ref: adds multi threading to the AI/ML embeddings component #2959
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
dosubot
bot
added
size:L
Pull Request Validation ReportThis comment is automatically generated by Conventional PR Whitelist Report
Result Pull request does not satisfy any enabled whitelist criteria. Pull request will be validated. Validation Report
Result Pull request satisfies all enabled pull request rules. Last Modified at 25 Jul 24 17:55 UTC |
|
This pull request is automatically being deployed by Amplify Hosting (learn more). |
…nting for better code clarit
nicoloboschi
pushed a commit
to datastax/ragstack-ai-langflow
that referenced
this pull request
Jul 30, 2024
…-ai#2959) * Use http client for requests and split texts naively * update models list * prints * multithread requests to aiml embeddings * remove comment * [autofix.ci] apply automated fixes * style(AIMLEmbeddingsImpl.py): improve code formatting and add type hinting for better code clarit --------- Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com> Co-authored-by: Gabriel Luiz Freitas Almeida <[email protected]> (cherry picked from commit 55693c9)
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Outdated suggestions cannot be applied.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.
The Langchain implementations of the embeddings classes obviously offer advanced parallelization / retries / etc. Our naive since request call was significantly slower.
This approach is still slower, but by much less of a factor. In the very few tests I had time to run, I was seeing maybe a 50% increase in time required to embed the
cosmosdocuments into AstraDB using OpenAI vs. AI/ML embedding components with this approach. (Previously, we couldn't even wait long enough for the AI/ML embedding component to embed successfully).The AI/ML Team is going to figure out why the Langchain OpenAI Implementation with base_url is not working.
Testing: