Struct VlmClient 

pub struct VlmClient {
    inner: Client<OpenAIConfig>,
    model: String,
}

Direct HTTP client for an OpenAI-compatible chat-completions endpoint. Cheap to clone — async_openai::Client wraps a reqwest::Client (an Arc<...> internally). No mutex needed when sharing across tasks.

Fields

inner: Client<OpenAIConfig>

model: String

Implementations

impl VlmClient

pub fn new(cfg: &VlmConfig) -> Self

pub async fn chat_stream( &self, messages: &[Message], tools: &[ToolDef], ) -> Result<Pin<Box<dyn Stream<Item = Result<VlmStreamItem>> + Send>>>

Open a streaming chat completion. Yields:

• TextDelta for every assistant content chunk
• ToolCall once per accumulated function call (after the upstream finishes streaming all argument deltas)
• one final Finish

Trait Implementations

impl Clone for VlmClient

fn clone(&self) -> VlmClient

Returns a duplicate of the value.

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

Performs copy-assignment from source.