Class OpenAIModelRunner

Runner implementation for OpenAI chat completions.

Implements the unified Runner protocol via run. Returned by OpenAIRunnerFactory.createModel.

Hierarchy

OpenAIModelRunner

Implements

Runner

Index

Constructors

Properties

_client _history _logger? _modelName _multiTurn _parameters

Methods

_runCompletion _runStructured getClient run

Constructors

constructor

new OpenAIModelRunner(client, config, logger?, multiTurn?): OpenAIModelRunner
Parameters
- client: OpenAI
- config: LDAICompletionConfig
- Optional logger: LDLogger
  Optional
- multiTurn: boolean = true
Returns OpenAIModelRunner
- Defined in ai-providers/server-ai-openai/src/OpenAIModelRunner.ts:27

Properties

`Private` _client

_client: OpenAI

`Private` _history

_history: LDMessage[]

`Private` `Optional` _logger

_logger?: LDLogger

`Private` _modelName

_modelName: string

`Private` _multiTurn

_multiTurn: boolean

`Private` _parameters

_parameters: Record<string, unknown>

Methods

`Private` _runCompletion

_runCompletion(messages): Promise<RunnerResult>
Parameters
- messages: LDMessage[]
Returns Promise<RunnerResult>
- Defined in ai-providers/server-ai-openai/src/OpenAIModelRunner.ts:84

`Private` _runStructured

_runStructured(messages, outputType): Promise<RunnerResult>
Parameters
- messages: LDMessage[]
- outputType: Record<string, unknown>
Returns Promise<RunnerResult>
- Defined in ai-providers/server-ai-openai/src/OpenAIModelRunner.ts:110

getClient

getClient(): OpenAI
Get the underlying OpenAI client instance.

Returns OpenAI
- Defined in ai-providers/server-ai-openai/src/OpenAIModelRunner.ts:80

run

run(input, outputType?): Promise<RunnerResult>
Run the OpenAI model with the given user prompt.

The runner maintains a conversation history that is initialized from any messages on the AI config (system prompt, instructions, etc.). On every invocation the user prompt is appended to the existing history before being sent to the model. When multiTurn is true (the default) and the call succeeds with non-empty content, the user prompt and the assistant's reply are persisted to the history so subsequent calls continue the conversation. When multiTurn is false, history is treated as read-only — useful for stateless runners (e.g. judges) where every call should see only the initial config messages plus the current input. Failed calls leave the history unchanged so the next call can retry cleanly.
Parameters
- input: string
  
  The user prompt string.
- Optional outputType: Record<string, unknown>
  
  Optional JSON schema for structured output. When provided, the response is parsed and exposed via RunnerResult.parsed.
  
  Optional
Returns Promise<RunnerResult>
Implementation of Runner.run
- Defined in ai-providers/server-ai-openai/src/OpenAIModelRunner.ts:60

Generated using TypeDoc