菜单
Implementing providers for Beluga AI v2 registries. Use when creating LLM, embedding, vectorstore, voice, or any other provider.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
| 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.