XEngineers/CamTalk
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 更新配置文档

Browse Source
This commit is contained in:
hhs
2026-06-13 19:57:35 +08:00
parent f764b3a7d8
commit 0d9d3db73b
12 changed files with 83 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
.env.example Normal file
View File

@@ -0,0 +1,21 @@
# CamTalk 环境变量模板
# 复制为 .env 并填入实际值：cp .env.example .env
# .env 已在 .gitignore 中，不会提交到版本控制
# ---- AI 服务 API Key ----
CAMTALK_AI_LLM_API_KEY=sk-xxx
CAMTALK_AI_STT_API_KEY=
CAMTALK_AI_TTS_API_KEY=
# ---- 可选覆盖（默认值见 config.yaml）----
# CAMTALK_AI_LLM_MODEL=gpt-4o
# CAMTALK_AI_LLM_ENDPOINT=https://api.openai.com/v1
# CAMTALK_AI_LLM_TIMEOUT=10
# CAMTALK_AI_STT_ENDPOINT=wss://api.deepgram.com/v1/listen
# CAMTALK_AI_TTS_ENDPOINT=https://api.openai.com/v1
# CAMTALK_AI_TTS_VOICE=alloy
# CAMTALK_AI_TTS_SPEED=1.0
# CAMTALK_AI_TTS_TIMEOUT=5
# ---- 应用 ----
# APP_ENV=dev

6
backend/cmd/server/main.go
View File

@@ -46,12 +46,12 @@ func main() {
defer sessionMgr.(*session.MemoryManager).Stop()
// 初始化 AI 服务
sttService := stt.NewDeepgramService(cfg.AI.STT.APIKey, cfg.AI.STT.Endpoint, logger.Log)
sttService := stt.NewDeepgramService(cfg.AI.STT.APIKey, cfg.AI.STT.Model, cfg.AI.STT.Endpoint, logger.Log)
llmService := llm.NewOpenAIService(cfg.AI.LLM.APIKey, cfg.AI.LLM.Model, cfg.AI.LLM.Endpoint, cfg.AI.LLM.Timeout, logger.Log)
ttsService := tts.NewOpenAIService(cfg.AI.TTS.APIKey, cfg.AI.TTS.Voice, cfg.AI.TTS.Endpoint, cfg.AI.TTS.Speed, cfg.AI.TTS.Timeout, logger.Log)
ttsService := tts.NewOpenAIService(cfg.AI.TTS.APIKey, cfg.AI.TTS.Model, cfg.AI.TTS.Voice, cfg.AI.TTS.Endpoint, cfg.AI.TTS.Speed, cfg.AI.TTS.Timeout, logger.Log)
// 初始化 Orchestrator
orch := orchestrator.New(sttService, llmService, ttsService, sessionMgr)
orch := orchestrator.New(sttService, llmService, ttsService, sessionMgr, cfg.AI.LLM.Model)
// Gin 模式
if cfg.App.Env == "prod" {

12
backend/config.yaml
View File

@@ -15,18 +15,20 @@ redis:
ai:
stt:
provider: deepgram
endpoint: "wss://api.deepgram.com/v1/listen"
provider: xiaomi
model: mimo-v2.5
endpoint: "https://token-plan-cn.xiaomimimo.com/v1"
llm:
provider: openai
model: gpt-4o
model: qwen3-vl-plus
endpoint: "https://api.openai.com/v1"
timeout: 10
tts:
provider: openai
provider: xiaomi
model: mimo-v2.5
voice: alloy
speed: 1.0
endpoint: "https://api.openai.com/v1"
endpoint: "https://token-plan-cn.xiaomimimo.com/v1"
timeout: 5
storage:

1
backend/go.mod
View File

@@ -27,6 +27,7 @@ require (
github.com/go-playground/validator/v10 v10.20.0 // indirect
github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
github.com/goccy/go-json v0.10.2 // indirect
github.com/joho/godotenv v1.5.1 // indirect
github.com/json-iterator/go v1.1.12 // indirect
github.com/klauspost/cpuid/v2 v2.2.10 // indirect
github.com/leodido/go-urn v1.4.0 // indirect

2
backend/go.sum
View File

@@ -44,6 +44,8 @@ github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg=
github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=

9
backend/internal/ai/stt/deepgram.go
View File

@@ -16,17 +16,22 @@ import (
// DeepgramService 基于 Deepgram WebSocket API 的语音识别实现。
type DeepgramService struct {
apiKey string
model string
endpoint string
logger *zap.SugaredLogger
}
// NewDeepgramService 创建 Deepgram STT 服务。
func NewDeepgramService(apiKey, endpoint string, logger *zap.SugaredLogger) *DeepgramService {
func NewDeepgramService(apiKey, model, endpoint string, logger *zap.SugaredLogger) *DeepgramService {
if model == "" {
model = "nova-2"
}
if endpoint == "" {
endpoint = "wss://api.deepgram.com/v1/listen"
}
return &DeepgramService{
apiKey: apiKey,
model: model,
endpoint: endpoint,
logger: logger,
}
@@ -128,7 +133,7 @@ func (d *DeepgramService) buildURL(opts Options) string {
q.Set("encoding", encoding)
q.Set("sample_rate", fmt.Sprintf("%d", sampleRate))
q.Set("language", language)
q.Set("model", "nova-2")
q.Set("model", d.model)
q.Set("punctuate", "true")
u.RawQuery = q.Encode()

12
backend/internal/ai/stt/deepgram_test.go
View File

@@ -74,7 +74,7 @@ func TestDeepgramService_Recognize_Success(t *testing.T) {
})
defer srv.Close()
svc := NewDeepgramService("test-key", wsToWss(srv.URL)+"/v1/listen", zap.NewNop().Sugar())
svc := NewDeepgramService("test-key", "", wsToWss(srv.URL)+"/v1/listen", zap.NewNop().Sugar())
text, err := svc.Recognize(context.Background(), []byte("fake-pcm-audio"), Options{
Encoding: "pcm_s16le",
@@ -90,7 +90,7 @@ func TestDeepgramService_Recognize_Success(t *testing.T) {
}
func TestDeepgramService_Recognize_EmptyAudio(t *testing.T) {
svc := NewDeepgramService("test-key", "ws://localhost", zap.NewNop().Sugar())
svc := NewDeepgramService("test-key", "", "ws://localhost", zap.NewNop().Sugar())
_, err := svc.Recognize(context.Background(), nil, Options{})
if err == nil {
t.Fatal("Recognize() with empty audio should return error")
@@ -98,7 +98,7 @@ func TestDeepgramService_Recognize_EmptyAudio(t *testing.T) {
}
func TestDeepgramService_Recognize_ConnectError(t *testing.T) {
svc := NewDeepgramService("test-key", "ws://localhost:1", zap.NewNop().Sugar())
svc := NewDeepgramService("test-key", "", "ws://localhost:1", zap.NewNop().Sugar())
ctx, cancel := context.WithTimeout(context.Background(), 2*time.Second)
defer cancel()
@@ -117,7 +117,7 @@ func TestDeepgramService_Recognize_Timeout(t *testing.T) {
})
defer srv.Close()
svc := NewDeepgramService("test-key", wsToWss(srv.URL)+"/v1/listen", zap.NewNop().Sugar())
svc := NewDeepgramService("test-key", "", wsToWss(srv.URL)+"/v1/listen", zap.NewNop().Sugar())
ctx, cancel := context.WithTimeout(context.Background(), 1*time.Second)
defer cancel()
@@ -147,7 +147,7 @@ func TestDeepgramService_Recognize_MultipleFinals(t *testing.T) {
})
defer srv.Close()
svc := NewDeepgramService("test-key", wsToWss(srv.URL)+"/v1/listen", zap.NewNop().Sugar())
svc := NewDeepgramService("test-key", "", wsToWss(srv.URL)+"/v1/listen", zap.NewNop().Sugar())
text, err := svc.Recognize(context.Background(), []byte("audio"), Options{})
if err != nil {
@@ -159,7 +159,7 @@ func TestDeepgramService_Recognize_MultipleFinals(t *testing.T) {
}
func TestDeepgramService_buildURL(t *testing.T) {
svc := NewDeepgramService("key", "wss://api.deepgram.com/v1/listen", zap.NewNop().Sugar())
svc := NewDeepgramService("key", "", "wss://api.deepgram.com/v1/listen", zap.NewNop().Sugar())
tests := []struct {
name string

9
backend/internal/ai/tts/openai.go
View File

@@ -15,6 +15,7 @@ import (
// OpenAIService 基于 OpenAI TTS API 的语音合成实现。
type OpenAIService struct {
apiKey string
model string
voice string
speed float64
endpoint string
@@ -24,7 +25,10 @@ type OpenAIService struct {
}
// NewOpenAIService 创建 OpenAI TTS 服务。
func NewOpenAIService(apiKey, voice, endpoint string, speed float64, timeoutSec int, logger *zap.SugaredLogger) *OpenAIService {
func NewOpenAIService(apiKey, model, voice, endpoint string, speed float64, timeoutSec int, logger *zap.SugaredLogger) *OpenAIService {
if model == "" {
model = "tts-1"
}
if voice == "" {
voice = "alloy"
}
@@ -40,6 +44,7 @@ func NewOpenAIService(apiKey, voice, endpoint string, speed float64, timeoutSec
}
return &OpenAIService{
apiKey: apiKey,
model: model,
voice: voice,
speed: speed,
endpoint: endpoint,
@@ -109,7 +114,7 @@ func (o *OpenAIService) synthesize(ctx context.Context, text, voice string, spee
defer cancel()
body := ttsRequest{
Model: "tts-1",
Model: o.model,
Input: text,
Voice: voice,
ResponseFormat: "mp3",

14
backend/internal/ai/tts/openai_test.go
View File

@@ -58,7 +58,7 @@ func TestOpenAIService_SynthesizeStream_Success(t *testing.T) {
})
defer srv.Close()
svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
svc := NewOpenAIService("test-key", "", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
textStream := sendSentences("你好", "世界", "！")
@@ -110,7 +110,7 @@ func TestOpenAIService_SynthesizeStream_APIError(t *testing.T) {
})
defer srv.Close()
svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
svc := NewOpenAIService("test-key", "", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
textStream := sendSentences("你好")
@@ -142,7 +142,7 @@ func TestOpenAIService_SynthesizeStream_Timeout(t *testing.T) {
defer srv.Close()
// 1 秒超时
svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 1, zap.NewNop().Sugar())
svc := NewOpenAIService("test-key", "", "alloy", srv.URL, 1.0, 1, zap.NewNop().Sugar())
textStream := sendSentences("很长的句子")
@@ -177,7 +177,7 @@ func TestOpenAIService_SynthesizeStream_EmptyText(t *testing.T) {
})
defer srv.Close()
svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
svc := NewOpenAIService("test-key", "", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
// 空句子应该被跳过
textStream := sendSentences("", "你好", "")
@@ -210,7 +210,7 @@ func TestOpenAIService_SynthesizeStream_ContextCancelled(t *testing.T) {
})
defer srv.Close()
svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
svc := NewOpenAIService("test-key", "", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
// 发送多个句子，但在第一个后取消
textStream := make(chan string, 3)
@@ -252,7 +252,7 @@ func TestOpenAIService_SynthesizeStream_PartialFailure(t *testing.T) {
})
defer srv.Close()
svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
svc := NewOpenAIService("test-key", "", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
textStream := sendSentences("第一句", "第二句", "第三句")
@@ -286,7 +286,7 @@ func TestOpenAIService_SynthesizeStream_CustomVoice(t *testing.T) {
})
defer srv.Close()
svc := NewOpenAIService("test-key", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
svc := NewOpenAIService("test-key", "", "alloy", srv.URL, 1.0, 5, zap.NewNop().Sugar())
textStream := sendSentences("你好")

10
backend/internal/config/config.go
View File

@@ -5,6 +5,7 @@ import (
"os"
"strings"
"github.com/joho/godotenv"
"github.com/spf13/viper"
)
@@ -50,6 +51,7 @@ type AIConfig struct {
type STTConfig struct {
Provider string `mapstructure:"provider"`
APIKey string `mapstructure:"api_key"`
Model string `mapstructure:"model"`
Endpoint string `mapstructure:"endpoint"`
}
@@ -64,6 +66,7 @@ type LLMConfig struct {
type TTSConfig struct {
Provider string `mapstructure:"provider"`
APIKey string `mapstructure:"api_key"`
Model string `mapstructure:"model"`
Voice string `mapstructure:"voice"`
Speed float64 `mapstructure:"speed"`
Endpoint string `mapstructure:"endpoint"`
@@ -98,12 +101,14 @@ func Load() (*Config, error) {
v.SetDefault("redis.addr", "localhost:6379")
v.SetDefault("redis.db", 0)
v.SetDefault("ai.stt.provider", "deepgram")
v.SetDefault("ai.stt.model", "nova-2")
v.SetDefault("ai.stt.endpoint", "wss://api.deepgram.com/v1/listen")
v.SetDefault("ai.llm.provider", "openai")
v.SetDefault("ai.llm.model", "gpt-4o")
v.SetDefault("ai.llm.endpoint", "https://api.openai.com/v1")
v.SetDefault("ai.llm.timeout", 10)
v.SetDefault("ai.tts.provider", "openai")
v.SetDefault("ai.tts.model", "tts-1")
v.SetDefault("ai.tts.voice", "alloy")
v.SetDefault("ai.tts.speed", 1.0)
v.SetDefault("ai.tts.endpoint", "https://api.openai.com/v1")
@@ -125,6 +130,11 @@ func Load() (*Config, error) {
_ = v.MergeInConfig()
}
// 加载 .env 文件（不覆盖已有环境变量）
// 按优先级尝试：当前目录、上级目录（兼容从 backend/ 或项目根目录启动）
_ = godotenv.Load()
_ = godotenv.Load("../.env")
// 环境变量覆盖
v.SetEnvPrefix("CAMTALK")
v.SetEnvKeyReplacer(strings.NewReplacer(".", "_"))

5
backend/internal/orchestrator/pipeline.go
View File

@@ -22,6 +22,7 @@ type Pipeline struct {
llmService llm.Service
ttsService tts.Service
sessionMgr session.Manager
model string // LLM 模型名，用于 llm_done 上报
}
// New 创建 Pipeline 实例。
@@ -30,12 +31,14 @@ func New(
llmService llm.Service,
ttsService tts.Service,
sessionMgr session.Manager,
model string,
) *Pipeline {
return &Pipeline{
sttService: sttService,
llmService: llmService,
ttsService: ttsService,
sessionMgr: sessionMgr,
model: model,
}
}
@@ -206,7 +209,7 @@ func (p *Pipeline) ProcessQuery(
Type: "llm_done",
RequestID: req.RequestID,
FullText: fullText,
Model: "gpt-4o",
Model: p.model,
LatencyMs: latency,
}); err != nil {
log.Errorw("发送 llm_done 失败", "error", err)

16
backend/internal/orchestrator/pipeline_test.go
View File

@@ -254,7 +254,7 @@ func TestProcessQuery_Success(t *testing.T) {
mockSender.On("SendTTSAudio", mock.Anything).Return(nil)
// 创建 Pipeline
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession, "gpt-4o")
// 执行
ctx := context.Background()
@@ -305,7 +305,7 @@ func TestProcessQuery_STTError(t *testing.T) {
mockSender.On("SendError", mock.Anything).Return(nil)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession, "gpt-4o")
ctx := context.Background()
err := pipeline.ProcessQuery(ctx, "session-123", req, nil, mockSender)
@@ -357,7 +357,7 @@ func TestProcessQuery_LLMError(t *testing.T) {
mockSender.On("SendError", mock.Anything).Return(nil)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession, "gpt-4o")
ctx := context.Background()
err := pipeline.ProcessQuery(ctx, "session-123", req, nil, mockSender)
@@ -415,7 +415,7 @@ func TestProcessQuery_TTSError(t *testing.T) {
mockTTS.On("SynthesizeStream", mock.Anything, mock.Anything, mock.Anything).
Return(nil, errors.New("TTS service unavailable"))
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession, "gpt-4o")
ctx := context.Background()
err := pipeline.ProcessQuery(ctx, "session-123", req, nil, mockSender)
@@ -485,7 +485,7 @@ func TestProcessQuery_ContextCancelled(t *testing.T) {
}()
mockTTS.On("SynthesizeStream", mock.Anything, mock.Anything, mock.Anything).Return((<-chan tts.Chunk)(ttsCh), nil)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession, "gpt-4o")
// 创建可取消的上下文
ctx, cancel := context.WithCancel(context.Background())
@@ -545,7 +545,7 @@ func TestProcessQuery_DisabledTTS(t *testing.T) {
mockSender.On("SendLLMChunk", mock.Anything).Return(nil)
mockSender.On("SendLLMDone", mock.Anything).Return(nil)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession, "gpt-4o")
ctx := context.Background()
err := pipeline.ProcessQuery(ctx, "session-123", req, nil, mockSender)
@@ -617,7 +617,7 @@ func TestProcessQuery_InvalidAudio(t *testing.T) {
mockSender.On("SendError", mock.Anything).Return(nil)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession, "gpt-4o")
ctx := context.Background()
err := pipeline.ProcessQuery(ctx, "session-123", req, nil, mockSender)
@@ -650,7 +650,7 @@ func TestProcessQuery_SessionNotFound(t *testing.T) {
mockSender.On("SendError", mock.Anything).Return(nil)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession)
pipeline := New(mockSTT, mockLLM, mockTTS, mockSession, "gpt-4o")
ctx := context.Background()
err := pipeline.ProcessQuery(ctx, "session-123", req, nil, mockSender)