ml-commons
ml-commons copied to clipboard
ml-commons provides a set of common machine learning algorithms, e.g. k-means, or linear regression, to help developers build ML related features within OpenSearch.
**Is your feature request related to a problem?** Client applications interacting with various http endpoints through remote models + http connectors need to be made vendor-aware as each LLM vendor,...
Most model service provider provide throttling. For now, we don't have rate limiting in ml-commons. That may trigger throttling if user don't control the rate.
Generally if user has permission of one model, they can get the model information, or operate on this model like deploy/undeploy. For some use case, user may need a hidden...
Support update model and connector. User don't need to undeploy model first before updating as undeploy will cause service interruption. For example user need to rotate their credential in connector,...
**Is your feature request related to a problem?** A clear and concise description of what the problem is, e.g. _I'm always frustrated when [...]_ When registering a ML model, you...
**What is the bug?** It is the same bug as described in the https://github.com/opensearch-project/ml-commons/issues/1666, but with the connector to Azure OpenAI embedding model. I was able to add connector for...
**Is your feature request related to a problem?** There is no solution to upload ML models from Google Cloud buckets (or other cloud providers) to OpenSearch. The only way is...
Add tutorial docs for how to build pre/post process functions for connector.
**What is the bug?** Sending a predict request to a model that uses SageMaker connector like so ``` POST /_plugins/_ml/models/_6gdD40BZqSAbrEiV6DT/_predict { "parameters": { "inputs": "test sentence" } } ``` produces...
### Description Removing unnecessary guava dependencies ### Issues Resolved https://github.com/opensearch-project/ml-commons/issues/1854 ### Check List - [ X] New functionality includes testing. - [X ] All tests pass - [X ] New...