OpenAIBuilder class
OpenAI-specific LLM builder with provider-specific configuration methods
This builder provides a layered configuration approach where OpenAI-specific parameters are handled separately from the generic LLMBuilder, keeping the main builder clean and focused.
Use this for OpenAI-specific parameters only. For common parameters like apiKey, model, temperature, etc., continue using the base LLMBuilder methods.
Constructors
- OpenAIBuilder(LLMBuilder _baseBuilder)
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
build(
) → Future< ChatCapability> - Builds and returns a configured LLM provider instance
-
buildAssistant(
) → Future< AssistantCapability> - Builds a provider with AssistantCapability
-
buildAudio(
) → Future< AudioCapability> - Builds a provider with AudioCapability
-
buildEmbedding(
) → Future< EmbeddingCapability> - Builds a provider with EmbeddingCapability
-
buildFileManagement(
) → Future< FileManagementCapability> - Builds a provider with FileManagementCapability
-
buildImageGeneration(
) → Future< ImageGenerationCapability> - Builds a provider with ImageGenerationCapability
-
buildModelListing(
) → Future< ModelListingCapability> - Builds a provider with ModelListingCapability
-
buildModeration(
) → Future< ModerationCapability> - Builds a provider with ModerationCapability
-
buildOpenAIResponses(
) → Future< OpenAIProvider> - Builds an OpenAI provider with Responses API enabled
-
computerUseTool(
{required int displayWidth, required int displayHeight, required String environment, Map< String, dynamic> ? parameters}) → OpenAIBuilder - Adds computer use built-in tool
-
fileSearchTool(
{List< String> ? vectorStoreIds, Map<String, dynamic> ? parameters}) → OpenAIBuilder - Adds file search built-in tool
-
forAnalysis(
{int topLogprobsCount = 5}) → OpenAIBuilder - Configure for analysis tasks with log probabilities
-
forCodeGeneration(
{int? seed}) → OpenAIBuilder - Configure for code generation with deterministic output
-
forConversation(
) → OpenAIBuilder - Configure for conversational AI with balanced creativity
-
forCreativeWriting(
) → OpenAIBuilder - Configure for creative writing with reduced repetition
-
forFactualResponses(
{int? seed}) → OpenAIBuilder - Configure for factual and consistent responses
-
frequencyPenalty(
double penalty) → OpenAIBuilder - Sets frequency penalty for reducing repetition (-2.0 to 2.0)
-
logitBias(
Map< String, double> bias) → OpenAIBuilder - Sets logit bias for specific tokens
-
logprobs(
bool enabled) → OpenAIBuilder - Enables or disables log probabilities
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
parallelToolCalls(
bool enabled) → OpenAIBuilder - Enables or disables parallel tool calls
-
presencePenalty(
double penalty) → OpenAIBuilder - Sets presence penalty for encouraging topic diversity (-2.0 to 2.0)
-
previousResponseId(
String responseId) → OpenAIBuilder - Sets previous response ID for chaining responses
-
seed(
int seedValue) → OpenAIBuilder - Sets seed for deterministic outputs
-
topLogprobs(
int count) → OpenAIBuilder - Sets the number of most likely tokens to return log probabilities for
-
toString(
) → String -
A string representation of this object.
inherited
-
useResponsesAPI(
[bool use = true]) → OpenAIBuilder - Enables the new Responses API instead of Chat Completions API
-
verbosity(
Verbosity level) → OpenAIBuilder - Sets verbosity level for GPT-5 family models
-
webSearch(
{WebSearchContextSize contextSize = WebSearchContextSize.medium}) → OpenAIBuilder - Configures web search for OpenAI models
-
webSearchTool(
) → OpenAIBuilder - Adds web search built-in tool
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited