Compare commits
3 Commits
563ca12790
...
312e762aff
| Author | SHA1 | Date | |
|---|---|---|---|
| 312e762aff | |||
| 41cacaa740 | |||
| 51ed6aa563 |
@@ -61,7 +61,7 @@ type chatMessage struct {
|
||||
|
||||
type contentPart struct {
|
||||
Type string `json:"type"`
|
||||
Text string `json:"text,omitempty"`
|
||||
Text string `json:"text"`
|
||||
ImageURL *imageURL `json:"image_url,omitempty"`
|
||||
}
|
||||
|
||||
@@ -100,6 +100,9 @@ func (o *OpenAIService) ChatStream(ctx context.Context, req Request) (<-chan Chu
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("llm: marshal request: %w", err)
|
||||
}
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("llm: marshal request: %w", err)
|
||||
}
|
||||
|
||||
// 创建带超时的 context
|
||||
ctx, cancel := context.WithTimeout(ctx, o.timeout)
|
||||
|
||||
@@ -55,6 +55,7 @@ type WsQuery struct {
|
||||
RequestID string `json:"request_id"`
|
||||
Image string `json:"image"` // base64
|
||||
Audio string `json:"audio"` // base64
|
||||
Text string `json:"text"` // 用户手动输入的文本(有值时跳过 STT)
|
||||
MimeType string `json:"mime_type"` // 默认 "audio/pcm"
|
||||
}
|
||||
|
||||
|
||||
@@ -62,22 +62,27 @@ func (p *Pipeline) ProcessQuery(
|
||||
log := logger.Log
|
||||
startTime := time.Now()
|
||||
|
||||
// 解码音频数据
|
||||
audio, err := base64.StdEncoding.DecodeString(req.Audio)
|
||||
if err != nil {
|
||||
log.Errorw("音频解码失败", "error", err)
|
||||
sender.SendError(models.WsError{
|
||||
Type: "error",
|
||||
RequestID: req.RequestID,
|
||||
Code: "INVALID_MESSAGE",
|
||||
Message: "音频数据解码失败",
|
||||
})
|
||||
return err
|
||||
// 解码音频数据(文本输入模式可跳过)
|
||||
var audio []byte
|
||||
if req.Text == "" && req.Audio != "" {
|
||||
var err error
|
||||
audio, err = base64.StdEncoding.DecodeString(req.Audio)
|
||||
if err != nil {
|
||||
log.Errorw("音频解码失败", "error", err)
|
||||
sender.SendError(models.WsError{
|
||||
Type: "error",
|
||||
RequestID: req.RequestID,
|
||||
Code: "INVALID_MESSAGE",
|
||||
Message: "音频数据解码失败",
|
||||
})
|
||||
return err
|
||||
}
|
||||
}
|
||||
|
||||
// 解码图片数据(可选)
|
||||
var image []byte
|
||||
if req.Image != "" {
|
||||
var err error
|
||||
image, err = base64.StdEncoding.DecodeString(req.Image)
|
||||
if err != nil {
|
||||
log.Errorw("图片解码失败", "error", err)
|
||||
@@ -110,45 +115,64 @@ func (p *Pipeline) ProcessQuery(
|
||||
return err
|
||||
}
|
||||
|
||||
// Step 1: STT 语音识别
|
||||
log.Infow("开始语音识别", "request_id", req.RequestID)
|
||||
sttResult, err := p.sttService.Recognize(ctx, audio, stt.Options{
|
||||
Encoding: "pcm_s16le",
|
||||
SampleRate: 16000,
|
||||
Language: sess.Config.Language,
|
||||
})
|
||||
if err != nil {
|
||||
log.Errorw("语音识别失败", "error", err)
|
||||
sender.SendError(models.WsError{
|
||||
Type: "error",
|
||||
RequestID: req.RequestID,
|
||||
Code: "STT_ERROR",
|
||||
Message: "语音识别失败",
|
||||
})
|
||||
return err
|
||||
}
|
||||
// Step 1: 获取用户文本(语音识别或直接使用输入文本)
|
||||
var userText string
|
||||
if req.Text != "" {
|
||||
// 文本输入模式:跳过 STT,直接使用用户输入的文本
|
||||
log.Infow("使用文本输入", "request_id", req.RequestID, "text", req.Text)
|
||||
userText = req.Text
|
||||
|
||||
// 发送 STT 结果
|
||||
if err := sender.SendSTTResult(models.WsSTTResult{
|
||||
Type: "stt_result",
|
||||
RequestID: req.RequestID,
|
||||
Text: sttResult,
|
||||
IsFinal: true,
|
||||
}); err != nil {
|
||||
log.Errorw("发送 STT 结果失败", "error", err)
|
||||
// 发送 stt_result 以保持前端消息流一致性
|
||||
if err := sender.SendSTTResult(models.WsSTTResult{
|
||||
Type: "stt_result",
|
||||
RequestID: req.RequestID,
|
||||
Text: userText,
|
||||
IsFinal: true,
|
||||
}); err != nil {
|
||||
log.Errorw("发送 STT 结果失败", "error", err)
|
||||
}
|
||||
} else {
|
||||
// 语音模式:执行 STT 语音识别
|
||||
log.Infow("开始语音识别", "request_id", req.RequestID)
|
||||
sttResult, err := p.sttService.Recognize(ctx, audio, stt.Options{
|
||||
Encoding: "pcm_s16le",
|
||||
SampleRate: 16000,
|
||||
Language: sess.Config.Language,
|
||||
})
|
||||
if err != nil {
|
||||
log.Errorw("语音识别失败", "error", err)
|
||||
sender.SendError(models.WsError{
|
||||
Type: "error",
|
||||
RequestID: req.RequestID,
|
||||
Code: "STT_ERROR",
|
||||
Message: "语音识别失败",
|
||||
})
|
||||
return err
|
||||
}
|
||||
userText = sttResult
|
||||
|
||||
// 发送 STT 结果
|
||||
if err := sender.SendSTTResult(models.WsSTTResult{
|
||||
Type: "stt_result",
|
||||
RequestID: req.RequestID,
|
||||
Text: userText,
|
||||
IsFinal: true,
|
||||
}); err != nil {
|
||||
log.Errorw("发送 STT 结果失败", "error", err)
|
||||
}
|
||||
}
|
||||
|
||||
// 追加用户消息到历史
|
||||
p.sessionMgr.AppendMessage(ctx, sessionID, models.Message{
|
||||
Role: "user",
|
||||
Content: sttResult,
|
||||
Content: userText,
|
||||
})
|
||||
|
||||
// Step 2+3: LLM 流式推理 + TTS 并行合成
|
||||
log.Infow("开始 LLM 推理", "request_id", req.RequestID)
|
||||
llmReq := llm.Request{
|
||||
Image: image,
|
||||
Text: sttResult,
|
||||
Text: userText,
|
||||
History: history,
|
||||
Language: sess.Config.Language,
|
||||
}
|
||||
|
||||
@@ -41,19 +41,22 @@ interface WsMessage {
|
||||
|
||||
#### `query` — 发起一次视觉对话
|
||||
|
||||
用户说完话后,客户端同时发送当前图像帧和语音片段:
|
||||
用户说完话后,客户端同时发送当前图像帧和语音片段。也支持文本输入模式(手动输入文字时跳过语音识别):
|
||||
|
||||
```typescript
|
||||
interface QueryMessage {
|
||||
type: "query";
|
||||
request_id: string; // 客户端生成的 UUID
|
||||
image: string; // Base64 编码的 JPEG 图像(不含 data: 前缀)
|
||||
audio: string; // Base64 编码的音频片段(PCM 16kHz)
|
||||
audio: string; // Base64 编码的音频片段(PCM 16kHz),文本输入时为空字符串
|
||||
text?: string; // 用户手动输入的文本(有值时跳过 STT,直接使用此文本)
|
||||
mime_type?: string; // 音频格式,默认 "audio/pcm"
|
||||
}
|
||||
```
|
||||
|
||||
> 为什么图像和音频放在同一条消息里?因为 VAD 检测到用户说完话时,需要同时捕获"此刻的画面"和"说的话",拆成两条消息会增加时序同步的复杂度。
|
||||
>
|
||||
> **文本输入模式**:当用户关闭麦克风后,可通过对话框手动输入文字。此时 `text` 字段携带用户输入,`audio` 为空字符串,服务端跳过 STT 直接使用 `text` 进行 LLM 推理。
|
||||
|
||||
#### `config` — 更新会话配置
|
||||
|
||||
@@ -211,13 +214,13 @@ interface PongMessage {
|
||||
|
||||
### 消息流时序
|
||||
|
||||
一次完整交互:
|
||||
**语音模式**(麦克风开启):
|
||||
|
||||
```
|
||||
Client Server
|
||||
| |
|
||||
|-- query {image, audio} ------>|
|
||||
|<-- stt_result {text} ---------|
|
||||
|<-- stt_result {text} ---------| (语音识别)
|
||||
| |
|
||||
|<-- llm_chunk {delta: "这"} ---| (LLM 流式输出)
|
||||
|<-- llm_chunk {delta: "是一"} -|
|
||||
@@ -228,6 +231,22 @@ Client Server
|
||||
|<-- tts_audio {is_last: true} -|
|
||||
```
|
||||
|
||||
**文本输入模式**(麦克风关闭,手动输入文字):
|
||||
|
||||
```
|
||||
Client Server
|
||||
| |
|
||||
|-- query {image, text} ------->| (跳过 STT)
|
||||
|<-- stt_result {text} ---------| (回显用户文本)
|
||||
| |
|
||||
|<-- llm_chunk {delta: "好的"} -| (LLM 流式输出)
|
||||
|<-- llm_chunk {delta: ",我"} -|
|
||||
|<-- llm_done {full_text} ------|
|
||||
| |
|
||||
|<-- tts_audio {audio} ---------| (TTS 音频流)
|
||||
|<-- tts_audio {is_last: true} -|
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 二、REST API
|
||||
@@ -891,6 +910,7 @@ type QueryRequest struct {
|
||||
RequestID string `json:"request_id"`
|
||||
Image []byte `json:"-"` // Base64 解码后
|
||||
Audio []byte `json:"-"` // Base64 解码后
|
||||
Text string `json:"text"` // 用户手动输入的文本(有值时跳过 STT)
|
||||
MimeType string `json:"mime_type"`
|
||||
}
|
||||
|
||||
|
||||
@@ -473,6 +473,13 @@ body {
|
||||
/* ---- Chat Panel (覆盖子组件样式) ---- */
|
||||
|
||||
.chat-panel {
|
||||
flex: 1;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
min-height: 0;
|
||||
}
|
||||
|
||||
.chat-panel__messages {
|
||||
flex: 1;
|
||||
overflow-y: auto;
|
||||
padding: 16px 24px;
|
||||
@@ -560,6 +567,56 @@ body {
|
||||
letter-spacing: 0.01em;
|
||||
}
|
||||
|
||||
/* ---- Chat Input ---- */
|
||||
|
||||
.chat-input {
|
||||
display: flex;
|
||||
gap: 8px;
|
||||
padding: 12px 24px 16px;
|
||||
border-top: 1px solid var(--color-border);
|
||||
background: var(--color-surface);
|
||||
}
|
||||
|
||||
.chat-input__field {
|
||||
flex: 1;
|
||||
padding: 10px 14px;
|
||||
border: 1px solid var(--color-border);
|
||||
border-radius: var(--radius-sm);
|
||||
background: var(--color-surface-2);
|
||||
color: var(--color-text);
|
||||
font-size: 0.82rem;
|
||||
outline: none;
|
||||
transition: border-color var(--transition-fast);
|
||||
}
|
||||
|
||||
.chat-input__field::placeholder {
|
||||
color: var(--color-text-muted);
|
||||
}
|
||||
|
||||
.chat-input__field:focus {
|
||||
border-color: var(--color-primary);
|
||||
}
|
||||
|
||||
.chat-input__send {
|
||||
padding: 10px 16px;
|
||||
border: none;
|
||||
border-radius: var(--radius-sm);
|
||||
background: var(--color-primary);
|
||||
color: white;
|
||||
font-size: 0.9rem;
|
||||
cursor: pointer;
|
||||
transition: opacity var(--transition-fast);
|
||||
}
|
||||
|
||||
.chat-input__send:hover:not(:disabled) {
|
||||
opacity: 0.9;
|
||||
}
|
||||
|
||||
.chat-input__send:disabled {
|
||||
opacity: 0.4;
|
||||
cursor: not-allowed;
|
||||
}
|
||||
|
||||
/* ---- Streaming Cursor ---- */
|
||||
|
||||
.cursor {
|
||||
|
||||
@@ -58,6 +58,7 @@ function App() {
|
||||
isMicOn,
|
||||
toggleCamera,
|
||||
toggleMic,
|
||||
sendTextMessage,
|
||||
} = useVisionSession();
|
||||
|
||||
const isConnected = connectionStatus === "connected";
|
||||
@@ -233,6 +234,7 @@ function App() {
|
||||
messages={messages}
|
||||
currentReply={currentReply}
|
||||
connectionStatus={connectionStatus}
|
||||
onSendText={sendTextMessage}
|
||||
/>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
// ============================================================
|
||||
// ChatPanel — 消息展示面板
|
||||
// 职责:渲染对话消息列表、流式光标、元数据、自动滚动
|
||||
// 职责:渲染对话消息列表、流式光标、元数据、自动滚动、文本输入
|
||||
// ============================================================
|
||||
|
||||
import { useEffect, useRef } from "react";
|
||||
import { useEffect, useRef, useState } from "react";
|
||||
import type { ChatMessage } from "../../types";
|
||||
import type { ConnectionStatus } from "../../lib/websocket";
|
||||
|
||||
@@ -11,12 +11,16 @@ interface ChatPanelProps {
|
||||
messages: ChatMessage[];
|
||||
currentReply?: string;
|
||||
connectionStatus: ConnectionStatus;
|
||||
onSendText?: (text: string) => void;
|
||||
}
|
||||
|
||||
export function ChatPanel({ messages, currentReply, connectionStatus }: ChatPanelProps) {
|
||||
export function ChatPanel({ messages, currentReply, connectionStatus, onSendText }: ChatPanelProps) {
|
||||
const bottomRef = useRef<HTMLDivElement>(null);
|
||||
const containerRef = useRef<HTMLDivElement>(null);
|
||||
const isAutoScroll = useRef(true);
|
||||
const [inputText, setInputText] = useState("");
|
||||
|
||||
const isConnected = connectionStatus === "connected";
|
||||
|
||||
// 用户上滚时暂停自动滚动,滚到底部时恢复
|
||||
useEffect(() => {
|
||||
@@ -39,9 +43,17 @@ export function ChatPanel({ messages, currentReply, connectionStatus }: ChatPane
|
||||
}
|
||||
}, [messages, currentReply]);
|
||||
|
||||
// 提交文本消息
|
||||
const handleSubmit = (e: React.FormEvent) => {
|
||||
e.preventDefault();
|
||||
if (!inputText.trim() || !onSendText) return;
|
||||
onSendText(inputText);
|
||||
setInputText("");
|
||||
};
|
||||
|
||||
// 空状态
|
||||
if (messages.length === 0 && !currentReply) {
|
||||
if (connectionStatus !== "connected") {
|
||||
if (!isConnected) {
|
||||
return (
|
||||
<div className="chat-panel chat-panel--empty">
|
||||
<span className="chat-panel--empty-icon">💬</span>
|
||||
@@ -60,35 +72,58 @@ export function ChatPanel({ messages, currentReply, connectionStatus }: ChatPane
|
||||
}
|
||||
|
||||
return (
|
||||
<div className="chat-panel" ref={containerRef}>
|
||||
{messages.map((msg, index) => (
|
||||
<div key={index} className={`chat-message chat-message--${msg.role}`}>
|
||||
<div className="chat-message__role">
|
||||
{msg.role === "user" ? "你" : "AI"}
|
||||
</div>
|
||||
<div className="chat-message__content">{msg.content}</div>
|
||||
{msg.role === "assistant" && msg.tokensUsed !== undefined && (
|
||||
<div className="chat-message__meta">
|
||||
{msg.tokensUsed} tokens
|
||||
{msg.latencyMs !== undefined && ` · ${(msg.latencyMs / 1000).toFixed(1)}s`}
|
||||
{msg.model && ` · ${msg.model}`}
|
||||
<div className="chat-panel">
|
||||
<div className="chat-panel__messages" ref={containerRef}>
|
||||
{messages.map((msg, index) => (
|
||||
<div key={index} className={`chat-message chat-message--${msg.role}`}>
|
||||
<div className="chat-message__role">
|
||||
{msg.role === "user" ? "你" : "AI"}
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
))}
|
||||
|
||||
{/* 流式回复(尚未完成) */}
|
||||
{currentReply && (
|
||||
<div className="chat-message chat-message--assistant chat-message--streaming">
|
||||
<div className="chat-message__role">AI</div>
|
||||
<div className="chat-message__content">
|
||||
{currentReply}
|
||||
<span className="cursor">▌</span>
|
||||
<div className="chat-message__content">{msg.content}</div>
|
||||
{msg.role === "assistant" && msg.tokensUsed !== undefined && (
|
||||
<div className="chat-message__meta">
|
||||
{msg.tokensUsed} tokens
|
||||
{msg.latencyMs !== undefined && ` · ${(msg.latencyMs / 1000).toFixed(1)}s`}
|
||||
{msg.model && ` · ${msg.model}`}
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
))}
|
||||
|
||||
<div ref={bottomRef} />
|
||||
{/* 流式回复(尚未完成) */}
|
||||
{currentReply && (
|
||||
<div className="chat-message chat-message--assistant chat-message--streaming">
|
||||
<div className="chat-message__role">AI</div>
|
||||
<div className="chat-message__content">
|
||||
{currentReply}
|
||||
<span className="cursor">▌</span>
|
||||
</div>
|
||||
</div>
|
||||
)}
|
||||
|
||||
<div ref={bottomRef} />
|
||||
</div>
|
||||
|
||||
{/* 文本输入框 */}
|
||||
{isConnected && onSendText && (
|
||||
<form className="chat-input" onSubmit={handleSubmit}>
|
||||
<input
|
||||
type="text"
|
||||
className="chat-input__field"
|
||||
placeholder="输入文字对话..."
|
||||
value={inputText}
|
||||
onChange={(e) => setInputText(e.target.value)}
|
||||
/>
|
||||
<button
|
||||
type="submit"
|
||||
className="chat-input__send"
|
||||
disabled={!inputText.trim()}
|
||||
title="发送"
|
||||
>
|
||||
➤
|
||||
</button>
|
||||
</form>
|
||||
)}
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
@@ -336,13 +336,17 @@ export function useVisionSession() {
|
||||
/** 麦克风开关 */
|
||||
const toggleMic = useCallback(async () => {
|
||||
if (isMicOn) {
|
||||
await stopVAD();
|
||||
stopMic();
|
||||
setIsMicOn(false);
|
||||
} else {
|
||||
const micStream = await startMic();
|
||||
setIsMicOn(!!micStream);
|
||||
if (micStream) {
|
||||
await startVAD(micStream);
|
||||
setIsMicOn(true);
|
||||
}
|
||||
}
|
||||
}, [isMicOn, startMic, stopMic]);
|
||||
}, [isMicOn, startMic, stopMic, startVAD, stopVAD]);
|
||||
|
||||
/** 打断当前回复 */
|
||||
const interrupt = useCallback(() => {
|
||||
@@ -363,6 +367,44 @@ export function useVisionSession() {
|
||||
setIsProcessing(false);
|
||||
}, [send, currentReply]);
|
||||
|
||||
/** 发送文本消息(手动输入) */
|
||||
const sendTextMessage = useCallback(
|
||||
(text: string) => {
|
||||
if (!text.trim() || isProcessingRef.current) return;
|
||||
|
||||
// 停止上一轮的 TTS 播放
|
||||
ttsPlayerRef.current?.stop();
|
||||
setIsAudioPlaying(false);
|
||||
|
||||
// 捕获当前摄像头画面
|
||||
const frame = captureFrame();
|
||||
|
||||
const requestId = uuidv4();
|
||||
send({
|
||||
type: "query",
|
||||
request_id: requestId,
|
||||
image: frame ? dataUrlToBase64(frame) : "",
|
||||
audio: "", // 文本输入无音频
|
||||
text: text.trim(),
|
||||
});
|
||||
|
||||
// 更新请求统计
|
||||
setStats((prev) => ({ ...prev, queryCount: prev.queryCount + 1 }));
|
||||
|
||||
// 添加用户消息
|
||||
setMessages((prev) => [
|
||||
...prev,
|
||||
{ role: "user", content: text.trim(), timestamp: Date.now() },
|
||||
]);
|
||||
|
||||
// 记录到对话历史
|
||||
historyRef.current.push({ role: "user", content: text.trim() });
|
||||
|
||||
setIsProcessing(true);
|
||||
},
|
||||
[captureFrame, send],
|
||||
);
|
||||
|
||||
return {
|
||||
messages,
|
||||
currentReply,
|
||||
@@ -387,5 +429,6 @@ export function useVisionSession() {
|
||||
isMicOn,
|
||||
toggleCamera,
|
||||
toggleMic,
|
||||
sendTextMessage,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -46,7 +46,8 @@ export interface QueryMessage {
|
||||
type: "query";
|
||||
request_id: string;
|
||||
image: string; // Base64 JPEG(不含 data: 前缀)
|
||||
audio: string; // Base64 PCM 16kHz
|
||||
audio: string; // Base64 PCM 16kHz(文本输入时为空字符串)
|
||||
text?: string; // 用户手动输入的文本(有值时跳过 STT)
|
||||
mime_type?: string; // 默认 "audio/pcm"
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user