feature: Add Jumpstart example notebooks (#3068)

Author: bencrabtree

doc/doc_utils/jumpstart_doc_utils.py

@@ -14,12 +14,73 @@
 from urllib import request
 import json
 from packaging.version import Version
+from enum import Enum
+
+
+class Tasks(str, Enum):
+    """The ML task name as referenced in the infix of the model ID."""
+
+    IC = "ic"
+    OD = "od"
+    OD1 = "od1"
+    SEMSEG = "semseg"
+    IS = "is"
+    TC = "tc"
+    SPC = "spc"
+    EQA = "eqa"
+    TEXT_GENERATION = "textgeneration"
+    IC_EMBEDDING = "icembedding"
+    TC_EMBEDDING = "tcembedding"
+    NER = "ner"
+    SUMMARIZATION = "summarization"
+    TRANSLATION = "translation"
+    TABULAR_REGRESSION = "regression"
+    TABULAR_CLASSIFICATION = "classification"
+
+
+class ProblemTypes(str, Enum):
+    """Possible problem types for JumpStart models."""
+
+    IMAGE_CLASSIFICATION = "Image Classification"
+    IMAGE_EMBEDDING = "Image Embedding"
+    OBJECT_DETECTION = "Object Detection"
+    SEMANTIC_SEGMENTATION = "Semantic Segmentation"
+    INSTANCE_SEGMENTATION = "Instance Segmentation"
+    TEXT_CLASSIFICATION = "Text Classification"
+    TEXT_EMBEDDING = "Text Embedding"
+    QUESTION_ANSWERING = "Question Answering"
+    SENTENCE_PAIR_CLASSIFICATION = "Sentence Pair Classification"
+    TEXT_GENERATION = "Text Generation"
+    TEXT_SUMMARIZATION = "Text Summarization"
+    MACHINE_TRANSLATION = "Machine Translation"
+    NAMED_ENTITY_RECOGNITION = "Named Entity Recognition"
+    TABULAR_REGRESSION = "Regression"
+    TABULAR_CLASSIFICATION = "Classification"
+
 
 JUMPSTART_REGION = "eu-west-2"
 SDK_MANIFEST_FILE = "models_manifest.json"
 JUMPSTART_BUCKET_BASE_URL = "https://jumpstart-cache-prod-{}.s3.{}.amazonaws.com".format(
     JUMPSTART_REGION, JUMPSTART_REGION
 )
+TASK_MAP = {
+    Tasks.IC: ProblemTypes.IMAGE_CLASSIFICATION,
+    Tasks.IC_EMBEDDING: ProblemTypes.IMAGE_EMBEDDING,
+    Tasks.OD: ProblemTypes.OBJECT_DETECTION,
+    Tasks.OD1: ProblemTypes.OBJECT_DETECTION,
+    Tasks.SEMSEG: ProblemTypes.SEMANTIC_SEGMENTATION,
+    Tasks.IS: ProblemTypes.INSTANCE_SEGMENTATION,
+    Tasks.TC: ProblemTypes.TEXT_CLASSIFICATION,
+    Tasks.TC_EMBEDDING: ProblemTypes.TEXT_EMBEDDING,
+    Tasks.EQA: ProblemTypes.QUESTION_ANSWERING,
+    Tasks.SPC: ProblemTypes.SENTENCE_PAIR_CLASSIFICATION,
+    Tasks.TEXT_GENERATION: ProblemTypes.TEXT_GENERATION,
+    Tasks.SUMMARIZATION: ProblemTypes.TEXT_SUMMARIZATION,
+    Tasks.TRANSLATION: ProblemTypes.MACHINE_TRANSLATION,
+    Tasks.NER: ProblemTypes.NAMED_ENTITY_RECOGNITION,
+    Tasks.TABULAR_REGRESSION: ProblemTypes.TABULAR_REGRESSION,
+    Tasks.TABULAR_CLASSIFICATION: ProblemTypes.TABULAR_CLASSIFICATION,
+}
 
 
 def get_jumpstart_sdk_manifest():
@@ -36,6 +97,11 @@ def get_jumpstart_sdk_spec(key):
     return json.loads(model_spec)
 
 
+def get_model_task(id):
+    task_short = id.split("-")[1]
+    return TASK_MAP[task_short] if task_short in TASK_MAP else "Source"
+
+
 def create_jumpstart_model_table():
     sdk_manifest = get_jumpstart_sdk_manifest()
     sdk_manifest_top_versions_for_models = {}
@@ -69,26 +135,29 @@ def create_jumpstart_model_table():
     )
     file_content.append(
         """
-    Each model id is linked to an external page that describes the model.\n
+    Click on the Problem Type to navigate to the source of the model.\n
     """
     )
     file_content.append("\n")
     file_content.append(".. list-table:: Available Models\n")
-    file_content.append("   :widths: 50 20 20 20\n")
+    file_content.append("   :widths: 50 20 20 20 30\n")
     file_content.append("   :header-rows: 1\n")
     file_content.append("   :class: datatable\n")
     file_content.append("\n")
     file_content.append("   * - Model ID\n")
     file_content.append("     - Fine Tunable?\n")
     file_content.append("     - Latest Version\n")
     file_content.append("     - Min SDK Version\n")
+    file_content.append("     - Problem Type/Source\n")
 
     for model in sdk_manifest_top_versions_for_models.values():
         model_spec = get_jumpstart_sdk_spec(model["spec_key"])
-        file_content.append("   * - `{} <{}>`_\n".format(model_spec["model_id"], model_spec["url"]))
+        model_task = get_model_task(model_spec["model_id"])
+        file_content.append("   * - {}\n".format(model_spec["model_id"]))
         file_content.append("     - {}\n".format(model_spec["training_supported"]))
         file_content.append("     - {}\n".format(model["version"]))
         file_content.append("     - {}\n".format(model["min_version"]))
+        file_content.append("     - `{} <{}>`__\n".format(model_task, model_spec["url"]))
 
     f = open("doc_utils/jumpstart.rst", "w")
     f.writelines(file_content)

doc/overview.rst

@@ -573,15 +573,49 @@ Here is an example:
         # When you are done using your endpoint
         model.sagemaker_session.delete_endpoint('my-endpoint')
 
-********************************************
-Use Prebuilt Models with SageMaker JumpStart
-********************************************
+*********************************************************
+Use SageMaker JumpStart Algorithms with Pretrained Models
+*********************************************************
+
+JumpStart for the SageMaker Python SDK uses model ids and model versions to access the necessary
+utilities. This table serves to provide the core material plus some extra information that can be useful
+in selecting the correct model id and corresponding parameters.
 
 .. toctree::
     :maxdepth: 2
 
     doc_utils/jumpstart
 
+Example notebooks
+=================
+
+JumpStart supports 15 different machine learning problem types. Below is a list of all the supported
+problem types with a link to a Jupyter notebook that provides example usage.
+
+Vision
+    - `Image Classification <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_image_classification/Amazon_JumpStart_Image_Classification.ipynb>`__
+    - `Object Detection <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_object_detection/Amazon_JumpStart_Object_Detection.ipynb>`__
+    - `Semantic Segmentation <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_semantic_segmentation/Amazon_JumpStart_Semantic_Segmentation.ipynb>`__
+    - `Instance Segmentation <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_instance_segmentation/Amazon_JumpStart_Instance_Segmentation.ipynb>`__
+    - `Image Embedding <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_image_embedding/Amazon_JumpStart_Image_Embedding.ipynb>`__
+
+Text
+    - `Text Classification <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_text_classification/Amazon_JumpStart_Text_Classification.ipynb>`__
+    - `Sentence Pair Classification <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_sentence_pair_classification/Amazon_JumpStart_Sentence_Pair_Classification.ipynb>`__
+    - `Question Answering <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_question_answering/Amazon_JumpStart_Question_Answering.ipynb>`__
+    - `Named Entity Recognition <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_named_entity_recognition/Amazon_JumpStart_Named_Entity_Recognition.ipynb>`__
+    - `Text Summarization <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_text_summarization/Amazon_JumpStart_Text_Summarization.ipynb>`__
+    - `Text Generation <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_text_generation/Amazon_JumpStart_Text_Generation.ipynb>`__
+    - `Machine Translation <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_machine_translation/Amazon_JumpStart_Machine_Translation.ipynb>`__
+    - `Text Embedding <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_text_embedding/Amazon_JumpStart_Text_Embedding.ipynb>`__
+
+Tabular
+    - `Tabular Classification (LightGBM & Catboost) <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_tabular_classification/Amazon_JumpStart_Tabular_Classification_LightGBM_CatBoost.ipynb>`__
+    - `Tabular Classification (XGBoost & Linear Learner) <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_tabular_classification/Amazon_JumpStart_Tabular_Classification_XGBoost_LinearLearner.ipynb>`__
+    - `Tabular Regression (LightGBM & Catboost) <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_tabular_regression/Amazon_JumpStart_Tabular_Regression_LightGBM_CatBoost.ipynb>`__
+    - `Tabular Regression (XGBoost & Linear Learner) <https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_tabular_regression/Amazon_JumpStart_Tabular_Regression_XGBoost_LinearLearner.ipynb>`__
+
+
 `Amazon SageMaker JumpStart <https://aws.amazon.com/sagemaker/getting-started/>`__ is a
 SageMaker feature that helps users bring machine learning (ML)
 applications to market using prebuilt solutions for common use cases,