Enum Provider 

pub enum Provider {
    LMStudio,
    Ollama,
    LlamaCpp,
    VLLM,
}

Local inference providers with conventional OpenAI-compatible endpoint URLs.

Variants

LMStudio

LM Studio - Popular GUI-based local model server (default port 1234)

Ollama

Ollama - Command-line focused local model server (default port 11434)

LlamaCpp

llama.cpp - C++ inference engine with server mode (default port 8080)

VLLM

vLLM - High-performance inference server (default port 8000)

Implementations

impl Provider

pub fn default_url(&self) -> &'static str

Returns the conventional local URL, without consulting environment variables.

LM Studio uses port 1234, Ollama 11434, llama.cpp 8080, and vLLM 8000; each URL ends in /v1.

Trait Implementations

impl Clone for Provider

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for Provider

impl Debug for Provider

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

Formats the value using the given formatter.

impl Eq for Provider

impl FromStr for Provider

fn from_str(s: &str) -> Result<Self, Self::Err>

Parses a case-insensitive provider name.

Accepts lmstudio, lm-studio, lm_studio, ollama, llamacpp, llama-cpp, llama_cpp, llama.cpp, and vllm. Unknown names return an error.

type Err = String

The associated error which can be returned from parsing.

impl PartialEq for Provider

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for Provider