feat: Add OpenRAG Workbench evaluation framework

evaluation/openrag_workbench/.env.example

@@ -0,0 +1,41 @@
+# OpenRAG Evaluation Environment Variables
+
+# OpenRAG API Key (required)
+# This is your API key for authenticating with the OpenRAG instance.
+# Format: orag_your_api_key_here
+# 
+# To obtain an API key:
+# 1. Navigate to your OpenRAG instance (e.g., http://localhost:3000)
+# 2. Go to Settings or API Keys section
+# 3. Generate a new API key
+# 4. Copy the key and paste it below
+OPENRAG_API_KEY=
+
+# OpenRAG URL (optional)
+# Base URL of your OpenRAG instance
+# Default: http://localhost:3000
+# OPENRAG_URL=http://localhost:3000
+
+# =============================================================================
+# IBM watsonx.ai Configuration (Optional)
+# =============================================================================
+# Required ONLY if using watsonx LLM-as-a-Judge metrics:
+#   - unitxt.answer_correctness.llmaaj_llama
+#   - unitxt.answer_correctness.llmaaj_llama4
+# Documentation: https://cloud.ibm.com/docs/watsonxdata
+
+# IBM Cloud API Key - Required for watsonx authentication
+# Get your API key from: https://cloud.ibm.com/iam/apikeys
+# WATSONX_APIKEY=your_ibm_cloud_api_key_here
+
+# watsonx.ai Project ID - Required for watsonx model access
+# Get from: https://dataplatform.cloud.ibm.com/projects → Open project → Manage tab → Project ID
+# WATSONX_PROJECT_ID=your_watsonx_project_id_here
+
+# watsonx.ai URL - Optional, defaults to US South region
+# Common values:
+#   - https://us-south.ml.cloud.ibm.com (US South - default)
+#   - https://eu-de.ml.cloud.ibm.com (Frankfurt)
+#   - https://eu-gb.ml.cloud.ibm.com (London)
+#   - https://jp-tok.ml.cloud.ibm.com (Tokyo)
+# WATSONX_URL=https://us-south.ml.cloud.ibm.com

evaluation/openrag_workbench/.gitignore

@@ -0,0 +1,203 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# IDEs
+.vscode/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Specific to project
+mlflow.db
+*milvus.db*
+output*/
+
+# From unitxt
+inference_engine_cache
+
+# Cache directories
+cache/
+
+# Task logs
+logs/
+
+src/openrag_workbench/data_loaders/ait_qa_pdf/documents/
+
+# RagWorkbench data directory
+ragworkbench_data/

evaluation/openrag_workbench/README.md

@@ -0,0 +1,79 @@
+# openrag-workbench
+
+OpenRAG Workbench Tool - an evaluation framework for OpenRAG.
+
+## Installation
+
+### Prerequisites
+
+Install [uv](https://docs.astral.sh/uv/):
+```bash
+curl -LsSf https://astral.sh/uv/install.sh | sh
+```
+
+### Installation
+
+```bash
+cd openrag/evaluation/openrag_workbench
+
+# Create virtual environment
+uv venv
+
+# Install with dependencies
+uv sync
+```
+
+## Usage
+
+Run the main evaluation script:
+
+```bash
+uv run python -m openrag_workbench.evaluate
+```
+
+
+## Development
+
+For development, install with development dependencies:
+
+```bash
+# Install with dev dependencies
+uv sync --extra dev
+
+# Run tests with uv
+uv run pytest
+
+# Format code with uv
+uv run black src/ tests/
+
+# Lint code with uv
+uv run ruff check src/ tests/
+
+# Type check with uv
+uv run mypy src/
+```
+
+## Structure
+
+The project is organized as follows:
+
+```
+openrag_workbench/
+├── src/openrag_workbench/    # Main package
+│   ├── pipelines/       # Ingest and inference pipelines
+│   ├── boards/          # Evaluation board configurations
+│   └── evaluate.py      # Main evaluation script
+└── tests/               # Tests
+```
+
+The main components are:
+
+### Pipelines (`src/openrag_workbench/pipelines/`)
+Contains implementations of RAG pipelines:
+- **`ingest.py`**: A RagWorkbench ingestion pipeline implemented with the OpenRAG SDK
+- **`inference.py`**: A RagWorkbench inference pipeline implemented with the OpenRAG SDK
+
+### Boards (`src/openrag_workbench/boards/`)
+Contains board configurations for evaluation experiments:
+- **`table_rich/`**: A definition for RAG experiments over table-rich documents.
+

evaluation/openrag_workbench/pyproject.toml

@@ -0,0 +1,69 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "openrag-workbench"
+version = "0.1.0"
+description = "OpenRAG Workbench Tool"
+readme = "README.md"
+requires-python = ">=3.13"
+license = {text = "Apache-2.0"}
+
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+
+dependencies = [
+    "openrag-sdk",
+    "ragworkbench==0.1.1",
+    "pydantic>=2.0.0",
+    "python-dotenv>=1.0.0",
+    "openai>=2.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-cov>=4.0.0",
+    "black>=26.1.0",
+    "ruff>=0.14.14",
+    "mypy>=1.14.0",
+]
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["openrag_workbench*"]
+
+[tool.black]
+line-length = 88
+target-version = ['py311']
+
+[tool.ruff]
+line-length = 88
+target-version = "py311"
+src = ["src"]
+
+[tool.ruff.lint]
+select = ["E", "W", "F", "I", "B", "C4", "UP"]
+ignore = ["E501", "B008"]
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+python_files = ["test_*.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = "-v -s --strict-markers"