levelapp 0.1.0__tar.gz

levelapp-0.1.0/.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

levelapp-0.1.0/.python-version

@@ -0,0 +1 @@
+3.12

levelapp-0.1.0/MANIFEST.in

@@ -0,0 +1,9 @@
+include LICENCE
+include README.md
+include docs/*
+include examples/*
+recursive-include levelapp *.py
+exclude .env
+exclude uv.lock
+recursive-exclude tests *
+recursive-exclude src *

levelapp-0.1.0/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

levelapp-0.1.0/PKG-INFO

@@ -0,0 +1,254 @@
+Metadata-Version: 2.4
+Name: levelapp
+Version: 0.1.0
+Summary: LevelApp is an evaluation framework for AI/LLM-based software application. [Powered by Norma]
+Project-URL: Homepage, https://github.com/levelapp-org
+Project-URL: Repository, https://github.com/levelapp-org/levelapp-framework
+Project-URL: Documentation, https://levelapp.readthedocs.io
+Project-URL: Issues, https://github.com/levelapp-org/levelapp-framework/issues
+Author-email: KadriSof <kadrisofyen@gmail.com>
+License-File: LICENSE
+Keywords: ai,evaluation,framework,llm,testing
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Testing
+Requires-Python: >=3.12
+Requires-Dist: arrow>=1.3.0
+Requires-Dist: httpx>=0.28.1
+Requires-Dist: numpy>=2.3.2
+Requires-Dist: openai>=1.99.9
+Requires-Dist: pandas-stubs==2.3.0.250703
+Requires-Dist: pandas>=2.3.1
+Requires-Dist: pydantic>=2.11.7
+Requires-Dist: python-dotenv>=1.1.1
+Requires-Dist: pyyaml>=6.0.2
+Requires-Dist: rapid>=0.0.3
+Requires-Dist: rapidfuzz>=3.13.0
+Requires-Dist: requests>=2.32.4
+Requires-Dist: tenacity>=9.1.2
+Provides-Extra: dev
+Requires-Dist: arrow>=1.3.0; extra == 'dev'
+Requires-Dist: httpx>=0.28.1; extra == 'dev'
+Requires-Dist: numpy>=2.3.2; extra == 'dev'
+Requires-Dist: openai>=1.99.9; extra == 'dev'
+Requires-Dist: pandas-stubs==2.3.0.250703; extra == 'dev'
+Requires-Dist: pandas>=2.3.1; extra == 'dev'
+Requires-Dist: pydantic>=2.11.7; extra == 'dev'
+Requires-Dist: python-dotenv>=1.1.1; extra == 'dev'
+Requires-Dist: pyyaml>=6.0.2; extra == 'dev'
+Requires-Dist: rapid>=0.0.3; extra == 'dev'
+Requires-Dist: rapidfuzz>=3.13.0; extra == 'dev'
+Requires-Dist: requests>=2.32.4; extra == 'dev'
+Requires-Dist: tenacity>=9.1.2; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# LevelApp: AI/LLM Evaluation Framework for Regression Testing
+
+[![PyPI version](https://badge.fury.io/py/levelapp.svg)](https://badge.fury.io/py/levelapp)  
+[![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)  
+[![Python Version](https://img.shields.io/badge/python-3.12%2B-blue.svg)](https://www.python.org/downloads/)
+
+## Overview
+
+LevelApp is an evaluation framework designed for regression testing (black-box) of already built LLM-based systems in production or testing phases. It focuses on assessing the performance and reliability of AI/LLM applications through simulation and comparison modules. Powered by Norma.
+
+Key benefits:
+- Configuration-driven: Minimal coding required; define evaluations via YAML files.
+- Supports LLM-as-a-judge for qualitative assessments and quantitative metrics for metadata evaluation.
+- Modular architecture for easy extension to new workflows, evaluators, and repositories.
+
+## Features
+
+- **Simulator Module**: Evaluates dialogue systems by simulating conversations using predefined scripts. It uses an LLM as a judge to score replies against references and supports metrics (e.g., Exact, Embedded, Token-based, Fuzzy) for comparing extracted metadata to ground truth.
+- **Comparator Module**: Evaluates metadata extraction from JSON outputs (e.g., from legal/financial document processing with LLMs) by comparing against reference/ground-truth data.
+- **Configuration-Based Workflow**: Users provide YAML configs for endpoints, parameters, data sources, and metrics, reducing the need for custom code.
+- **Supported Workflows**: SIMULATOR, COMPARATOR, ASSESSOR (coming soon!).
+- **Repositories**: FIRESTORE, FILESYSTEM, MONGODB.
+- **Evaluators**: JUDGE, REFERENCE, RAG.
+- **Metrics**: Exact, Levenshtein, and more (see docs for full list).
+- **Data Sources**: Local or remote JSON for conversation scripts.
+
+## Installation
+
+Install LevelApp via pip:
+
+```bash
+pip install levelapp
+```
+
+### Prerequisites
+- Python 3.12 or higher.
+- API keys for LLM providers (e.g., OpenAI, Anthropic) if using external clients—store in a `.env` file.
+- Optional: Google Cloud credentials for Firestore repository.
+- Dependencies are automatically installed, including `openai`, `pydantic`, `numpy`, etc. (see `pyproject.toml` for full list).
+
+## Configuration
+
+LevelApp uses a YAML configuration file to define the evaluation setup. Create a `workflow_config.yaml` with the following structure:
+
+```yaml
+project_name: "test-project"
+evaluation_params:
+  attempts: 1  # Number of simulation attempts.
+
+workflow: SIMULATOR  # SIMULATOR, COMPARATOR, ASSESSOR.
+repository: FIRESTORE  # FIRESTORE, FILESYSTEM, MONGODB.
+evaluators: # JUDGE, REFERENCE, RAG.
+  - JUDGE
+  - REFERENCE
+
+endpoint_configuration:
+  base_url: "http://127.0.0.1:8000"
+  url_path: ''
+  api_key: "<API-KEY>"
+  bearer_token: "<BEARER-TOKEN>"
+  model_id: "meta-llama/Meta-Llama-3.1-8B-Instruct"
+  payload_path: "../../src/data/payload_example_1.yaml"
+  default_request_payload_template:
+    prompt: "${user_message}"
+    details: "${request_payload}"  # Rest of the request payload data.
+  default_response_payload_template:
+    agent_reply: "${agent_reply}"
+    guardrail_flag: "${guardrail_flag}"
+    generated_metadata: "${generated_metadata}"
+
+reference_data:
+  source: LOCAL  # LOCAL or REMOTE.
+  path: "../../src/data/conversation_example_1.json"
+
+metrics_map:
+  field_1: EXACT
+  field_2: LEVENSHTEIN
+```
+
+- **Endpoint Configuration**: Define how to interact with your LLM-based system (base URL, auth, payload templates).
+- **Placeholders**: For the request payload, change the field names (e.g., 'prompt' to 'message') according to your API specs. For the response payload, change the place holders values (e.g., `${agent_reply}` to `${generated_reply}`).
+- **Secrets**: Store API keys in `.env` and load via `python-dotenv` (e.g., `API_KEY=your_key_here`).
+
+For conversation scripts (used in Simulator), provide a JSON file with this schema:
+
+```json
+{
+  "id": "1fa6f6ed-3cfe-4c0b-b389-7292f58879d4",
+  "scripts": [
+    {
+      "id": "65f58cec-d55d-4a24-bf16-fa8327a3aa6b",
+      "interactions": [
+        {
+          "id": "e99a2898-6a79-4a20-ac85-dfe977ea9935",
+          "user_message": "Hello, I would like to book an appointment with a doctor.",
+          "reference_reply": "Sure, I can help with that. Could you please specify the type of doctor you need to see?",
+          "interaction_type": "initial",
+          "reference_metadata": {},
+          "generated_metadata": {},
+          "guardrail_flag": false,
+          "request_payload": {"user_id":  "0001", "user_role": "ADMIN"}
+        },
+        {
+          "id": "fe5c539a-d0a1-40ee-97bd-dbe456703ccc",
+          "user_message": "I need to see a cardiologist.",
+          "reference_reply": "When would you like to schedule your appointment?",
+          "interaction_type": "intermediate",
+          "reference_metadata": {},
+          "generated_metadata": {},
+          "guardrail_flag": false,
+          "request_payload": {"user_id":  "0001", "user_role": "ADMIN"}
+        },
+        {
+          "id": "2cfdbd1c-a065-48bb-9aa9-b958342154b1",
+          "user_message": "I would like to book it for next Monday morning.",
+          "reference_reply": "We have an available slot at 10 AM next Monday. Does that work for you?",
+          "interaction_type": "intermediate",
+          "reference_metadata": {
+            "appointment_type": "Cardiology",
+            "date": "next Monday",
+            "time": "10 AM"
+          },
+          "generated_metadata": {
+            "appointment_type": "Cardiology",
+            "date": "next Monday",
+            "time": "morning"
+          },
+          "guardrail_flag": false,
+          "request_payload": {"user_id":  "0001", "user_role": "ADMIN"}
+        },
+        {
+          "id": "f4f2dd35-71d7-4b75-ba2b-93a4f546004a",
+          "user_message": "Yes, please book it for 10 AM then.",
+          "reference_reply": "Your appointment with the cardiologist is booked for 10 AM next Monday. Is there anything else I can help you with?",
+          "interaction_type": "final",
+          "reference_metadata": {},
+          "generated_metadata": {},
+          "guardrail_flag": false,
+          "request_payload": {"user_id":  "0001", "user_role": "ADMIN"}
+        }
+      ],
+      "description": "A conversation about booking a doctor appointment.",
+      "details": {
+        "context": "Booking a doctor appointment"
+      }
+    }
+  ]
+}
+```
+
+- **Fields**: Include user messages, reference/references replies, metadata for comparison, guardrail flags, and request payloads.
+
+## Usage Example
+
+To run an evaluation:
+
+1. Prepare your YAML config and JSON data files.
+2. Use the following Python script:
+
+```python
+if __name__ == "__main__":
+    from levelapp.workflow.schemas import WorkflowConfig
+    from levelapp.core.session import EvaluationSession
+
+    # Load configuration from YAML
+    config = WorkflowConfig.load(path="../data/workflow_config.yaml")
+
+    # Run evaluation session
+    with EvaluationSession(session_name="sim-test", workflow_config=config) as session:
+        session.run()
+        results = session.workflow.collect_results()
+        print("Results:", results)
+
+    stats = session.get_stats()
+    print(f"session stats:\n{stats}")
+```
+
+- This loads the config, runs the specified workflow (e.g., Simulator), collects results, and prints stats.
+
+For more examples, see the `examples/` directory.
+
+## Documentation
+
+Detailed docs are in the `docs/` directory, including API references and advanced configuration.
+
+## Contributing
+
+Contributions are welcome! Please follow these steps:
+- Fork the repository on GitHub.
+- Create a feature branch (`git checkout -b feature/new-feature`).
+- Commit changes (`git commit -am 'Add new feature'`).
+- Push to the branch (`git push origin feature/new-feature`).
+- Open a pull request.
+
+Report issues via GitHub Issues. Follow the code of conduct (if applicable).
+
+## Acknowledgments
+
+- Powered by Norma.
+- Thanks to contributors and open-source libraries like Pydantic, NumPy, and OpenAI SDK.
+
+## License
+
+This project is licensed under the MIT License - see the [LICENCE](LICENCE) file for details.
+
+---