-
Notifications
You must be signed in to change notification settings - Fork 25.8k
[Inference API] Add VoyageAI inference service integration #142562
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
Open
fzowl
wants to merge
15
commits into
elastic:main
Choose a base branch
from
voyage-ai:voyageai-embedding-task
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
15 commits
Select commit
Hold shift + click to select a range
8a9f3ca
Voyage integration:
fzowl 8eaf33e
Voyage integration:
fzowl c17f82d
Voyage integration:
fzowl eef38e4
Merge branch 'main' into voyageai-embedding-task
fzowl ed05daa
Merge branch 'main' into voyageai-embedding-task
fzowl c3600b8
Merge remote-tracking branch 'upstream/main' into voyageai-embedding-…
fzowl 13eb526
Merge remote-tracking branch 'origin/voyageai-embedding-task' into vo…
fzowl 18ea08d
Merge branch 'main' into voyageai-embedding-task
fzowl 0ccfb9a
Voyage integration:
fzowl a4603e4
Voyage integration:
fzowl 9d6da89
Voyage integration:
fzowl 884d7db
Merge branch 'voyageai-embedding-task' of https://github.com/voyage-a…
fzowl 99c3611
Address PR review feedback: fix bugs, add BWC support, and comprehens…
fzowl 09f5b5f
Merge branch 'main' into voyageai-embedding-task
fzowl 06db692
Rename VoyageAIEmbeddingsServiceSettings to VoyageAITextEmbeddingServ…
fzowl File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| pr: 142562 | ||
| summary: "[Inference API] Add VoyageAI inference service integration" | ||
| area: Inference | ||
| type: enhancement | ||
| issues: [] |
1 change: 1 addition & 0 deletions
1
.../main/resources/transport/definitions/referable/voyage_ai_multimodal_embeddings_added.csv
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1 @@ | ||
| 9318000 |
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1 +1 @@ | ||
| esql_async_source_bytes_buffered,9317000 | ||
| voyage_ai_multimodal_embeddings_added,9318000 |
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
Oops, something went wrong.
Oops, something went wrong.
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.
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.
Where are these values coming from? In the documentation for the embeddings API and the multimodal embeddings API, the maximum number of inputs is given as 1000. 7 seems extremely small.
Uh oh!
There was an error while loading. Please reload this page.
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.
@DonalEvans These values are based on the safe and conservative calculation. We have a token limit for the request (batch) and per document, so to be on the safe side with batching, the total number of documents can be calculated as total_number_of_tokens_per_batch/maximum_number_of_tokens_per_document.
The ideal solution would be to build token-aware batching (which is technically possible), but it requires the tokeniser to be downloaded from HuggingFace. If you are fine with this, i'd be more than happy to build it, that'd be a more elegant solution.