兼容性仅在 Node.js 上可用。
设置
- 在您的计算机上使用 Docker 运行 Milvus 实例 文档
-
安装 Milvus Node.js SDK。
npm复制向 AI 提问
npm install -S @zilliz/milvus2-sdk-node -
在运行代码之前设置 Milvus 的环境变量 3.1 OpenAI3.2 Azure OpenAI复制向 AI 提问
export OPENAI_API_KEY=YOUR_OPENAI_API_KEY_HERE export MILVUS_URL=YOUR_MILVUS_URL_HERE # for example https://:19530复制向 AI 提问export AZURE_OPENAI_API_KEY=YOUR_AZURE_OPENAI_API_KEY_HERE export AZURE_OPENAI_API_INSTANCE_NAME=YOUR_AZURE_OPENAI_INSTANCE_NAME_HERE export AZURE_OPENAI_API_DEPLOYMENT_NAME=YOUR_AZURE_OPENAI_DEPLOYMENT_NAME_HERE export AZURE_OPENAI_API_COMPLETIONS_DEPLOYMENT_NAME=YOUR_AZURE_OPENAI_COMPLETIONS_DEPLOYMENT_NAME_HERE export AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME=YOUR_AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME_HERE export AZURE_OPENAI_API_VERSION=YOUR_AZURE_OPENAI_API_VERSION_HERE export AZURE_OPENAI_BASE_PATH=YOUR_AZURE_OPENAI_BASE_PATH_HERE export MILVUS_URL=YOUR_MILVUS_URL_HERE # for example https://:19530
索引和查询文档
有关安装 LangChain 软件包的一般说明,请参阅此部分。
npm
复制
向 AI 提问
npm install @langchain/openai @langchain/core
复制
向 AI 提问
import { Milvus } from "@langchain/classic/vectorstores/milvus";
import { OpenAIEmbeddings } from "@langchain/openai";
// text sample from Godel, Escher, Bach
const vectorStore = await Milvus.fromTexts(
[
"Tortoise: Labyrinth? Labyrinth? Could it Are we in the notorious Little\
Harmonic Labyrinth of the dreaded Majotaur?",
"Achilles: Yiikes! What is that?",
"Tortoise: They say-although I person never believed it myself-that an I\
Majotaur has created a tiny labyrinth sits in a pit in the middle of\
it, waiting innocent victims to get lost in its fears complexity.\
Then, when they wander and dazed into the center, he laughs and\
laughs at them-so hard, that he laughs them to death!",
"Achilles: Oh, no!",
"Tortoise: But it's only a myth. Courage, Achilles.",
],
[{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }],
new OpenAIEmbeddings(),
{
collectionName: "goldel_escher_bach",
}
);
// or alternatively from docs
const vectorStore = await Milvus.fromDocuments(docs, new OpenAIEmbeddings(), {
collectionName: "goldel_escher_bach",
});
const response = await vectorStore.similaritySearch("scared", 2);
从现有集合中查询文档
复制
向 AI 提问
import { Milvus } from "@langchain/classic/vectorstores/milvus";
import { OpenAIEmbeddings } from "@langchain/openai";
const vectorStore = await Milvus.fromExistingCollection(
new OpenAIEmbeddings(),
{
collectionName: "goldel_escher_bach",
}
);
const response = await vectorStore.similaritySearch("scared", 2);
相关
以编程方式连接这些文档到 Claude、VSCode 等,通过 MCP 获取实时答案。