Refactor ML section - local and remote models #5609

kolchfa-aws · 2023-11-16T00:02:29Z

Description

Refactor ML section - local and remote models

Issues Resolved

Fixes #5591
Fixes #4866
Fixes #4966
Fixes #5559

Checklist

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license and subject to the Developers Certificate of Origin.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

ylwu-amzn · 2023-11-17T08:31:40Z

_ml-commons-plugin/api/model-apis/index.md

+ML Commons supports the following model-level APIs:
+
+- [Register model]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api/model-apis/register-model/)
+- [Deploy model]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api/model-apis/deploy-model/)


minor: move this line after Get model?

ylwu-amzn · 2023-11-17T08:37:43Z

_ml-commons-plugin/api/model-apis/index.md

+- [Undeploy model]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api/model-apis/undeploy-model/)
+- [Delete model]({{site.url}}{{site.baseurl}}/ml-commons-plugin/api/model-apis/delete-model/)
+
+## Model access control considerations


This is mainly about model groups, Should we move this to model-group-apis/index.md ?

This is about model groups but from the perspective of accessing a model. This section gives a brief overview of what models can be accessed by what users and then links to the model access control page for further details. So I think I'll leave this here.

ylwu-amzn · 2023-11-17T08:46:26Z

_ml-commons-plugin/api/model-apis/register-model.md

+
+## Request fields
+
+All request fields are required. 


This is not correct.
For different model, they need different fields.

For pretrained model, check https://opensearch.org/docs/latest/ml-commons-plugin/pretrained-models/, the mandatory fields are name, version, model_format

For uploading model via URL, refer to https://github.com/opensearch-project/ml-commons/blob/2.x/docs/model_serving_framework/text_embedding_model_examples.md, mandatory fields:

name

version

function_name

model_format

model_content_hash_value

model_config: {model_type, embedding_dimension, framework_type},

url

For remote model , refer to https://github.com/opensearch-project/ml-commons/blob/2.x/docs/tutorials/remote_inference.md

ylwu-amzn · 2023-11-17T08:50:13Z

_ml-commons-plugin/api/model-apis/register-model.md

+}
+```
+
+## Registering a model containing an internal connector


Refer to https://github.com/opensearch-project/ml-commons/blob/2.x/docs/tutorials/remote_inference.md

For Register remote model, user can use internal connector or connector id (standalone connector)

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

vagimeli

@kolchfa-aws Solid documentation. Edits are minimal. I agree with capitalizing the API sections because they serve as headings.

vagimeli · 2023-11-17T19:40:18Z

_ml-commons-plugin/api/model-apis/register-model.md

+}
+```
+{% include copy-curl.html %}
+


Delete extra blank line

_ml-commons-plugin/api/model-apis/register-model.md

_ml-commons-plugin/cluster-settings.md

vagimeli · 2023-11-17T20:08:46Z

_ml-commons-plugin/custom-local-models.md

+  "last_update_time": 1689793851101,
+  "is_async": true
+}
+```


Do we need a blank line between lines 208 and 209?

vagimeli · 2023-11-17T20:16:15Z

_ml-commons-plugin/api/model-apis/register-model.md

+| `model_type` | String | The model type, such as `bert`. For a Hugging Face model, the model type is specified in `config.json`. For an example, see the [`all-MiniLM-L6-v2` Hugging Face model `config.json`](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/blob/main/config.json#L15). Required. |
+| `embedding_dimension` | Integer | The dimension of the model-generated dense vector. For a Hugging Face model, the dimension is specified in the model card. For example, in the [`all-MiniLM-L6-v2` Hugging Face model card](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2), the statement `384 dimensional dense vector space` specifies 384 as the embedding dimension. Required. |
+| `framework_type` | String  | The framework the model is using. Currently, we support `sentence_transformers` and `huggingface_transformers` frameworks. The `sentence_transformers` model outputs text embeddings directly, so ML Commons does not perform any post processing. For `huggingface_transformers`, ML Commons performs post processing by applying mean pooling to get text embeddings. See the example [`all-MiniLM-L6-v2` Hugging Face model](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) for more details. Required. |
+| `all_config` | String | This field is used for reference purposes. You can specify all model configurations in this field. For example, if you are using a Hugging Face model, you can minify the `config.json` file to one line and save its contents in the `all_config` field. Once the model is uploaded, you can use the get model API operation to get all model configurations stored in this field. Optional. |


Should this read "Get Model API?"

vagimeli · 2023-11-17T20:18:20Z

_ml-commons-plugin/api/profile.md

+
+# Profile
+
+The profile API operation returns runtime information about ML tasks and models. The profile operation can help debug model issues at runtime. 


Should this read "Profile API operation?"

vagimeli · 2023-11-17T20:21:02Z

_ml-commons-plugin/api/train-predict/train.md

+
+# Train 
+
+The train API operation trains a model based on a selected algorithm. Training can occur both synchronously and asynchronously.


Should this read "Train API operation?"

_ml-commons-plugin/api/model-apis/register-model.md

_ml-commons-plugin/custom-local-models.md

Co-authored-by: Melissa Vagi <vagimeli@amazon.com> Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

* Refactor ML section - local and remote models Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Added command to calculate checksum Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Add ONNX format to register API Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Add sparse encoding predict example Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Add API section Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Refactor the API section Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Typo Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Implemented Vale comments Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Add get connector API Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Reword heading Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Addressed tech review comments Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Apply suggestions from code review Co-authored-by: Melissa Vagi <vagimeli@amazon.com> Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com> --------- Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com> Co-authored-by: Melissa Vagi <vagimeli@amazon.com> (cherry picked from commit 826e677) Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* Refactor ML section - local and remote models * Added command to calculate checksum * Add ONNX format to register API * Add sparse encoding predict example * Add API section * Refactor the API section * Typo * Implemented Vale comments * Add get connector API * Reword heading * Addressed tech review comments * Apply suggestions from code review --------- (cherry picked from commit 826e677) Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com> Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Melissa Vagi <vagimeli@amazon.com>

* Refactor ML section - local and remote models Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Added command to calculate checksum Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Add ONNX format to register API Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Add sparse encoding predict example Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Add API section Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Refactor the API section Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Typo Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Implemented Vale comments Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Add get connector API Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Reword heading Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Addressed tech review comments Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> * Apply suggestions from code review Co-authored-by: Melissa Vagi <vagimeli@amazon.com> Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com> --------- Signed-off-by: Fanit Kolchina <kolchfa@amazon.com> Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com> Co-authored-by: Melissa Vagi <vagimeli@amazon.com>

Refactor ML section - local and remote models

d0e4383

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

kolchfa-aws requested review from hdhalter, Naarcha-AWS, vagimeli, ananzh, seanneumann, AMoo-Miki and natebower as code owners November 16, 2023 00:02

kolchfa-aws self-assigned this Nov 16, 2023

kolchfa-aws added 10 commits November 15, 2023 21:24

Added command to calculate checksum

657070c

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

Merge branch 'main' into ml-example

812f0ce

Add ONNX format to register API

ff2aba4

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

Add sparse encoding predict example

809c8b6

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

Add API section

bf3038e

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

Refactor the API section

f4f4333

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

Typo

4c98fe4

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

Implemented Vale comments

109733e

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

Add get connector API

c991145

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

Reword heading

2f511f3

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

ylwu-amzn reviewed Nov 17, 2023

View reviewed changes

Addressed tech review comments

c6c7894

Signed-off-by: Fanit Kolchina <kolchfa@amazon.com>

vagimeli approved these changes Nov 17, 2023

View reviewed changes

kolchfa-aws commented Nov 17, 2023

View reviewed changes

_ml-commons-plugin/api/model-apis/register-model.md Show resolved Hide resolved

kolchfa-aws commented Nov 17, 2023

View reviewed changes

_ml-commons-plugin/custom-local-models.md Show resolved Hide resolved

kolchfa-aws and others added 2 commits November 17, 2023 15:54

Apply suggestions from code review

da9274f

Co-authored-by: Melissa Vagi <vagimeli@amazon.com> Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

Merge branch 'main' into ml-example

d5f8006

Signed-off-by: kolchfa-aws <105444904+kolchfa-aws@users.noreply.github.com>

kolchfa-aws merged commit 826e677 into main Nov 17, 2023
4 checks passed

kolchfa-aws added the backport 2.11 PR: Backport label for 2.11 label Nov 17, 2023

opensearch-trigger-bot bot mentioned this pull request Nov 17, 2023

[Backport 2.11] Refactor ML section - local and remote models #5630

Merged

Naarcha-AWS deleted the ml-example branch March 28, 2024 23:23

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Refactor ML section - local and remote models #5609

Refactor ML section - local and remote models #5609

kolchfa-aws commented Nov 16, 2023 •

edited

Loading

ylwu-amzn Nov 17, 2023

ylwu-amzn Nov 17, 2023

kolchfa-aws Nov 17, 2023

ylwu-amzn Nov 17, 2023 •

edited

Loading

ylwu-amzn Nov 17, 2023

ylwu-amzn Nov 17, 2023

vagimeli left a comment

vagimeli Nov 17, 2023

vagimeli Nov 17, 2023

vagimeli Nov 17, 2023

vagimeli Nov 17, 2023

vagimeli Nov 17, 2023


		# Profile

		The profile API operation returns runtime information about ML tasks and models. The profile operation can help debug model issues at runtime.


		# Train

		The train API operation trains a model based on a selected algorithm. Training can occur both synchronously and asynchronously.

Refactor ML section - local and remote models #5609

Refactor ML section - local and remote models #5609

Conversation

kolchfa-aws commented Nov 16, 2023 • edited Loading

Description

Issues Resolved

Checklist

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

ylwu-amzn Nov 17, 2023 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

vagimeli left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

kolchfa-aws commented Nov 16, 2023 •

edited

Loading

ylwu-amzn Nov 17, 2023 •

edited

Loading