Struct OpenAiClient 

pub struct OpenAiClient { /* private fields */ }

Client for interactions with OpenAI’s API, particularly for generating embeddings

Implementations

impl OpenAiClient

pub fn new(config: Option<&LlmConfig>) -> Result<Self>

Creates a new OpenAI client.

Uses the provided configuration or falls back to environment variables. Will attempt to read OPENAI_API_KEY from environment if not specified in config.

pub fn get_embedding_config(&self) -> &EmbeddingModelConfig

Get current embedding model configuration

Trait Implementations

impl Clone for OpenAiClient

fn clone(&self) -> OpenAiClient

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl EmbeddingProvider for OpenAiClient

fn generate_embedding<'life0, 'life1, 'async_trait>( &'life0 self, text: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<Vec<f32>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Generates an embedding for a single text.

fn generate_embeddings<'life0, 'async_trait>( &'life0 self, texts: Vec<String>, ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Generates embeddings for multiple texts in a single API call.

Arguments

• texts - Vector of strings to generate embeddings for

Returns

Vector of embedding vectors, in the same order as the input texts

fn count_tokens(&self, text: &str) -> Result<usize>

Counts the number of tokens in a text using the cl100k_base tokenizer.

Uses the same tokenizer as the OpenAI API to get accurate token counts.