-
Notifications
You must be signed in to change notification settings - Fork 1.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
community[minor]:feat(embedding integration): modifying the Alibaba Tongyi chat model enableSearch parameter is invalid; add Alibaba Tongyi embedding #4662
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
Could you please reply, Does the code not meet the specification? Why can't it be merged? |
request_id: string | ||
} | ||
|
||
export class AlibabaAIEmbeddings extends Embeddings implements AlibabaAIEmbeddingsParams { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
See above, rename to AlibabaTongyiEmbeddingsParams
* The number of dimensions the resulting output embeddings should have. | ||
* Only supported in `text-embedding-3` and later models. | ||
*/ | ||
// dimensions?: number |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Remove unused comments
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I changed it
text_type: fieldsWithDefaults?.parameters?.text_type ?? "document" | ||
} | ||
// this.timeout = fieldsWithDefaults?.timeout | ||
// this.dimensions = fieldsWithDefaults?.dimensions |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Remove commented out code
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I changed it
|
||
/** | ||
* Method to generate embeddings for an array of documents. Splits the | ||
* documents into batches and makes requests to the OpenAI API to generate |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Update OpenAI
in docstring
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I changed it
Hey @JoeABCDEF, sorry for the delay, I have a lot to cover! I don't think I can test this myself but the URL looks right and overall looks good, minus comments. Can you run |
I'm very sorry, a lot of things are not careful, but this function is normal that I have used it myself, and I will carefully change and resubmit the problem that occurs, I am very sorry |
Added docs + entrypoint from |
Okay, I will, where is the documentation added? |
Oh, I added it! It's live: https://js.langchain.com/docs/integrations/text_embedding/alibaba_tongyi It is finished :) |
thank you so much |
by the way ,how can you get the AlibabaTongyiEmbeddings key,when i visit "https://dashvector.console.aliyun.com/cn-hangzhou/overview" and get get key . its invalid |
Fix the issue that the chatModel searchEnable parameter is invalid when only using community alibaba_tongyi;
Embedding with alibaba_tongyi integration