ml-commons
ml-commons copied to clipboard
opensearch-project
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.
1. Download a trained model (from the cluster , that was trained with the train api) and upload to another cluster. 2. Download custom model and upload to another cluster.
Summary ML Commons primarily relies on [MLException](https://github.com/opensearch-project/ml-commons/blob/main/common/src/main/java/org/opensearch/ml/common/exception/MLException.java) and its derived classes: [ExecuteException](https://github.com/opensearch-project/ml-commons/blob/main/common/src/main/java/org/opensearch/ml/common/exception/ExecuteException.java) [MLLimitExceededException](https://github.com/opensearch-project/ml-commons/blob/main/common/src/main/java/org/opensearch/ml/common/exception/MLLimitExceededException.java) [MLResourceNotFoundException](https://github.com/opensearch-project/ml-commons/blob/main/common/src/main/java/org/opensearch/ml/common/exception/MLResourceNotFoundException.java) [MLValidationException](https://github.com/opensearch-project/ml-commons/blob/main/common/src/main/java/org/opensearch/ml/common/exception/MLValidationException.java) These exceptions define log severity ([reference](https://github.com/opensearch-project/ml-commons/blob/main/common/src/main/java/org/opensearch/ml/common/exception/MLValidationException.java)) and contribute to stats updates in the following places:...
We can add helper checks via API (or at the least ML commons UI) to scan ingest pipelines, search pipelines, any other places where the models may be used in...
**Is your feature request related to a problem?** Currently when a [connector blueprint](https://github.com/opensearch-project/ml-commons/tree/main/docs/remote_inference_blueprints) is added to the ml-commons repo, the [list of supported connectors](https://opensearch.org/docs/latest/ml-commons-plugin/remote-models/connectors/#supported-connectors) in the documentation website is not...
**Is your feature request related to a problem?** Currently, there is no easy way to determine if a model was un-deployed at a particular point in time or not. For...
Add how to configure ML inference processor for ingest and search pipeline to Cohere embedding multilingual blueprint.
**What is the bug?** Text Chunking processor in ingest pipeline while connecting to external embedding model like nvidia/nv-embedqa-mistral-7b-v2 is not sending the data to external model in correctly. It sends...
From https://github.com/opensearch-project/ml-commons/issues/2986, user found they can create connector with invalid input like a wrong `pre_process_function`. We should add more validation.
**Is your feature request related to a problem?** Currently, we are configuring it to include authentication information when creating a custom ML connector. ```json POST /_plugins/_ml/connectors/_create { "name": "Custom Connector:...
**Is your feature request related to a problem?** - [x] template query --targeting 2.19 - [x] ml inference search request extension --targeting 2.19 ~~load image from url function in Connector...
Metadata
Owner
Metadata
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.