Comments (14)
I will add an example in the repo's doc for those who like to use langchain.js tomorrow.
from milvus-sdk-node.
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.
- get embedding from openAI's api
- insert embedding into milvus
- search with milvus
from milvus-sdk-node.
ok, let me check this later today.
from milvus-sdk-node.
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) },
]
from milvus-sdk-node.
I will add an example in the repo's doc for those who like to use langchain.js tomorrow.
hi, where is the example?
from milvus-sdk-node.
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
from milvus-sdk-node.
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!
from milvus-sdk-node.
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
from milvus-sdk-node.
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?
from milvus-sdk-node.
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'.
from milvus-sdk-node.
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
from milvus-sdk-node.
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.
from milvus-sdk-node.
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
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
from milvus-sdk-node.
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。
- get embedding from openAI's api从OpenAI的API获取嵌入
- insert embedding into milvus将嵌入插入 milvus
- search with milvus 使用米尔维斯搜索
ok
i understand
from milvus-sdk-node.
Related Issues (20)
- useDatabase is not available HOT 1
- getVersion Should be removed from API? HOT 1
- Ignore Growing Segment
- Delete is not working, Delete entities not working HOT 9
- Provide a count function HOT 4
- Can not work on `grpc/grpc-js: 1.8.19` default dependency HOT 3
- `milvusClient.delete()` can not delete entities when the primary key is string.
- Fail to run langchain milvus vector store sample HOT 9
- Lack of error handling on invalid collection names
- output_fields error
- search api only return `score` and `id` HOT 7
- It should handle int64 properly
- support missing AlterCollection
- failed to get channels, collection not loaded HOT 3
- MilvusClient instantiation is not catchable HOT 1
- The dynamicSchema in the example is OK? HOT 2
- Please support search for multiple vectors HOT 2
- [Langchain] - How to set collection vector dimension? HOT 2
- Build a pool of connections <> Check if the connection is dead to revive it. HOT 1
- Error: ENOENT: no such file or directory, open '/admin/.next/server/app/api/proto/proto/schema.proto HOT 13
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from milvus-sdk-node.