Add sample code to measure latency on TextEmbeddingModel
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- Half a day
- Newbie friendliness
- 35/100
- Issue type
- Feature
- Clarity
- Mostly clear
- Activity status
- Stale
- Tech stack
- python
- Domain
- machine-learning
Research direction
No file or test is named. Start by locating existing TextEmbeddingModel samples in the repository and follow their entry points and conventions. Done means a new sample sends the given text N times, measures each request, and reports the 50th, 95th, and 99th percentile latencies.
Written by the indexing model from the issue text.
Description
Thanks for stopping by to let us know something could be better!
PLEASE READ: If you have a support contract with Google, please create an issue in the support console instead of filing on GitHub. This will ensure a timely response.
The issue you're having must be related to a file in this repository. We are unable to provide assistance for issues unrelated to samples in this repository.
Please include as much information as possible:
Is your feature request related to a problem? Please describe.
Customer is looking for an authoritative way to properly measure the latency on a given model of TextEmbeddingModel
Describe the solution you'd like.
I would like to contribute by adding a new file with a code to send a given text N times, measure the time on each request and grouping them in percentiles 50, 95 and 99.
Describe alternatives you've considered.
I have not thought on any other alternative.
Additional context.
This is useful for those early adapters who want to make sure and confirm that this is indeed a reliable solution for the enterprise.
Making sure to follow these steps will guarantee the quickest resolution possible.
Thanks!
- Dominant language
- Jupyter Notebook
- Stars
- 8.1k
- Forks
- 6.7k
- Avg merge
- 4d 4h
- Merged PRs (30d)
- 8
Getting set up
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from GoogleCloudPlatform/python-docs-samples
-
samples
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
GoogleCloudPlatform/python-docs-samples#14609 ·
Maintainers usually reply within 1 day
-
samples
Difficulty 1/5 Under an hour Newbie friendliness 92/100
GoogleCloudPlatform/python-docs-samples#14610 ·
Maintainers usually reply within 1 day
-
samples
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
GoogleCloudPlatform/python-docs-samples#14611 ·
Maintainers usually reply within 1 day
-
chore(generative_ai) Update model references for generative_ai samplesMay be free again @XrossFox claimed this 152 days ago, and no pull request is open. Opensamples
GoogleCloudPlatform/python-docs-samples#14117 · 1 assignee ·
Maintainers usually reply within 1 day
-
Fix Pipeline dependency issues for geospatial-classification/serving_appMay be free again @XrossFox claimed this 164 days ago, and no pull request is open. Opensamples
GoogleCloudPlatform/python-docs-samples#14091 · 1 assignee ·
Maintainers usually reply within 1 day
All issues in GoogleCloudPlatform/python-docs-samples
Similar issues
-
Bug in GaussianTailProbabilityCalibrator: running_statistics=False still uses a windowed varianceOpenbug good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
selimfirat/pysad#107 ·
Maintainers usually reply within 1 day
-
bug ci-failure high priority
Difficulty 1/5 Under an hour Newbie friendliness 88/100
vllm-project/vllm-omni#8194 · 1 comment ·
Maintainers usually reply within 1 day
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
sktime/sktime#11310 · 1 comment ·
Maintainers usually reply within 1 day
-
[Bug] Models with tied embeddings, such as LFM2, fail to load when built with is_symmetric=falseOpen
Difficulty 2/5 1-3 hours Newbie friendliness 90/100
microsoft/onnxruntime-genai#2632 ·
Maintainers usually reply within 1 day
-
automation missing-model model-sync provider:fireworks-ai
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
anomalyco/models.dev#8146 ·
Maintainers usually reply within 1 day