feat(openai): include raw data in embedQuery method #6924
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
1 Skipped Deployment
|
dosubot
bot
added
size:M
|
Hi @CarlosSLoureiro , thanks for this very nice addition! I was looking through the whole langchain-js github to see how openai embeddings were handled because like you I need to get the usages when I do embeddings:
I'd like to know the total cost of tokens to track my users' consumption in my saas. Is it possible for you to add what you've done to the embedDocuments method? 🙏 |
|
Hi @XStarlink , that's a great suggestion, thanks. When I have some free time I'll make this adjustment and open another PR. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I would like to contribute with this small feature because it is a need I have and perhaps others may have as well.
We have the option to obtain the full response data from OpenAI in completion methods such as
withStructuredOutput, for example, but we don't have it in this embedding generation method. I need to obtain the data on the number of tokens sent without necessarily having another library estimate this data for me.Here’s an example:
Additionally, this adjustment will not cause any changes to the existing interface unless we explicitly the
includeRawin the options param.