Struct OpenAiConfig 

pub struct OpenAiConfig {
    pub api_key: String,
    pub base_url: String,
    pub model: String,
    pub max_tokens: u32,
    pub embedding_model: Option<String>,
    pub reasoning_effort: Option<String>,
}

Configuration for OpenAiProvider.

Pass to OpenAiProvider::new instead of individual positional arguments to avoid silent parameter transposition.

Examples

use zeph_llm::openai::{OpenAiConfig, OpenAiProvider};

let cfg = OpenAiConfig {
    api_key: "sk-...".into(),
    base_url: "https://api.openai.com/v1".into(),
    model: "gpt-4o".into(),
    max_tokens: 4096,
    embedding_model: Some("text-embedding-3-small".into()),
    reasoning_effort: None,
};
let provider = OpenAiProvider::new(cfg);

Fields

api_key: String

Secret API key sent in the Authorization: Bearer header.

base_url: String

Base URL of the endpoint, e.g. "https://api.openai.com/v1". Trailing slashes are stripped automatically.

model: String

Chat model identifier, e.g. "gpt-4o".

max_tokens: u32

Upper bound on completion tokens returned by the model.

embedding_model: Option<String>

Embedding model identifier. Set to None when the endpoint does not support embeddings.

reasoning_effort: Option<String>

Reasoning effort level for o* models ("low", "medium", or "high"). Leave None for standard chat models.

Trait Implementations

impl Clone for OpenAiConfig

fn clone(&self) -> OpenAiConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for OpenAiConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.