Error: Insert fail: some field does not exist for this collection in line. 0 about milvus-sdk-node

[shanghaikid]

I will add an example in the repo's doc for those who like to use langchain.js tomorrow.

[shanghaikid]

why?
there are my parameter
export const address =
'https://in01-c664772af99277c.aws-us-west-2.vectordb.zillizcloud.com:19532';
export const username = 'ttc'; // optional username
export const password = 'Ttc.zilliz'; // optional password
export const ssl = true; // secure or not

I know. I just reviewed the langchain code, zilliz cloud doesn't support the index type used in langchain.

I will contribute a zilliz vector store in langchain.js.

Anyway, langchain is just a chain tool, you can archive your target without it and in a more controllable way.

1. get embedding from openAI's api
2. insert embedding into milvus
3. search with milvus

[shanghaikid]

ok, let me check this later today.

[shanghaikid]

Hi, if you are using langchain, you shouldn't create the collection via https://github.com/zilliztech/cloud-vectordb-examples/blob/master/node/HelloZillizCloud.js

Because in the helloZillizCloud, it defines the schema and create a collection in advanced.
But langchain.js does this for you. all you need is a milvus cluster address, langchain's fromDocuments function will insert embeddings into that predefined collection for you.

And the schema defined in helloZillizCloud is different from langchain's.

This data format is for zilliz Cloud example, not for langchain.

[
{ id: 2, word_count: 24, book_intro: Math.floor(Math.random() * 1000) },
{ id: 1, word_count: 4, book_intro: Math.floor(Math.random() * 1000) },
{ id: 3, word_count: 6, book_intro: Math.floor(Math.random() * 1000) },
{ id: 4, word_count: 2, book_intro: Math.floor(Math.random() * 1000) },
{ id: 5, word_count: 9, book_intro: Math.floor(Math.random() * 1000) },
]

[DeeWooo]

I will add an example in the repo's doc for those who like to use langchain.js tomorrow.

hi, where is the example?

[shanghaikid]

I will add an example in the repo's doc for those who like to use langchain.js tomorrow.

hi, where is the example?

https://github.com/milvus-io/milvus-sdk-node/tree/main/example/LangChain

[DeeWooo]

I will add an example in the repo's doc for those who like to use langchain.js tomorrow.

hi, where is the example?

https://github.com/milvus-io/milvus-sdk-node/tree/main/example/LangChain

thank you！

[DeeWooo]

I will add an example in the repo's doc for those who like to use langchain.js tomorrow.

hi, where is the example?

https://github.com/milvus-io/milvus-sdk-node/tree/main/example/LangChain

I used the example above and got the following error. I am using Zilliz Cloud.

Error: ErrorCode: UnexpectedError. Reason: index doesn't exist, collectionID 441713954587545704

[DeeWooo]

I found that there were no successfully built indexes on the Zilliz console, and after manually creating them, the problem was solved. ‘Metric Type’ needs to be manually selected. I chose ‘L2’.
Why is that?

[shanghaikid]

I found that there were no successfully built indexes on the Zilliz console, and after manually creating them, the problem was solved. ‘Metric Type’ needs to be manually selected. I chose ‘L2’. Why is that?

Maybe you can try a new collection to see if it is working. not the old name 'books'.

[DeeWooo]

I found that there were no successfully built indexes on the Zilliz console, and after manually creating them, the problem was solved. ‘Metric Type’ needs to be manually selected. I chose ‘L2’. Why is that?

Maybe you can try a new collection to see if it is working. not the old name 'books'.
yes,this is a new collection. you can try to use zilliz cloud

[shanghaikid]

I found that there were no successfully built indexes on the Zilliz console, and after manually creating them, the problem was solved. ‘Metric Type’ needs to be manually selected. I chose ‘L2’. Why is that?

Maybe you can try a new collection to see if it is working. not the old name 'books'.
yes,this is a new collection. you can try to use zilliz cloud

I tested it's working. it's weird.

[DeeWooo]

I found that there were no successfully built indexes on the Zilliz console, and after manually creating them, the problem was solved. ‘Metric Type’ needs to be manually selected. I chose ‘L2’. Why is that?

Maybe you can try a new collection to see if it is working. not the old name 'books'.
yes,this is a new collection. you can try to use zilliz cloud

I tested it's working. it's weird.

why?
there are my parameter
export const address =
'https://in01-c664772af99277c.aws-us-west-2.vectordb.zillizcloud.com:19532';
export const username = 'ttc'; // optional username
export const password = 'Ttc.zilliz'; // optional password
export const ssl = true; // secure or not

[DeeWooo]

why? 为什么？
there are my parameter有我的参数
export const address =导出常量地址 =
'https://in01-c664772af99277c.aws-us-west-2.vectordb.zillizcloud.com:19532';“https://in01-c664772af99277c.aws-us-west-2.vectordb.zillizcloud.com:19532”;
export const username = 'ttc'; // optional username导出常量用户名 = 'TTC';可选用户名
export const password = 'Ttc.zilliz'; // optional password导出常量密码 = 'Ttc.zilliz';可选密码
export const ssl = true; // secure or not导出常量 SSL = 真;安全与否

I know. I just reviewed the langchain code, zilliz cloud doesn't support the index type used in langchain.我知道。我刚刚查看了语言链代码，zilliz 云不支持语言链中使用的索引类型。

I will contribute a zilliz vector store in langchain.js.我将在 langchain.js 中贡献一个 zilliz 向量存储。

Anyway, langchain is just a chain tool, you can archive your target without it and in a more controllable way.无论如何，langchain 只是一个链工具，您可以在没有它的情况下以更可控的方式存档目标。

1. get embedding from openAI's api从OpenAI的API获取嵌入
2. insert embedding into milvus将嵌入插入 milvus
3. search with milvus 使用米尔维斯搜索

ok
i understand