import { QdrantClient } from "@qdrant/js-client-rest";
import OpenAI from "openai";
const openai = new OpenAI({
apiKey: process.env.ANTHROPIC_API_KEY, // 复用 DashScope 密钥
baseURL: process.env.EMBEDDING_BASE_URL,
});
const qdrant = new QdrantClient({ host: "localhost", port: 6333 });
const COLLECTION = "knowledge_base";
const EMBEDDING_MODEL = process.env.EMBEDDING_MODEL ?? "text-embedding-v3";
const VECTOR_SIZE = 1024; // 必须与模型输出维度一致
const BATCH_SIZE = 50;
async function ensureCollection() {
const { collections } = await qdrant.getCollections();
if (!collections.some((c) => c.name === COLLECTION)) {
await qdrant.createCollection(COLLECTION, {
vectors: { size: VECTOR_SIZE, distance: "Cosine" },
});
}
}
async function ingestChunks(chunks: Array<{ text: string; metadata: { source: string; section?: string; chunkIndex: number } }>) {
for (let i = 0; i < chunks.length; i += BATCH_SIZE) {
const batch = chunks.slice(i, i + BATCH_SIZE);
const response = await openai.embeddings.create({
model: EMBEDDING_MODEL,
input: batch.map((c) => c.text), // 批量请求,降低 RPM 压力
});
const points = batch.map((chunk, j) => ({
id: i + j,
vector: response.data[j].embedding,
payload: {
text: chunk.text,
source: chunk.metadata.source,
section: chunk.metadata.section ?? "",
chunkIndex: chunk.metadata.chunkIndex,
},
}));
await qdrant.upsert(COLLECTION, { points });
}
}
async function search(query: string, limit = 5, scoreThreshold = 0.65, sourceFilter?: string) {
const res = await openai.embeddings.create({ model: EMBEDDING_MODEL, input: query });
const queryVector = res.data[0].embedding;
const results = await qdrant.search(COLLECTION, {
vector: queryVector,
limit,
score_threshold: scoreThreshold, // 低于此分数直接过滤
with_payload: true,
...(sourceFilter ? { filter: { must: [{ key: "source", match: { value: sourceFilter } }] } } : {}),
});
if (results.length === 0) {
return "没有找到相关内容,无法回答这个问题。"; // 宁可拒答,不用噪音误导 LLM
}
return results;
}