llmwire - v2.2.0
    Preparing search index...

    Class OllamaProvider

    Hierarchy (View Summary)

    Index
    _supportedModels: string[] = []
    baseConfig: BaseProviderConfig
    • get baseURL(): string

      Origin this provider talks to; shown in PROVIDER_UNREACHABLE hints.

      Returns string

    • Provider-specific reading of an error body. Return the fields you can tell from it (code, providerCode, hint, retryAfterMs); the status code default fills the rest.

      Parameters

      • _status: number
      • json: any
      • text: string

      Returns Refinement

    • A fresh AIError for a failure this provider detects itself (no key, no model, blocked answer).

      Parameters

      • code: AIErrorCode
      • message: string
      • extra: { details?: unknown; hint?: string; model?: string } = {}

      Returns AIError

    • Streaming request: the body as an async iterable of bytes, idle-guarded. Non-2xx throws [HttpError].

      Parameters

      Returns Promise<AsyncIterable<Uint8Array>>

    • Check if the Ollama CLI is available on the system (needs cli in the config).

      Returns Promise<boolean>

    • Records what discovery found, keeping any seeded models first so the caller's chosen default stays the default.

      Parameters

      • ids: string[]

      Returns string[]