Merge pull request #622 from IBM/v0.2.1

Pull request source branch to cut release 0.2.1- All test have passed.
IBM · Sep 25, 2024 · 3236911 · 3236911
2 parents 877acab + 446b45a
commit 3236911
Show file tree

Hide file tree

Showing 90 changed files with 242 additions and 212 deletions.
diff --git a/.make.versions b/.make.versions
@@ -19,7 +19,7 @@ DPK_MINOR_VERSION=2
 DPK_MICRO_VERSION=1
 # The suffix is generally always set in the main/development branch and only nulled out when creating release branches.
 # It can be manually incremented, for example, to allow publishing a new intermediate version wheel to pypi. 
-DPK_VERSION_SUFFIX=.dev3
+DPK_VERSION_SUFFIX=
 
 DPK_VERSION=$(DPK_MAJOR_VERSION).$(DPK_MINOR_VERSION).$(DPK_MICRO_VERSION)$(DPK_VERSION_SUFFIX)
 

diff --git a/data-processing-lib/python/pyproject.toml b/data-processing-lib/python/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "data_prep_toolkit"
-version = "0.2.1.dev3"
+version = "0.2.1"
 requires-python = ">=3.10"
 keywords = ["data", "data preprocessing", "data preparation", "llm", "generative", "ai", "fine-tuning", "llmapps" ]
 description = "Data Preparation Toolkit Library"
@@ -41,7 +41,7 @@ dev = [
 ]
 
 [options]
-package_dir = ["src","test"]
+package_dir = ["src"]
 
 [options.packages.find]
 where = ["src/data_processing"]

diff --git a/data-processing-lib/ray/pyproject.toml b/data-processing-lib/ray/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "data_prep_toolkit_ray"
-version = "0.2.1.dev3"
+version = "0.2.1"
 keywords = ["data", "data preprocessing", "data preparation", "llm", "generative", "ai", "fine-tuning", "llmapps" ]
 requires-python = ">=3.10"
 description = "Data Preparation Toolkit Library for Ray"
@@ -11,7 +11,7 @@ authors = [
     { name = "Boris Lublinsky", email = "blublinsky@ibm.com" },
 ]
 dependencies = [
-    "data-prep-toolkit>=0.2.1.dev3",
+    "data-prep-toolkit>=0.2.1",
     "ray[default]==2.24.0",
     # These two are to fix security issues identified by quay.io
     "fastapi>=0.110.2",
@@ -42,7 +42,7 @@ dev = [
 ]
 
 [options]
-package_dir = ["src","test"]
+package_dir = ["src"]
 
 [options.packages.find]
 where = ["src/data_processing_ray"]

diff --git a/data-processing-lib/spark/Makefile b/data-processing-lib/spark/Makefile
@@ -4,7 +4,6 @@ include $(REPOROOT)/.make.defaults
 SPARK_VERSION=3.5.2
 DOCKER_IMAGE_NAME=data-prep-kit-spark-$(SPARK_VERSION)
 DOCKER_IMAGE_LIB_NAME=data-prep-kit-spark
-DOCKER_IMAGE_VERSION := latest
 
 
 .check-env::

diff --git a/data-processing-lib/spark/pyproject.toml b/data-processing-lib/spark/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "data_prep_toolkit_spark"
-version = "0.2.1.dev3"
+version = "0.2.1"
 keywords = ["data", "data preprocessing", "data preparation", "llm", "generative", "ai", "fine-tuning", "llmapps" ]
 requires-python = ">=3.10"
 description = "Data Preparation Toolkit Library for Spark"
@@ -11,7 +11,7 @@ authors = [
     { name = "Boris Lublinsky", email = "blublinsk@ibm.com" },
 ]
 dependencies = [
-    "data-prep-toolkit==0.2.1.dev3",	
+    "data-prep-toolkit==0.2.1",	
     "pyspark>=3.5.2",
     "psutil>=6.0.0"
 ]

diff --git a/kfp/kfp_ray_components/createRayClusterComponent.yaml b/kfp/kfp_ray_components/createRayClusterComponent.yaml
@@ -11,7 +11,7 @@ inputs:
 
 implementation:
     container:
-        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:latest"
+        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:0.2.1"
         # command is a list of strings (command-line arguments).
         # The YAML language has two syntaxes for lists and you can use either of them.
         # Here we use the "flow syntax" - comma-separated strings inside square brackets.

diff --git a/kfp/kfp_ray_components/deleteRayClusterComponent.yaml b/kfp/kfp_ray_components/deleteRayClusterComponent.yaml
@@ -9,7 +9,7 @@ inputs:
 
 implementation:
     container:
-        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:latest"
+        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:0.2.1"
         # command is a list of strings (command-line arguments).
         # The YAML language has two syntaxes for lists and you can use either of them.
         # Here we use the "flow syntax" - comma-separated strings inside square brackets.

diff --git a/kfp/kfp_ray_components/executeRayJobComponent.yaml b/kfp/kfp_ray_components/executeRayJobComponent.yaml
@@ -12,7 +12,7 @@ inputs:
 
 implementation:
     container:
-        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:latest"
+        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:0.2.1"
         # command is a list of strings (command-line arguments).
         # The YAML language has two syntaxes for lists and you can use either of them.
         # Here we use the "flow syntax" - comma-separated strings inside square brackets.

diff --git a/kfp/kfp_ray_components/executeRayJobComponent_multi_s3.yaml b/kfp/kfp_ray_components/executeRayJobComponent_multi_s3.yaml
@@ -13,7 +13,7 @@ inputs:
 
 implementation:
     container:
-        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:latest"
+        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:0.2.1"
         # command is a list of strings (command-line arguments).
         # The YAML language has two syntaxes for lists and you can use either of them.
         # Here we use the "flow syntax" - comma-separated strings inside square brackets.

diff --git a/kfp/kfp_ray_components/executeSubWorkflowComponent.yaml b/kfp/kfp_ray_components/executeSubWorkflowComponent.yaml
@@ -27,7 +27,7 @@ outputs:
 
 implementation:
     container:
-        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:latest"
+        image: "quay.io/dataprep1/data-prep-kit/kfp-data-processing:0.2.1"
         # command is a list of strings (command-line arguments).
         # The YAML language has two syntaxes for lists, and you can use either of them.
         # Here we use the "flow syntax" - comma-separated strings inside square brackets.

diff --git a/kfp/kfp_support_lib/kfp_v1_workflow_support/pyproject.toml b/kfp/kfp_support_lib/kfp_v1_workflow_support/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "data_prep_toolkit_kfp_v1"
-version = "0.2.1.dev3"
+version = "0.2.1"
 requires-python = ">=3.10,<3.12"
 description = "Data Preparation Kit Library. KFP support"
 license = {text = "Apache-2.0"}
@@ -13,7 +13,7 @@ authors = [
 ]
 dependencies = [
     "kfp==1.8.22",
-    "data-prep-toolkit-kfp-shared==0.2.1.dev3",
+    "data-prep-toolkit-kfp-shared==0.2.1",
 ]
 
 [build-system]

diff --git a/kfp/kfp_support_lib/kfp_v2_workflow_support/pyproject.toml b/kfp/kfp_support_lib/kfp_v2_workflow_support/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "data_prep_toolkit_kfp_v2"
-version = "0.2.1.dev3"
+version = "0.2.1"
 requires-python = ">=3.10,<3.12"
 description = "Data Preparation Kit Library. KFP support"
 license = {text = "Apache-2.0"}
@@ -14,7 +14,7 @@ authors = [
 dependencies = [
     "kfp==2.8.0",
     "kfp-kubernetes==1.2.0",
-    "data-prep-toolkit-kfp-shared==0.2.1.dev3",
+    "data-prep-toolkit-kfp-shared==0.2.1",
 ]
 
 [build-system]

diff --git a/kfp/kfp_support_lib/shared_workflow_support/pyproject.toml b/kfp/kfp_support_lib/shared_workflow_support/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "data_prep_toolkit_kfp_shared"
-version = "0.2.1.dev3"
+version = "0.2.1"
 requires-python = ">=3.10,<3.12"
 description = "Data Preparation Kit Library. KFP support"
 license = {text = "Apache-2.0"}
@@ -14,7 +14,7 @@ authors = [
 dependencies = [
     "requests",
     "kubernetes",
-    "data-prep-toolkit-ray==0.2.1.dev3",
+    "data-prep-toolkit-ray==0.2.1",
 ]
 
 [build-system]

diff --git a/kfp/superworkflows/ray/kfp_v1/superworkflow_code_sample_wf.py b/kfp/superworkflows/ray/kfp_v1/superworkflow_code_sample_wf.py
@@ -17,14 +17,14 @@
 run_fuzzy_dedup_op = comp.load_component_from_file(component_spec_path + "executeSubWorkflowComponent.yaml")
 run_tokenization_op = comp.load_component_from_file(component_spec_path + "executeSubWorkflowComponent.yaml")
 
-code_to_parquet_image = "quay.io/dataprep1/data-prep-kit/code2parquet-ray:latest"
-proglang_select_image = "quay.io/dataprep1/data-prep-kit/proglang_select-ray:latest"
-code_quality_image = "quay.io/dataprep1/data-prep-kit/code_quality-ray:latest"
-malware_image = "quay.io/dataprep1/data-prep-kit/malware-ray:latest"
-doc_id_image = "quay.io/dataprep1/data-prep-kit/doc_id-ray:latest"
-ededup_image = "quay.io/dataprep1/data-prep-kit/ededup-ray:latest"
-fdedup_image = "quay.io/dataprep1/data-prep-kit/fdedup-ray:latest"
-tokenizer_image = "quay.io/dataprep1/data-prep-kit/tokenization-ray:latest"
+code_to_parquet_image = "quay.io/dataprep1/data-prep-kit/code2parquet-ray:0.2.1"
+proglang_select_image = "quay.io/dataprep1/data-prep-kit/proglang_select-ray:0.2.1"
+code_quality_image = "quay.io/dataprep1/data-prep-kit/code_quality-ray:0.2.1"
+malware_image = "quay.io/dataprep1/data-prep-kit/malware-ray:0.2.1"
+doc_id_image = "quay.io/dataprep1/data-prep-kit/doc_id-ray:0.2.1"
+ededup_image = "quay.io/dataprep1/data-prep-kit/ededup-ray:0.2.1"
+fdedup_image = "quay.io/dataprep1/data-prep-kit/fdedup-ray:0.2.1"
+tokenizer_image = "quay.io/dataprep1/data-prep-kit/tokenization-ray:0.2.1"
 
 
 # Pipeline to invoke execution on remote resource

diff --git a/kfp/superworkflows/ray/kfp_v1/superworkflow_dedups_sample_wf.py b/kfp/superworkflows/ray/kfp_v1/superworkflow_dedups_sample_wf.py
@@ -12,9 +12,9 @@
 run_exact_dedup_op = comp.load_component_from_file(component_spec_path + "executeSubWorkflowComponent.yaml")
 run_fuzzy_dedup_op = comp.load_component_from_file(component_spec_path + "executeSubWorkflowComponent.yaml")
 
-doc_id_image = "quay.io/dataprep1/data-prep-kit/doc_id-ray:latest"
-ededup_image = "quay.io/dataprep1/data-prep-kit/ededup-ray:latest"
-fdedup_image = "quay.io/dataprep1/data-prep-kit/fdedup-ray:latest"
+doc_id_image = "quay.io/dataprep1/data-prep-kit/doc_id-ray:0.2.1"
+ededup_image = "quay.io/dataprep1/data-prep-kit/ededup-ray:0.2.1"
+fdedup_image = "quay.io/dataprep1/data-prep-kit/fdedup-ray:0.2.1"
 
 # Pipeline to invoke execution on remote resource
 @dsl.pipeline(

diff --git a/release-notes.md b/release-notes.md
@@ -1,5 +1,36 @@
 # Data Prep Kit Release notes
 
+## Release 0.2.1 - 9/24/2024
+
+### General 
+1. Bug fixes across the repo
+1. Added AI Alliance RAG demo, tutorials and notebooks and tips for running on google colab
+1. Added new transforms and single package for transforms published to pypi
+1. Improved CI/CD with targeted workflow triggered on specific changes to specific modules
+1. New enhancements for cutting a release
+
+
+### data-prep-toolkit libraries (python, ray, spark) 
+
+1. Restructure the repository to distinguish/separate runtime libraries
+1. Split data-processing-lib/ray into python and ray
+1. Spark runtime
+1. Updated pyarrow version
+1. Define required transform() method as abstract to AbstractTableTransform
+1. Enables configuration of makefile to use src or pypi for data-prep-kit library dependencies 
+
+
+### KFP Workloads 
+
+1. Add a configurable timeout before destroying the deployed Ray cluster.
+
+### Transforms
+
+1. Added 7 new transdforms including: language identification, profiler, repo level ordering, doc quality, pdf2parquet, HTML2Parquet and PII Transform
+1. Added ededup python implementation and incremental ededup 
+1. Added fuzzy floating point comparison
+
+
 ## Release 0.2.0 - 6/27/2024
 
 ### General 

diff --git a/transforms/code/code2parquet/kfp_ray/code2parquet_wf.py b/transforms/code/code2parquet/kfp_ray/code2parquet_wf.py
@@ -21,11 +21,11 @@
 # the name of the job script
 EXEC_SCRIPT_NAME: str = "code2parquet_transform_ray.py"
 
-task_image = "quay.io/dataprep1/data-prep-kit/code2parquet-ray:latest"
+task_image = "quay.io/dataprep1/data-prep-kit/code2parquet-ray:0.2.1"
 
 
 # components
-base_kfp_image = "quay.io/dataprep1/data-prep-kit/kfp-data-processing:latest"
+base_kfp_image = "quay.io/dataprep1/data-prep-kit/kfp-data-processing:0.2.1"
 
 # path to kfp component specifications files
 component_spec_path = "../../../../kfp/kfp_ray_components/"

diff --git a/transforms/code/code2parquet/python/pyproject.toml b/transforms/code/code2parquet/python/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "dpk_code2parquet_transform_python"
-version = "0.2.1.dev3"
+version = "0.2.1"
 requires-python = ">=3.10"
 description = "code2parquet Python Transform"
 license = {text = "Apache-2.0"}
@@ -10,7 +10,7 @@ authors = [
     { name = "Boris Lublinsky", email = "blublinsky@ibm.com" },
 ]
 dependencies = [
-    "data-prep-toolkit==0.2.1.dev3",
+    "data-prep-toolkit==0.2.1",
     "parameterized",
     "pandas",
 ]
@@ -33,7 +33,7 @@ dev = [
 ]
 
 [options]
-package_dir = ["src","test"]
+package_dir = ["src"]
 
 [options.packages.find]
 where = ["src/"]

diff --git a/transforms/code/code2parquet/ray/pyproject.toml b/transforms/code/code2parquet/ray/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "dpk_code2parquet_transform_ray"
-version = "0.2.1.dev3"
+version = "0.2.1"
 requires-python = ">=3.10"
 description = "code2parquet Ray Transform"
 license = {text = "Apache-2.0"}
@@ -10,8 +10,8 @@ authors = [
     { name = "Boris Lublinsky", email = "blublinsky@ibm.com" },
 ]
 dependencies = [
-    "data-prep-toolkit-ray==0.2.1.dev3",
-    "dpk-code2parquet-transform-python==0.2.1.dev3",
+    "data-prep-toolkit-ray==0.2.1",
+    "dpk-code2parquet-transform-python==0.2.1",
     "parameterized",
     "pandas",
 ]
@@ -34,7 +34,7 @@ dev = [
 ]
 
 [options]
-package_dir = ["src","test"]
+package_dir = ["src"]
 
 [options.packages.find]
 where = ["src/"]

diff --git a/transforms/code/code_quality/kfp_ray/code_quality_wf.py b/transforms/code/code_quality/kfp_ray/code_quality_wf.py
@@ -21,10 +21,10 @@
 EXEC_SCRIPT_NAME: str = "code_quality_transform_ray.py"
 PREFIX: str = ""
 
-task_image = "quay.io/dataprep1/data-prep-kit/code_quality-ray:latest"
+task_image = "quay.io/dataprep1/data-prep-kit/code_quality-ray:0.2.1"
 
 # components
-base_kfp_image = "quay.io/dataprep1/data-prep-kit/kfp-data-processing:latest"
+base_kfp_image = "quay.io/dataprep1/data-prep-kit/kfp-data-processing:0.2.1"
 
 # path to kfp component specifications files
 component_spec_path = "../../../../kfp/kfp_ray_components/"

diff --git a/transforms/code/code_quality/python/pyproject.toml b/transforms/code/code_quality/python/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "dpk_code_quality_transform_python"
-version = "0.2.1.dev3"
+version = "0.2.1"
 requires-python = ">=3.10"
 description = "Code Quality Python Transform"
 license = {text = "Apache-2.0"}
@@ -9,7 +9,7 @@ authors = [
     { name = "Shivdeep Singh", email = "shivdeep.singh@ibm.com" },
 ]
 dependencies = [
-    "data-prep-toolkit==0.2.1.dev3",
+    "data-prep-toolkit==0.2.1",
     "bs4==0.0.2",
     "transformers==4.38.2",
 ]
@@ -32,7 +32,7 @@ dev = [
 ]
 
 [options]
-package_dir = ["src","test"]
+package_dir = ["src"]
 
 [options.packages.find]
 where = ["src/"]

diff --git a/transforms/code/code_quality/ray/pyproject.toml b/transforms/code/code_quality/ray/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "dpk_code_quality_transform_ray"
-version = "0.2.1.dev3"
+version = "0.2.1"
 requires-python = ">=3.10"
 description = "Code Quality Ray Transform"
 license = {text = "Apache-2.0"}
@@ -9,8 +9,8 @@ authors = [
     { name = "Shivdeep Singh", email = "shivdeep.singh@ibm.com" },
 ]
 dependencies = [
-    "dpk-code-quality-transform-python==0.2.1.dev3",
-    "data-prep-toolkit-ray==0.2.1.dev3",
+    "dpk-code-quality-transform-python==0.2.1",
+    "data-prep-toolkit-ray==0.2.1",
 ]
 
 [build-system]
@@ -31,7 +31,7 @@ dev = [
 ]
 
 [options]
-package_dir = ["src","test"]
+package_dir = ["src"]
 
 [options.packages.find]
 where = ["src/"]

diff --git a/transforms/code/header_cleanser/kfp_ray/header_cleanser_wf.py b/transforms/code/header_cleanser/kfp_ray/header_cleanser_wf.py
@@ -21,10 +21,10 @@
 EXEC_SCRIPT_NAME: str = "header_cleanser_transform_ray.py"
 PREFIX: str = ""
 
-task_image = "quay.io/dataprep1/data-prep-kit/header_cleanser-ray:latest"
+task_image = "quay.io/dataprep1/data-prep-kit/header_cleanser-ray:0.2.1"
 
 # components
-base_kfp_image = "quay.io/dataprep1/data-prep-kit/kfp-data-processing:latest"
+base_kfp_image = "quay.io/dataprep1/data-prep-kit/kfp-data-processing:0.2.1"
 
 # path to kfp component specifications files
 component_spec_path = "../../../../kfp/kfp_ray_components/"