sdg-hub 0.4.2__tar.gz → 0.5.0__tar.gz

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/.github/workflows/integration-test.yml

@@ -7,29 +7,11 @@ on:
     branches:
       - "main"
       - "release-**"
-    paths:
-      # Only trigger on changes to relevant flows and examples (EXTEND THIS):
-      - 'src/sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/**'
-      - 'examples/knowledge_tuning/enhanced_summary_knowledge_tuning/**'
-      # Standard integration test triggers, DONT CHANGE THIS
-      - 'tests/integration/**/*.py'
-      - 'pyproject.toml'
-      - 'tox.ini'
-      - '.github/workflows/integration-test.yml'
   pull_request:
     branches:
       - "main"
       - "release-**"
     types: [opened, synchronize, reopened, labeled]
-    paths:
-      # Only trigger on changes to relevant flows and examples (EXTEND THIS):
-      - 'src/sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/**'
-      - 'examples/knowledge_tuning/enhanced_summary_knowledge_tuning/**'
-      # Standard integration test triggers, DONT CHANGE THIS
-      - 'tests/integration/**/*.py'
-      - 'pyproject.toml'
-      - 'tox.ini'
-      - '.github/workflows/integration-test.yml'
 
 env:
   LC_ALL: en_US.UTF-8
@@ -42,19 +24,58 @@ permissions:
   contents: read
 
 jobs:
+  check-trigger:
+    name: "Check If Integration Should Run"
+    runs-on: ubuntu-latest
+    outputs:
+      should_run: ${{ steps.check.outputs.should_run }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: dorny/paths-filter@v3
+        id: filter
+        if: github.event_name == 'pull_request'
+        with:
+          filters: |
+            relevant:
+              # Only trigger on changes to relevant flows and examples (EXTEND THIS):
+              - 'src/sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/**'
+              - 'examples/knowledge_tuning/enhanced_summary_knowledge_tuning/**'
+              # Standard integration test triggers, DONT CHANGE THIS
+              - 'tests/integration/**/*.py'
+              - 'pyproject.toml'
+              - 'tox.ini'
+              - '.github/workflows/integration-test.yml'
+
+      - name: Determine if tests should run
+        id: check
+        run: |
+          if [[ "${{ github.event_name }}" == "workflow_dispatch" ]] || [[ "${{ github.event_name }}" == "push" ]]; then
+            echo "should_run=true" >> "$GITHUB_OUTPUT"
+          elif [[ "${{ github.event_name }}" == "pull_request" ]]; then
+            # Check if from fork
+            if [[ "${{ github.event.pull_request.head.repo.full_name }}" != "${{ github.repository }}" ]]; then
+              echo "should_run=false" >> "$GITHUB_OUTPUT"
+            # Check if labeled event with correct label
+            elif [[ "${{ github.event.action }}" == "labeled" ]] && [[ "${{ contains(github.event.pull_request.labels.*.name, 'run-integration-tests') }}" == "true" ]]; then
+              echo "should_run=true" >> "$GITHUB_OUTPUT"
+            # Check if relevant paths changed for non-labeled events
+            elif [[ "${{ github.event.action }}" != "labeled" ]] && [[ "${{ steps.filter.outputs.relevant }}" == "true" ]]; then
+              echo "should_run=true" >> "$GITHUB_OUTPUT"
+            else
+              echo "should_run=false" >> "$GITHUB_OUTPUT"
+            fi
+          else
+            echo "should_run=false" >> "$GITHUB_OUTPUT"
+          fi
+
   integration-test:
     name: "Integration Tests - ${{ matrix.python }} on ${{ matrix.platform }}"
     runs-on: "${{ matrix.platform }}"
+    needs: check-trigger
+    if: needs.check-trigger.outputs.should_run == 'true'
     # Require manual approval before running (via GitHub Environment)
     environment: integration-tests
-    # Skip fork PRs (they can't access environment secrets anyway)
-    # Also check for 'run-integration-tests' label on labeled events
-    if: |
-      github.event_name == 'workflow_dispatch' ||
-      github.event_name == 'push' ||
-      (github.event_name == 'pull_request' &&
-       github.event.pull_request.head.repo.full_name == github.repository &&
-       (github.event.action != 'labeled' || contains(github.event.pull_request.labels.*.name, 'run-integration-tests')))
     strategy:
       matrix:
         python:
@@ -89,12 +110,9 @@ jobs:
             **/pyproject.toml
             **/requirements*.txt
 
-      - name: Remove llama-cpp-python from cache
-        run: |
-          pip cache remove llama_cpp_python
 
       - name: Cache huggingface datasets
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
+        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: ~/.cache/huggingface
           # Invalidate cache when any example notebook changes (may affect dataset downloads)
@@ -111,10 +129,6 @@ jobs:
         run: |
           tox -e py3-integrationcov
 
-      - name: Remove llama-cpp-python from cache
-        if: always()
-        run: |
-          pip cache remove llama_cpp_python
 
       - name: Upload integration test coverage to Codecov
         uses: codecov/codecov-action@v4

sdg_hub-0.5.0/.github/workflows/packer.yml

@@ -0,0 +1,33 @@
+name: Build AMI with Packer
+
+on:
+  workflow_dispatch:
+
+jobs:
+  build-ami:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write # This is required for OIDC
+      contents: read
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@ff717079ee2060e4bcee96c4779b553acc87447c
+        with:
+          role-to-assume: arn:aws:iam::851725220677:role/github-actions-packer-role
+          aws-region: us-east-2
+          role-session-name: github-actions-packer  # For tracking in CloudTrail
+
+      - name: Setup Packer
+        uses: hashicorp/setup-packer@1aa358be5cf73883762b302a3a03abd66e75b232
+
+      - name: Build and create AMI
+        run: |
+          set -euo pipefail
+          cd scripts/packer
+          packer init .
+          packer validate .
+          packer build .

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/.github/workflows/test.yml

@@ -86,16 +86,7 @@ jobs:
             **/pyproject.toml
             **/requirements*.txt
 
-      - name: Remove llama-cpp-python from cache
-        run: |
-          pip cache remove llama_cpp_python
 
-      - name: Cache huggingface
-        uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4.2.3
-        with:
-          path: ~/.cache/huggingface
-          # config contains DEFAULT_MODEL
-          key: huggingface-${{ hashFiles('src/instructlab/configuration.py') }}
 
       - name: Install dependencies
         run: |
@@ -107,10 +98,6 @@ jobs:
           tox -e py3-unitcov
 
 
-      - name: Remove llama-cpp-python from cache
-        if: always()
-        run: |
-          pip cache remove llama_cpp_python
       
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/CLAUDE.md

@@ -86,7 +86,6 @@ The framework is built around a modular block system with **composability at its
   - `transform/`: Data transformation blocks (column operations, text manipulation)
   - `filtering/`: Data filtering blocks with quality thresholds
   - `evaluation/`: Quality evaluation blocks (faithfulness, relevancy assessment)
-  - `deprecated_blocks/`: Legacy blocks maintained for backward compatibility
 
 **Key Benefits**: Type-safe composition, automatic validation, rich logging, and high-performance async processing.
 
@@ -97,7 +96,6 @@ Flows orchestrate multiple blocks into data processing pipelines:
 - **FlowRegistry** (`src/sdg_hub/core/flow/registry.py`): Registry for flow discovery
 - **FlowMetadata** (`src/sdg_hub/core/flow/metadata.py`): Metadata and parameter definitions
 - **FlowValidator** (`src/sdg_hub/core/flow/validation.py`): YAML structure validation
-- **FlowMigration** (`src/sdg_hub/core/flow/migration.py`): Backward compatibility for old flow formats
 
 ### Flow Configuration
 Flows are defined in YAML files with this structure:
@@ -148,11 +146,6 @@ All blocks operate on HuggingFace `datasets.Dataset` objects:
 - Rich logging provides processing summaries
 - Empty dataset handling with appropriate errors
 
-### Backward Compatibility
-The framework maintains compatibility with legacy formats:
-- Deprecated blocks are preserved in `deprecated_blocks/`
-- Flow migration automatically converts old YAML formats
-- Legacy LLMBlocks receive special handling during execution
 
 ## Testing Guidelines
 

{sdg_hub-0.4.2/src/sdg_hub.egg-info → sdg_hub-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdg_hub
-Version: 0.4.2
+Version: 0.5.0
 Summary: Synthetic Data Generation
 Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
 License: Apache-2.0
@@ -23,7 +23,7 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: click<9.0.0,>=8.1.7
-Requires-Dist: datasets<4.0.0,>=2.18.0
+Requires-Dist: datasets>=4.0.0
 Requires-Dist: httpx<1.0.0,>=0.25.0
 Requires-Dist: jinja2
 Requires-Dist: litellm<1.75.0,>=1.73.0

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/examples/knowledge_tuning/enhanced_summary_knowledge_tuning/knowledge_mixing.ipynb

@@ -359,7 +359,7 @@
     "processed_knowledge_dataset = processed_knowledge_dataset.remove_columns(['messages']).rename_column('messages_without_think', 'messages')\n",
     "\n",
     "cfg = RAFTConfig(k_passages=5, max_tokens_per_chunk=400, p_include_oracle=0.9)\n",
-    "raft_samples = build_raft_samples(ds, cfg)\n",
+    "raft_samples = build_raft_samples(processed_knowledge_dataset, cfg)\n",
     "raft_samples = raft_samples.map(build_messages).remove_columns(['question', 'context', 'oracle_context', 'cot_answer', 'answer', 'instruction', 'type', 'meta'])\n",
     "\n",
     "fp = \"<Instruction/Skills dataset>\" # TODO: Replace with huggingface dataset path once its uploaded\n",

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/examples/knowledge_tuning/enhanced_summary_knowledge_tuning/raft_builder.py

@@ -237,20 +237,13 @@ def build_messages(raft_record: Dict[str, Any]):
     Output:
       messages: list of {"role": "system"|"user"|"assistant", "content": str}
     """
-    # 1. System message
-    sys_msg = raft_record.get("instruction") or (
-        "You are a domain expert. You must answer questions by first quoting a span "
-        "verbatim from the relevant passage, then giving reasoning, then the final answer. "
-        "Ignore distractor passages."
-    )
-
-    # 2. User message: serialize passages + question
+    # 1. User message: serialize passages + question
     passages = "\n\n".join(
         [f"[Passage {i+1}] {p}" for i, p in enumerate(raft_record["context"])]
     )
     user_msg = f"Passages:\n{passages}\n\nQuestion: {raft_record['question']}"
 
-    # 3. Assistant message: the gold output
+    # 2. Assistant message: the gold output
     assistant_msg = raft_record["answer"]
 
     return {"messages" : [

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/pyproject.toml

@@ -30,7 +30,7 @@ classifiers = [
 # Core dependencies moved from requirements.txt
 dependencies = [
     "click>=8.1.7,<9.0.0",
-    "datasets>=2.18.0,<4.0.0",
+    "datasets>=4.0.0",
     "httpx>=0.25.0,<1.0.0",
     "jinja2",
     "litellm>=1.73.0,<1.75.0",

sdg_hub-0.5.0/scripts/packer/centos.pkr.hcl

@@ -0,0 +1,52 @@
+packer {
+  required_plugins {
+    amazon = {
+      version = ">= 1.2.8"
+      source  = "github.com/hashicorp/amazon"
+    }
+  }
+}
+
+variable "github_sha" {
+  type        = string
+  description = "GitHub commit SHA to tag the AMI with"
+  default     = env("GITHUB_SHA")
+}
+
+variable "github_repository" {
+  type        = string
+  description = "GitHub repository name to tag the AMI with"
+  default     = env("GITHUB_REPOSITORY")
+}
+
+source "amazon-ebs" "centos" {
+  ami_name      = "github-actions-centos-nvidia-ami-{{timestamp}}"
+  # Use the lowest-cost instance type that can efficiently build and santity-check the driver.
+  # It should be old enough to be low-cost, but new enough to be compatible with our desired driver version.
+  instance_type = "g6.xlarge"
+  region        = "us-east-2"
+  source_ami_filter {
+    filters = {
+      name                = "CentOS Stream 9 x86_64*"
+      root-device-type    = "ebs"
+      virtualization-type = "hvm"
+    }
+    most_recent = true
+    owners      = ["125523088429"] # CentOS CPE team ID.
+  }
+  ssh_username = "ec2-user"
+  tags = {
+    Name = "CentOS Stream 9 with Nvidia Drivers"
+    BuiltBy = "Packer"
+    GitHubCommitSHA = var.github_sha
+    GitHubRepository = var.github_repository
+  }
+}
+
+build {
+  sources = ["source.amazon-ebs.centos"]
+  provisioner "shell" {
+    script = "./setup-centos.sh"
+    execute_command = "sudo bash {{.Path}}"
+  }
+}

sdg_hub-0.5.0/scripts/packer/setup-centos.sh

@@ -0,0 +1,80 @@
+#!/bin/bash
+# Setup script for CentOS GitHub Actions AMI
+# Derived from:
+# github.com/containers/ai-lab-recipes/blob/main/training/nvidia-bootc/Containerfile
+
+set -euxo pipefail
+
+DRIVER_VERSION="580.65.06"
+# CUDA_VERSION is embedded in the driver "local repo" package
+
+if [[ $(id -u) != "0" ]]; then
+    echo "you must run this script as root."
+    exit 1
+fi
+
+function configure_dnf {
+  # Configure the DNF repos and options we need for CI.
+  dnf -y install dnf-plugins-core
+  dnf config-manager --save \
+    --setopt=skip_missing_names_on_install=False \
+    --setopt=install_weak_deps=False
+
+  dnf -y install epel-release
+  dnf -y install https://us.download.nvidia.com/tesla/$DRIVER_VERSION/nvidia-driver-local-repo-rhel9-$DRIVER_VERSION-1.0-1.x86_64.rpm
+  # TODO: We might be able to use a nvidia.com yum repo instead of the local repo?
+  # dnf config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel${OS_VERSION_MAJOR}/${CUDA_REPO_ARCH}/cuda-rhel${OS_VERSION_MAJOR}.repo
+}
+
+function install_userland_packages {
+  # CI tests in GH Actions will require these packages:
+  dnf -y install nvtop podman skopeo git python3.12 python3.12-devel
+}
+
+function install_kernel_driver {
+  # Install nvidia kernel driver.
+  # DKMS will compile the nvidia.ko driver for all kernels for which we have installed a kernel-devel package.
+  # By default, the "dnf module install" command will install the latest kernel-devel package that CentOS has published.
+  dnf -y install "kernel-devel-$(uname -r)" gcc make dkms elfutils-libelf-devel  # also build for the currently-running kernel.
+  # If we had configured a previous nvidia-driver version with DNF, reset it:
+  dnf -y module reset nvidia-driver || true
+  DRIVER_STREAM=$(echo $DRIVER_VERSION | cut -d. -f1)
+  dnf -y module install nvidia-driver:${DRIVER_STREAM}-dkms # or use :latest-dkms after confirming available streams
+}
+
+function test_kernel_driver {
+  # The nvidia driver DNF module (above) installs a dkms RPM.
+  # That dkms RPM compiles and installs the nvidia.ko module.
+  # List all the modules that dkms has compiled:
+  dkms status || true
+  # Load the module (ok if it’s already loaded or unavailable for this kernel):
+  modprobe -q nvidia || true
+  # If a GPU is present, verify userspace; otherwise, fail the job:
+  nvidia-smi
+}
+
+function install_container_toolkit {
+  # Install nvidia container toolkit.
+  # When we pass GPU devices to a container (podman run --device nvidia.com/gpu=all), we use the nvidia CTK to do that.
+  # See docs at https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
+  curl -sSfL -o /etc/yum.repos.d/nvidia-container-toolkit.repo \
+    https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo
+  dnf config-manager --enable nvidia-container-toolkit-experimental
+  export NVIDIA_CONTAINER_TOOLKIT_VERSION=1.17.8-1
+  dnf install -y \
+      nvidia-container-toolkit-${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
+      nvidia-container-toolkit-base-${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
+      libnvidia-container-tools-${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
+      libnvidia-container1-${NVIDIA_CONTAINER_TOOLKIT_VERSION}
+  # Verify it works:
+  nvidia-ctk --version
+  # When you boot a node, you must run:
+  #   sudo nvidia-ctk cdi generate --output=/etc/cdi/nvidia.yaml
+  # This command scans your system for NVIDIA GPUs and creates a YAML file that lists the available devices.
+}
+
+configure_dnf
+install_userland_packages
+install_kernel_driver
+test_kernel_driver
+install_container_toolkit

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/src/sdg_hub/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.4.2'
-__version_tuple__ = version_tuple = (0, 4, 2)
+__version__ = version = '0.5.0'
+__version_tuple__ = version_tuple = (0, 5, 0)
 
-__commit_id__ = commit_id = 'gfbb2504ba'
+__commit_id__ = commit_id = 'ge1e260984'

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/src/sdg_hub/core/blocks/__init__.py

@@ -5,17 +5,6 @@ This package provides various block implementations for data generation, process
 
 # Local
 from .base import BaseBlock
-from .deprecated_blocks import (
-    CombineColumnsBlock,
-    DuplicateColumns,
-    FilterByValueBlock,
-    FlattenColumnsBlock,
-    LLMBlock,
-    RenameColumns,
-    SamplePopulatorBlock,
-    SelectorBlock,
-    SetToMajorityValue,
-)
 from .filtering import ColumnValueFilterBlock
 from .llm import LLMChatBlock, LLMParserBlock, PromptBuilderBlock, TextParserBlock
 from .registry import BlockRegistry
@@ -28,8 +17,6 @@ from .transform import (
     UniformColumnValueSetter,
 )
 
-# All blocks moved to deprecated_blocks or transform modules
-
 __all__ = [
     "BaseBlock",
     "BlockRegistry",
@@ -40,15 +27,6 @@ __all__ = [
     "RenameColumnsBlock",
     "TextConcatBlock",
     "UniformColumnValueSetter",
-    "CombineColumnsBlock",  # Deprecated
-    "DuplicateColumns",  # Deprecated
-    "FilterByValueBlock",  # Deprecated
-    "FlattenColumnsBlock",  # Deprecated
-    "RenameColumns",  # Deprecated
-    "SamplePopulatorBlock",  # Deprecated
-    "SelectorBlock",  # Deprecated
-    "SetToMajorityValue",  # Deprecated
-    "LLMBlock",  # Deprecated
     "LLMChatBlock",
     "LLMParserBlock",
     "TextParserBlock",

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/src/sdg_hub/core/blocks/transform/rename_columns.py

@@ -64,6 +64,25 @@ class RenameColumnsBlock(BaseBlock):
         -------
         Dataset
             Dataset with renamed columns.
+
+        Raises
+        ------
+        ValueError
+            If attempting to rename to a column name that already exists.
         """
+        # Check for column name collisions
+        # Strict validation: no target column name can be an existing column name
+        # This prevents chained/circular renames which can be confusing
+        existing_cols = set(samples.column_names)
+        target_cols = set(self.input_cols.values())
+
+        collision = target_cols & existing_cols
+        if collision:
+            raise ValueError(
+                f"Cannot rename to existing column names: {sorted(collision)}. "
+                "Target column names must not already exist in the dataset. "
+                "Chained renames are not supported."
+            )
+
         # Rename columns using HuggingFace datasets method
         return samples.rename_columns(self.input_cols)

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/src/sdg_hub/core/flow/base.py

@@ -41,7 +41,6 @@ from ..utils.time_estimator import estimate_execution_time
 from ..utils.yaml_utils import save_flow_yaml
 from .checkpointer import FlowCheckpointer
 from .metadata import DatasetRequirements, FlowMetadata
-from .migration import FlowMigration
 from .validation import FlowValidator
 
 logger = setup_logger(__name__)
@@ -73,8 +72,6 @@ class Flow(BaseModel):
     model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
 
     # Private attributes (not serialized)
-    _migrated_runtime_params: dict[str, dict[str, Any]] = {}
-    _llm_client: Any = None  # Only used for backward compatibility with old YAMLs
     _model_config_set: bool = False  # Track if model configuration has been set
     _block_metrics: list[dict[str, Any]] = PrivateAttr(
         default_factory=list
@@ -113,16 +110,13 @@ class Flow(BaseModel):
         return self
 
     @classmethod
-    def from_yaml(cls, yaml_path: str, client: Any = None) -> "Flow":
+    def from_yaml(cls, yaml_path: str) -> "Flow":
         """Load flow from YAML configuration file.
 
         Parameters
         ----------
         yaml_path : str
             Path to the YAML flow configuration file.
-        client : Any, optional
-            LLM client instance. Required for backward compatibility with old format YAMLs
-            that use deprecated LLMBlocks. Ignored for new format YAMLs.
 
         Returns
         -------
@@ -153,21 +147,6 @@ class Flow(BaseModel):
         except yaml.YAMLError as exc:
             raise FlowValidationError(f"Invalid YAML in {yaml_path}: {exc}") from exc
 
-        # Check if this is an old format flow and migrate if necessary
-        migrated_runtime_params = None
-        is_old_format = FlowMigration.is_old_format(flow_config)
-        if is_old_format:
-            logger.info(f"Detected old format flow, migrating: {yaml_path}")
-            if client is None:
-                logger.warning(
-                    "Old format YAML detected but no client provided. LLMBlocks may fail."
-                )
-            flow_config, migrated_runtime_params = FlowMigration.migrate_to_new_format(
-                flow_config, yaml_path
-            )
-            # Save migrated config back to YAML to persist id
-            save_flow_yaml(yaml_path, flow_config, "migrated to new format")
-
         # Validate YAML structure
         validator = FlowValidator()
         validation_errors = validator.validate_yaml_structure(flow_config)
@@ -194,19 +173,6 @@ class Flow(BaseModel):
 
         for i, block_config in enumerate(block_configs):
             try:
-                # Inject client for deprecated LLMBlocks if this is an old format flow
-                if (
-                    is_old_format
-                    and block_config.get("block_type") == "LLMBlock"
-                    and client is not None
-                ):
-                    if "block_config" not in block_config:
-                        block_config["block_config"] = {}
-                    block_config["block_config"]["client"] = client
-                    logger.debug(
-                        f"Injected client for deprecated LLMBlock: {block_config['block_config'].get('block_name')}"
-                    )
-
                 block = cls._create_block_from_config(block_config, yaml_dir)
                 blocks.append(block)
             except Exception as exc:
@@ -228,12 +194,6 @@ class Flow(BaseModel):
                 )
             else:
                 logger.debug(f"Flow already had id: {flow.metadata.id}")
-            # Store migrated runtime params and client for backward compatibility
-            if migrated_runtime_params:
-                flow._migrated_runtime_params = migrated_runtime_params
-            if is_old_format and client is not None:
-                flow._llm_client = client
-
             # Check if this is a flow without LLM blocks
             llm_blocks = flow._detect_llm_blocks()
             if not llm_blocks:
@@ -484,12 +444,6 @@ class Flow(BaseModel):
         self._block_metrics = []
         run_start = time.perf_counter()
 
-        # Merge migrated runtime params with provided ones (provided ones take precedence)
-        merged_runtime_params = self._migrated_runtime_params.copy()
-        if runtime_params:
-            merged_runtime_params.update(runtime_params)
-        runtime_params = merged_runtime_params
-
         # Execute flow with metrics capture, ensuring metrics are always displayed/saved
         final_dataset = None
         execution_successful = False
@@ -647,22 +601,8 @@ class Flow(BaseModel):
             input_cols = set(current_dataset.column_names)
 
             try:
-                # Check if this is a deprecated block and skip validations
-                is_deprecated_block = (
-                    hasattr(block, "__class__")
-                    and hasattr(block.__class__, "__module__")
-                    and "deprecated_blocks" in block.__class__.__module__
-                )
-
-                if is_deprecated_block:
-                    exec_logger.debug(
-                        f"Skipping validations for deprecated block: {block.block_name}"
-                    )
-                    # Call generate() directly to skip validations, but keep the runtime params
-                    current_dataset = block.generate(current_dataset, **block_kwargs)
-                else:
-                    # Execute block with validation and logging
-                    current_dataset = block(current_dataset, **block_kwargs)
+                # Execute block with validation and logging
+                current_dataset = block(current_dataset, **block_kwargs)
 
                 # Validate output
                 if len(current_dataset) == 0:
@@ -724,9 +664,11 @@ class Flow(BaseModel):
         return current_dataset
 
     def _prepare_block_kwargs(
-        self, block: BaseBlock, runtime_params: dict[str, dict[str, Any]]
+        self, block: BaseBlock, runtime_params: Optional[dict[str, dict[str, Any]]]
     ) -> dict[str, Any]:
         """Prepare execution parameters for a block."""
+        if runtime_params is None:
+            return {}
         return runtime_params.get(block.block_name, {})
 
     def set_model_config(
@@ -1114,22 +1056,8 @@ class Flow(BaseModel):
                 if max_concurrency is not None:
                     block_kwargs["_flow_max_concurrency"] = max_concurrency
 
-                # Check if this is a deprecated block and skip validations
-                is_deprecated_block = (
-                    hasattr(block, "__class__")
-                    and hasattr(block.__class__, "__module__")
-                    and "deprecated_blocks" in block.__class__.__module__
-                )
-
-                if is_deprecated_block:
-                    logger.debug(
-                        f"Dry run: Skipping validations for deprecated block: {block.block_name}"
-                    )
-                    # Call generate() directly to skip validations, but keep the runtime params
-                    current_dataset = block.generate(current_dataset, **block_kwargs)
-                else:
-                    # Execute block with validation and logging
-                    current_dataset = block(current_dataset, **block_kwargs)
+                # Execute block with validation and logging
+                current_dataset = block(current_dataset, **block_kwargs)
 
                 block_execution_time = (
                     time.perf_counter() - block_start_time

{sdg_hub-0.4.2 → sdg_hub-0.5.0}/src/sdg_hub/flows/qa_generation/document_grounded_qa/enhanced_multi_summary_qa/detailed_summary/flow.yaml

@@ -77,9 +77,13 @@ blocks:
     - ''
 - block_type: RenameColumnsBlock
   block_config:
-    block_name: rename_to_document_column
+    block_name: rename_to_raw_document_column
     input_cols:
       document: raw_document
+- block_type: RenameColumnsBlock
+  block_config:
+    block_name: rename_to_document_column
+    input_cols:
       summary: document
 - block_type: PromptBuilderBlock
   block_config: