OpenAIRequest

Defined in: frontend/dist/types/adapters/openai.d.ts:93

OpenAI Chat Completions API request structure.

Defines all parameters for making a chat completion request to OpenAI’s API. This matches the official OpenAI API specification and is compatible with OpenAI-compatible endpoints (Azure OpenAI, local models, etc.).

See

• OpenAIMessage
• OpenAIResponse
• https://platform.openai.com/docs/api-reference/chat/create

Example

const request: OpenAIRequest = {
  model: 'gpt-4',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello!' }
  ],
  temperature: 0.7,
  max_tokens: 150
};

Properties

frequency_penalty?

optional frequency_penalty: number

Defined in: frontend/dist/types/adapters/openai.d.ts:105

Penalty for token frequency -2 to 2. Reduces repetition

---

max_tokens?

optional max_tokens: number

Defined in: frontend/dist/types/adapters/openai.d.ts:101

Maximum tokens to generate in the response

---

messages

messages: OpenAIMessage[]

Defined in: frontend/dist/types/adapters/openai.d.ts:97

Array of conversation messages

---

model

model: string

Defined in: frontend/dist/types/adapters/openai.d.ts:95

Model ID (e.g., ‘gpt-4’, ‘gpt-3.5-turbo’)

---

presence_penalty?

optional presence_penalty: number

Defined in: frontend/dist/types/adapters/openai.d.ts:107

Penalty for token presence -2 to 2. Encourages new topics

---

seed?

optional seed: number

Defined in: frontend/dist/types/adapters/openai.d.ts:115

Deterministic sampling seed for reproducible outputs

---

stop?

optional stop: string | string[]

Defined in: frontend/dist/types/adapters/openai.d.ts:109

Stop sequence(s) - generation stops when encountered

---

stream?

optional stream: boolean

Defined in: frontend/dist/types/adapters/openai.d.ts:111

Enable streaming responses via Server-Sent Events

---

temperature?

optional temperature: number

Defined in: frontend/dist/types/adapters/openai.d.ts:99

Sampling temperature 0-2. Higher = more random. Default 1

---

top_p?

optional top_p: number

Defined in: frontend/dist/types/adapters/openai.d.ts:103

Nucleus sampling parameter 0-1. Alternative to temperature

---

user?

optional user: string

Defined in: frontend/dist/types/adapters/openai.d.ts:113

Unique user identifier for abuse monitoring