Module llm

Module llm 

Source
Expand description

LLM abstraction: params, requests/responses, and the registry.

Modules§

gemini
Concrete Gemini LLM implementation using gemini-live Client.
registry
LLM registry — pattern-based resolution of LLM providers.

Structs§

EnvTokenProvider
Default token provider — reads GOOGLE_ACCESS_TOKEN from environment.
GcloudTokenProvider
Token provider that shells out to gcloud auth print-access-token, caching the result with a configurable TTL.
GeminiLlm
Concrete Gemini LLM implementation using gemini-live Client.
GeminiLlmParams
Parameters for constructing a GeminiLlm.
LlmRegistry
Registry that maps model name patterns to LLM factory functions.
LlmRequest
Configuration for an LLM generation request.
LlmResponse
The response from an LLM generation request.
MockLlm
A BaseLlm that replies from a script or a closure and records every request, for tests that must not reach a provider.
ModelCapabilities
Capability declaration for a model — what callers may rely on without probing. See BaseLlm::capabilities.
TokenUsage
Token usage statistics.

Enums§

LlmError
Errors from LLM operations.

Traits§

BaseLlm
Trait for LLM providers — decouples agents from specific models.
TokenProvider
Provides access tokens for VertexAI authentication.

Type Aliases§

LlmStream
A reply streamed in chunks; see BaseLlm::generate_stream.