fix: cache SentenceTransformer model at startup instead of per-request#190
Open
adarshkumar23 wants to merge 1 commit intokubeflow:mainfrom
Open
fix: cache SentenceTransformer model at startup instead of per-request#190adarshkumar23 wants to merge 1 commit intokubeflow:mainfrom
adarshkumar23 wants to merge 1 commit intokubeflow:mainfrom
Conversation
The embedding model (~400MB) was being re-initialized inside milvus_search() on every call. For agentic RAG workflows with multiple tool calls per user turn, this added seconds of latency per query. Move model initialization to module level so it loads once at server startup and is reused across all requests. Signed-off-by: Adarsh Kumar <adarsh23072005@gmail.com> Signed-off-by: adarshkumar23 <131923092+adarshkumar23@users.noreply.github.com>
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Cache the SentenceTransformer embedding model at module level instead of re-initializing it on every search request.
Fixes #XX (replace with your issue number)
Problem
milvus_search()in bothserver/app.pyandserver-https/app.pycallsSentenceTransformer(EMBEDDING_MODEL)on every invocation. Loadingall-mpnet-base-v2takes ~2-5 seconds and ~400MB. In agentic workflows with 3-5 tool calls per turn, this adds 10-25 seconds of unnecessary latency.Changes
server/app.py— move model init to module levelserver-https/app.py— move model init to module levelPerformance Impact