Gradient.ai - updating the SDK #110
Merged
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
|
|
mhaligowski
reviewed
Dec 15, 2023
integrations/gradient/src/gradient_haystack/embedders/gradient_document_embedder.py
Show resolved
Hide resolved
mhaligowski
reviewed
Dec 15, 2023
|
LGTM, let's make sure that the tests are ran and we're gtg! |
mhaligowski
reviewed
Dec 15, 2023
integrations/gradient/src/gradient_haystack/embedders/gradient_document_embedder.py
Outdated
Show resolved
Hide resolved
michaelfeil
requested review from
silvanocerza
and removed request for
a team
|
All tests passing on my end. |
|
Thanks folks! FYI, in #103 we removed all the |
|
@masci Alright. |
michaelfeil
commented
Dec 15, 2023
integrations/gradient/src/gradient_haystack/embedders/gradient_document_embedder.py
Outdated
Show resolved
Hide resolved
integrations/gradient/src/gradient_haystack/embedders/gradient_document_embedder.py
Show resolved
Hide resolved
|
Awesome, thanks guys! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Our SDK
gradientai >= 1.4.0supports nowasyncAPI and threaded batching in our API - the embedding model now exposes.embed=> This PR aims to improve speed of embeddings over large numbers of documents.Dependencies:
gradientaifrom1.3.0to1.4.0. The SDK always had a minium python version of 3.8, except for some initial experiments (e.g.1.0.0.dev1). Therefore, I raised the miniumum version to1.4.0tqdmas optional. It should be pre-installed, and we are using no advanced options other thanfrom tqdm import tqdm, no version pin required. I think this will improve developer experience, especially since the embeddings are now faster on the server side.@mhaligowski Can you give this a check before I mark as ready?