not of type "role", it converts it into an inline data structure.
  • Otherwise, wraps the text in an associative array. The method also extracts a system instruction from a "role" element, if present, and updates the driver's prompt and system_instruction request parameter.
Parameters
$prompt : SUAprompt

A SUAprompt instance.

Tags
throws
InvalidArgumentException

if the prompt is not a SUAprompt instance.

Return values
self

stream()

Executes a streaming API request and yields JSON-encoded output chunks.

public stream() : Generator

Sets the API to streaming mode, processes each output chunk, and yields the JSON-encoded chunk.

Return values
Generator —

Yields JSON-encoded data chunks.

streamArray()

Executes a streaming API request and yields output as decoded arrays.

public streamArray() : Generator

Sets the API to streaming mode, processes each output chunk, and yields the decoded output.

Return values
Generator —

Yields decoded output as an array.

streamText()

Executes a streaming API request and yields text output chunks.

public streamText() : Generator

Sets the API to streaming mode, processes each output chunk, and yields the text content if available in the candidate's content parts.

Return values
Generator —

Yields text output chunks.

text()

Retrieves the text output from the API response.

public text() : string

Decodes the response and returns the text content from the first candidate.

Return values
string —

The text output.


        

        
    




    

    

                                

                

                                
    

        On this page

        
    


                

                            

            

    

        

            
Search results