使用 LangChain 构建语音代理

import { AssemblyAISTT } from "./assemblyai";
import type { VoiceAgentEvent } from "./types";

async function* sttStream(
  audioStream: AsyncIterable<Uint8Array>
): AsyncGenerator<VoiceAgentEvent> {
  const stt = new AssemblyAISTT({ sampleRate: 16000 });
  const passthrough = writableIterator<VoiceAgentEvent>();

  // Producer: pump audio chunks to AssemblyAI
  const producer = (async () => {
    try {
      for await (const audioChunk of audioStream) {
        await stt.sendAudio(audioChunk);
      }
    } finally {
      await stt.close();
    }
  })();

  // Consumer: receive transcription events
  const consumer = (async () => {
    for await (const event of stt.receiveEvents()) {
      passthrough.push(event);
    }
  })();

  try {
    // Yield events as they arrive
    yield* passthrough;
  } finally {
    // Wait for producer and consumer to complete
    await Promise.all([producer, consumer]);
  }
}

import { createAgent } from "langchain";
import { HumanMessage } from "@langchain/core/messages";
import { MemorySaver } from "@langchain/langgraph";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

// Define agent tools
const addToOrder = tool(
  async ({ item, quantity }) => {
    return `Added ${quantity} x ${item} to the order.`;
  },
  {
    name: "add_to_order",
    description: "Add an item to the customer's sandwich order.",
    schema: z.object({
      item: z.string(),
      quantity: z.number(),
    }),
  }
);

const confirmOrder = tool(
  async ({ orderSummary }) => {
    return `Order confirmed: ${orderSummary}. Sending to kitchen.`;
  },
  {
    name: "confirm_order",
    description: "Confirm the final order with the customer.",
    schema: z.object({
      orderSummary: z.string().describe("Summary of the order"),
    }),
  }
);

// Create agent with tools and memory
const agent = createAgent({
  model: "claude-haiku-4-5",
  tools: [addToOrder, confirmOrder],
  checkpointer: new MemorySaver(),
  systemPrompt: `You are a helpful sandwich shop assistant.
Your goal is to take the user's order. Be concise and friendly.
Do NOT use emojis, special characters, or markdown.
Your responses will be read by a text-to-speech engine.`,
});

async function* agentStream(
  eventStream: AsyncIterable<VoiceAgentEvent>
): AsyncGenerator<VoiceAgentEvent> {
  // Generate unique thread ID for conversation memory
  const threadId = crypto.randomUUID();

  for await (const event of eventStream) {
    // Pass through all upstream events
    yield event;

    // Process final transcripts through the agent
    if (event.type === "stt_output") {
      const stream = await agent.stream(
        { messages: [new HumanMessage(event.transcript)] },
        {
          configurable: { thread_id: threadId },
          streamMode: "messages",
        }
      );

      // Yield agent response chunks as they arrive
      for await (const [message] of stream) {
        yield { type: "agent_chunk", text: message.text, ts: Date.now() };
      }
    }
  }
}

import { CartesiaTTS } from "./cartesia";

async function* ttsStream(
  eventStream: AsyncIterable<VoiceAgentEvent>
): AsyncGenerator<VoiceAgentEvent> {
  const tts = new CartesiaTTS();
  const passthrough = writableIterator<VoiceAgentEvent>();

  // Producer: read upstream events and send text to Cartesia
  const producer = (async () => {
    try {
      for await (const event of eventStream) {
        passthrough.push(event);
        if (event.type === "agent_chunk") {
          await tts.sendText(event.text);
        }
      }
    } finally {
      await tts.close();
    }
  })();

  // Consumer: receive audio from Cartesia
  const consumer = (async () => {
    for await (const event of tts.receiveEvents()) {
      passthrough.push(event);
    }
  })();

  try {
    // Yield events from both producer and consumer
    yield* passthrough;
  } finally {
    await Promise.all([producer, consumer]);
  }
}

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="..."

// using https://hono.dev/
app.get("/ws", upgradeWebSocket(async () => {
  const inputStream = writableIterator<Uint8Array>();

  // Chain the three stages
  const transcriptEventStream = sttStream(inputStream);
  const agentEventStream = agentStream(transcriptEventStream);
  const outputEventStream = ttsStream(agentEventStream);

  // Process pipeline and send TTS audio to client
  const flushPromise = (async () => {
    for await (const event of outputEventStream) {
      if (event.type === "tts_chunk") {
        currentSocket?.send(event.audio);
      }
    }
  })();

  return {
    onMessage(event) {
      // Push incoming audio into pipeline
      const data = event.data;
      if (Buffer.isBuffer(data)) {
        inputStream.push(new Uint8Array(data));
      }
    },
    async onClose() {
      inputStream.cancel();
      await flushPromise;
    },
  };
}));