feat: 引入 Eino 框架并实现 AI 编排层基础设施与节点
- 引入 cloudwego/eino v0.9.9 和 eino-ext/components/model/openai v0.1.13 - 新增 internal/eino/ 包: - types.go: PipelineInput/Output、STTOutput、TokenUsage 类型定义 - state.go: PipelineState 跨节点状态收集(线程安全) - callback.go: ChatModel OnEndWithStreamOutput 回调,逐 token 推送 llm_chunk - nodes_stt.go: STT Lambda,支持文本/语音输入模式 - nodes_history.go: 历史组装 Lambda,含多模态图片支持 - nodes_splitter.go: 句子分割 Transform Lambda - nodes_tts.go: TTS Lambda,逐句合成推送音频 - nodes_done.go: Done Lambda,发送 llm_done 并追加历史 Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
92
backend/internal/eino/nodes_tts.go
Normal file
92
backend/internal/eino/nodes_tts.go
Normal file
@@ -0,0 +1,92 @@
|
||||
package eino
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/base64"
|
||||
|
||||
"github.com/cloudwego/eino/compose"
|
||||
|
||||
"github.com/hhs/camtalk/internal/ai/tts"
|
||||
"github.com/hhs/camtalk/internal/logger"
|
||||
"github.com/hhs/camtalk/internal/models"
|
||||
)
|
||||
|
||||
// NewTTSLambda 创建 TTS Lambda 节点。
|
||||
// 输入: []string(句子数组,框架自动从 StreamReader concat)→ 输出: struct{}
|
||||
//
|
||||
// 将句子数组转为 channel,调用 ttsService.SynthesizeStream() 流式合成,
|
||||
// 逐 chunk 推送 tts_audio 到客户端。TTS 失败静默跳过。
|
||||
func NewTTSLambda(ttsService tts.Service, ttsVoice string, ttsSpeed float64, ttsOutputFmt string, ttsSampleRate int) *compose.Lambda {
|
||||
return compose.InvokableLambda(func(ctx context.Context, sentences []string) (struct{}, error) {
|
||||
log := logger.Log
|
||||
sender := senderFromCtx(ctx)
|
||||
requestID := requestIDFromCtx(ctx)
|
||||
state := stateFromCtx(ctx)
|
||||
|
||||
// 检查 TTS 是否启用(从 State 或 context 获取)
|
||||
// TTSEnabled 信息在 PipelineInput 中,通过 State 传递
|
||||
if state != nil {
|
||||
state.mu.Lock()
|
||||
ttsEnabled := true // 默认启用,由适配器通过 State 设置
|
||||
state.mu.Unlock()
|
||||
if !ttsEnabled {
|
||||
return struct{}{}, nil
|
||||
}
|
||||
}
|
||||
|
||||
if len(sentences) == 0 {
|
||||
return struct{}{}, nil
|
||||
}
|
||||
|
||||
if sender == nil || requestID == "" {
|
||||
return struct{}{}, nil
|
||||
}
|
||||
|
||||
log.Infow("开始 TTS 合成", "request_id", requestID, "sentence_count", len(sentences))
|
||||
|
||||
// 将句子数组转为 channel(ttsService.SynthesizeStream 需要 <-chan string)
|
||||
sentenceCh := make(chan string, len(sentences))
|
||||
for _, s := range sentences {
|
||||
sentenceCh <- s
|
||||
}
|
||||
close(sentenceCh)
|
||||
|
||||
// 调用 TTS 服务
|
||||
ttsStream, err := ttsService.SynthesizeStream(ctx, sentenceCh, tts.Options{
|
||||
Voice: ttsVoice,
|
||||
Speed: ttsSpeed,
|
||||
OutputFmt: ttsOutputFmt,
|
||||
SampleRate: ttsSampleRate,
|
||||
})
|
||||
if err != nil {
|
||||
log.Errorw("TTS 合成启动失败(已跳过)", "error", err, "request_id", requestID)
|
||||
return struct{}{}, nil // TTS 失败不中断流程
|
||||
}
|
||||
|
||||
// 消费 TTS 音频流,推送到客户端
|
||||
for chunk := range ttsStream {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
log.Infow("TTS 流被中断", "request_id", requestID)
|
||||
return struct{}{}, ctx.Err()
|
||||
default:
|
||||
}
|
||||
|
||||
audioBase64 := base64.StdEncoding.EncodeToString(chunk.Audio)
|
||||
|
||||
if err := sender.SendTTSAudio(models.WsTTSAudio{
|
||||
Type: "tts_audio",
|
||||
RequestID: requestID,
|
||||
Audio: audioBase64,
|
||||
MimeType: "audio/mp3",
|
||||
IsLast: chunk.IsLast,
|
||||
Final: chunk.Final,
|
||||
}); err != nil {
|
||||
log.Errorw("发送 tts_audio 失败", "error", err)
|
||||
}
|
||||
}
|
||||
|
||||
log.Infow("TTS 合成完成", "request_id", requestID)
|
||||
return struct{}{}, nil
|
||||
})
|
||||
}
|
||||
Reference in New Issue
Block a user