Crate zeph_llm 

LLM provider abstraction and backend implementations.

Re-exports

pub use classifier::metrics::ClassifierMetrics;

pub use classifier::metrics::ClassifierMetricsSnapshot;

pub use classifier::metrics::TaskMetricsSnapshot;

pub use claude::ThinkingConfig;

pub use claude::ThinkingEffort;

pub use error::LlmError;

pub use extractor::Extractor;

pub use gemini::ThinkingLevel as GeminiThinkingLevel;

pub use provider::ChatStream;

pub use provider::LlmProvider;

pub use provider::StreamChunk;

pub use provider::ThinkingBlock;

pub use stt::SpeechToText;

pub use stt::Transcription;

Modules

any

classifier

ML-backed classifier infrastructure (feature classifiers).

claude

Claude (Anthropic) LLM provider implementation.

compatible

ema

Per-provider EMA tracker for latency-aware super::router::RouterProvider ordering.

error

extractor

gemini

http

Shared HTTP client construction for consistent timeout and TLS configuration.

mock

Test-only mock LLM provider.

model_cache

Disk-backed cache for remote model listings with 24-hour TTL.

ollama

openai

provider

router

Provider router: EMA-based, Thompson Sampling, Cascade, and PILOT Bandit strategies.

stt

whisper