메뉴
Implementing providers for Beluga AI v2 registries. Use when creating LLM, embedding, vectorstore, voice, or any other provider.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Documentation writing patterns for Beluga AI v2. Use when creating package docs, tutorials, API guides, or teaching-oriented content.
Go framework design patterns for Beluga AI v2. Use when designing package structure, registries, lifecycle, or creating new packages.
Go interface design with registry, middleware, and hooks for Beluga AI v2. Use when creating interfaces, extension contracts, or adding hooks/middleware.
Go testing patterns for Beluga AI v2. Use when writing tests, mocks, or benchmarks.
Go 1.23 iter.Seq2 streaming patterns for Beluga AI v2. Use when implementing streaming, transforms, or backpressure.
SOC 직업 분류 기준
| name | provider-implementation |
| description | Implementing providers for Beluga AI v2 registries. Use when creating LLM, embedding, vectorstore, voice, or any other provider. |
init() with parent package's Register().core.Error with correct ErrorCode.var _ Interface = (*Impl)(nil).llm/providers/openai/
├── openai.go # Implementation + New() + init()
├── stream.go # Streaming
├── errors.go # Error mapping
├── openai_test.go # Tests
└── testdata/ # Recorded HTTP responses
var _ llm.ChatModel = (*Model)(nil)
func init() {
llm.Register("openai", func(cfg llm.ProviderConfig) (llm.ChatModel, error) { return New(cfg) })
}
func New(cfg llm.ProviderConfig) (*Model, error) {
if cfg.APIKey == "" { return nil, &core.Error{Op: "openai.new", Code: core.ErrAuth, Message: "API key required"} }
return &Model{client: newClient(cfg.APIKey, cfg.BaseURL), model: cfg.Model}, nil
}
func (m *Model) Stream(ctx context.Context, msgs []schema.Message, opts ...llm.GenerateOption) iter.Seq2[schema.StreamChunk, error] {
return func(yield func(schema.StreamChunk, error) bool) { /* stream implementation */ }
}
switch apiErr.StatusCode {
case 401: code = core.ErrAuth
case 429: code = core.ErrRateLimit
case 408, 504: code = core.ErrTimeout
case 400: code = core.ErrInvalidInput
}
See docs/providers.md for provider categories and priorities.