mdgraph-ai 0.1.0__tar.gz

mdgraph_ai-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,39 @@
+name: Publish to PyPI
+
+# Trigger the workflow only when a new GitHub Release is published
+on:
+  release:
+    types: [published]
+
+jobs:
+  build-and-publish:
+    name: Build and Publish Python Package
+    runs-on: ubuntu-latest
+    
+    # Define the environment name (required for PyPI Trusted Publishing)
+    environment:
+      name: pypi
+      url: https://pypi.org/p/mdgraph-ai
+
+    # Required permissions for PyPI OIDC authentication
+    permissions:
+      id-token: write 
+      contents: read
+
+    steps:
+      - name: Checkout Source Code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install build tools
+        run: python -m pip install --upgrade pip build
+
+      - name: Build Source Distribution and Wheel
+        run: python -m build
+
+      - name: Publish Package to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

mdgraph_ai-0.1.0/.gitignore

@@ -0,0 +1,224 @@
+# 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
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# 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/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+
+devops.md
+
+
+.pypirc

mdgraph_ai-0.1.0/CHANGELOG.md

@@ -0,0 +1,25 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+---
+
+## [0.1.0] - 2026-10-17
+
+### Added
+- **Google Open Knowledge Format (OKF v0.2)** implementation with Pydantic validation and serialization.
+- **Universal Ingestion Pipeline** supporting PDF (`pypdf`, `docling`), HTML with structural table extraction, Markdown, and plain text.
+- **Pluggable LLM Compiler** powered by `LiteLLM` supporting OpenAI, Anthropic, Gemini, and local Ollama models.
+- **Deterministic Rule-Based Offline Compiler** for offline test and production setups without API keys.
+- **Git-Backed Truth Storage Layer** ensuring Markdown files in Git serve as the single source of truth.
+- **SQLite FTS5 Vectorless Relational Cache** with BM25 full-text keyword ranking.
+- **Multi-Hop Graph Traversal** using native SQL Recursive Common Table Expressions (`WITH RECURSIVE`).
+- **Shortest Path Topological Search** via SQL Recursive CTEs.
+- **Optional Enterprise PostgreSQL Backend** with `JSONB`, `tsvector`, and recursive CTE support.
+- **Incremental & Full Index Synchronization Worker** (`IndexSyncWorker`).
+- **Native FastMCP Server** exposing `get_concept()`, `read_concept_body()`, `search_knowledge()`, `traverse_graph()`, `find_path()`, `list_concepts()`, `get_graph_stats()`, and `reindex()` over SSE and stdio transports.
+- **Rich Interactive CLI (`mdgraph`)** with commands: `init`, `ingest`, `compile`, `index`, `query`, `traverse`, `show`, `stats`, `serve`.
+- Comprehensive test suite with 23 passing tests across all modules.

mdgraph_ai-0.1.0/CODE_OF_CONDUCT.md

@@ -0,0 +1,73 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+**conduct@mdgraph.dev**. All complaints will be reviewed and investigated promptly
+and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org),
+version 2.1, available at
+https://www.contributor-covenant.org/version/2/1/code_of_conduct.html

mdgraph_ai-0.1.0/CONTRIBUTING.md

@@ -0,0 +1,102 @@
+# Contributing to MdGraph
+
+Thank you for your interest in contributing to **MdGraph**! 
+
+MdGraph is an open-source storage engine implementing Google's Open Knowledge Format (OKF) to build deterministic, traversable, and version-controlled context for autonomous AI agents.
+
+Whether you're fixing a bug, adding a parser for new file formats, improving graph traversal algorithms, or extending MCP tools, we welcome your contributions.
+
+---
+
+## Code of Conduct
+
+This project adheres to the [Contributor Covenant](CODE_OF_CONDUCT.md). By participating, you are expected to uphold this code.
+
+---
+
+## Development Setup
+
+### Prerequisites
+
+- **Python**: 3.10, 3.11, 3.12, 3.13, or 3.14
+- **Git**: Installed and configured on your system
+
+### 1. Clone the Repository
+
+```bash
+git clone https://github.com/firecodex/mdgraph.git
+cd mdgraph
+```
+
+### 2. Create and Activate a Virtual Environment
+
+```bash
+python3 -m venv .venv
+source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+```
+
+### 3. Install in Editable Mode with Dev Dependencies
+
+```bash
+pip install -e ".[dev]"
+```
+
+---
+
+## Development Workflow
+
+### Running Tests
+
+We maintain strict test coverage. Run the test suite using `pytest`:
+
+```bash
+pytest
+```
+
+Run tests with verbose output:
+
+```bash
+pytest -v
+```
+
+### Code Formatting and Linting
+
+We adhere to standard Python PEP 8 styling, formatted with `ruff`:
+
+```bash
+# Check linting
+ruff check .
+
+# Fix auto-fixable lint issues
+ruff check --fix .
+
+# Check formatting
+ruff format --check .
+```
+
+---
+
+## Submitting Pull Requests
+
+1. **Fork the Repository**: Create your own fork and create a feature branch:
+   ```bash
+   git checkout -b feature/my-new-feature
+   ```
+2. **Make Your Changes**: Write clean, readable code with descriptive comments and type annotations where appropriate.
+3. **Add Tests**: Every bug fix or new feature must include corresponding unit or integration tests in `tests/`.
+4. **Run the Full Test Suite**: Ensure all existing and new tests pass before submitting.
+5. **Commit Your Changes**: Follow conventional commits:
+   - `feat: add support for docx document ingestion`
+   - `fix: resolve cycle prevention edge case in recursive CTE`
+   - `docs: update FastMCP tool signatures in README`
+6. **Open a Pull Request**: Open a PR targeting the `main` branch with a clear description of the problem solved and changes made.
+
+---
+
+## Architecture Guidelines
+
+- **Compiler vs. Cache Separation**: Keep the Compiler Layer (heavy, LLM-driven, state-mutating) strictly decoupled from the Query Cache (lightweight, read-optimized, vectorless index).
+- **Strict OKF Conformance**: Ensure all generated Markdown files adhere strictly to Google's Open Knowledge Format (non-empty `type`, YAML frontmatter, explicit links `[Title](./target.md)`).
+- **Git-Backed Truth**: The Markdown filesystem in Git is always the single source of truth. The database cache must be disposable and completely rebuildable from Git at any time.
+
+Thank you for helping make context engines better for autonomous AI!

mdgraph_ai-0.1.0/LICENSE

@@ -0,0 +1,122 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work.
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner.
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License.