Documentation
¶
Overview ¶
Package openpipe provides OpenPipe-backed LLM via OpenAI-compatible API.
Index ¶
Constants ¶
View Source
const DefaultLLMModel = "gpt-4.1"
DefaultLLMModel is the default OpenPipe chat model when none is specified.
Variables ¶
This section is empty.
Functions ¶
Types ¶
type LLMService ¶
type LLMService struct {
// contains filtered or unexported fields
}
LLMService implements services.LLMService using OpenPipe's OpenAI-compatible chat API.
func NewLLMService ¶
func NewLLMService(apiKey, model string) *LLMService
NewLLMService creates an OpenPipe LLM service. If apiKey is empty, config.GetEnv("OPENPIPE_API_KEY", "") is used. If model is empty, DefaultLLMModel is used.
func (*LLMService) Chat ¶
func (s *LLMService) Chat(ctx context.Context, messages []map[string]any, onToken func(*frames.LLMTextFrame)) error
Chat runs a completion and calls onToken for each streamed content delta (as LLMTextFrame).
Click to show internal directories.
Click to hide internal directories.