Initial Release

.github/dependabot.yml

@@ -0,0 +1,19 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+version: 2
+updates:
+  - package-ecosystem: "npm" # See documentation for possible values
+    directory: "docsite/" # Location of package manifests
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "pip" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "github-actions"
+    # Workflow files stored in the default location of `.github/workflows`. (You don't need to specify `/.github/workflows` for `directory`. You can use `directory: "/"`.)
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/pull_request_template.md

@@ -0,0 +1,36 @@
+<!--
+Thanks for contributing to GraphRAG!
+
+Please do not make *Draft* pull requests, as they still notify anyone watching the repo.
+
+Create a pull request when it is ready for review and feedback.
+
+About this template
+
+The following template aims to help contributors write a good description for their pull requests.
+We'd like you to provide a description of the changes in your pull request (i.e. bugs fixed or features added), the motivation behind the changes, and complete the checklist below before opening a pull request.
+
+Feel free to discard it if you need to (e.g. when you just fix a typo). -->
+
+## Description
+
+[Provide a brief description of the changes made in this pull request.]
+
+## Related Issues
+
+[Reference any related issues or tasks that this pull request addresses.]
+
+## Proposed Changes
+
+[List the specific changes made in this pull request.]
+
+## Checklist
+
+- [ ] I have tested these changes locally.
+- [ ] I have reviewed the code changes.
+- [ ] I have updated the documentation (if necessary).
+- [ ] I have added appropriate unit tests (if applicable).
+
+## Additional Notes
+
+[Add any additional notes or context that may be helpful for the reviewer(s).]

.github/workflows/gh-pages.yml

@@ -0,0 +1,95 @@
+name: gh-pages
+on:
+  push:
+    branches: [main]
+
+permissions:
+  contents: write
+
+env:
+  POETRY_VERSION: 1.8.3
+  PYTHON_VERSION: '3.11'
+  NODE_VERSION: 18.x
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    env:
+      GH_PAGES: 1
+      DEBUG: 1
+      GRAPHRAG_LLM_TYPE: "azure_openai_chat"
+      GRAPHRAG_EMBEDDING_TYPE: "azure_openai_embedding"
+      GRAPHRAG_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      GRAPHRAG_API_BASE: ${{ secrets.GRAPHRAG_API_BASE }}
+      GRAPHRAG_API_VERSION: ${{ secrets.GRAPHRAG_API_VERSION }}
+      GRAPHRAG_LLM_DEPLOYMENT_NAME: ${{ secrets.GRAPHRAG_LLM_DEPLOYMENT_NAME }}
+      GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME: ${{ secrets.GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME }}
+      GRAPHRAG_CACHE_TYPE: "blob"
+      GRAPHRAG_CACHE_CONNECTION_STRING: ${{ secrets.BLOB_STORAGE_CONNECTION_STRING }}
+      GRAPHRAG_CACHE_CONTAINER_NAME: "cicache"
+      GRAPHRAG_CACHE_BASE_DIR": "cache"
+      GRAPHRAG_LLM_MODEL: gpt-3.5-turbo-16k
+      GRAPHRAG_EMBEDDING_MODEL: text-embedding-ada-002
+      # We have Windows + Linux runners in 3.10 and 3.11, so we need to divide the rate limits by 4
+      GRAPHRAG_LLM_TPM: 45_000 # 180,000 / 4
+      GRAPHRAG_LLM_RPM: 270 # 1,080 / 4
+      GRAPHRAG_EMBEDDING_TPM: 87_500 # 350,000 / 4
+      GRAPHRAG_EMBEDDING_RPM: 525 # 2,100 / 4
+      GRAPHRAG_CHUNK_SIZE: 1200
+      GRAPHRAG_CHUNK_OVERLAP: 0
+      # Azure AI Search config
+      AZURE_AI_SEARCH_URL_ENDPOINT: ${{ secrets.AZURE_AI_SEARCH_URL_ENDPOINT }}
+      AZURE_AI_SEARCH_API_KEY: ${{ secrets.AZURE_AI_SEARCH_API_KEY }}
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          persist-credentials: false
+
+      - name: Set up Python ${{ env.PYTHON_VERSION }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Install Poetry ${{ env.POETRY_VERSION }}
+        uses: abatilo/[email protected]
+        with:
+          poetry-version: ${{ env.POETRY_VERSION }}
+
+      - name: Use Node ${{ env.NODE_VERSION }}
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+
+      - name: Install Yarn dependencies
+        run: yarn install
+        working-directory: docsite
+
+      - name: Install Poetry dependencies
+        run: poetry install
+
+      - name: Install Azurite
+        id: azuright
+        uses: potatoqualitee/[email protected]
+
+      - name: Generate Indexer Outputs
+        run: |
+          poetry run poe test_smoke
+          zip -jrm docsite/data/operation_dulce/dataset.zip tests/fixtures/min-csv/output/*/artifacts/*.parquet
+        
+      - name: Build Jupyter Notebooks
+        run: poetry run poe convert_docsite_notebooks
+
+      - name: Build docsite
+        run: yarn build
+        working-directory: docsite
+
+      - name: List docsite files
+        run: find docsite/_site
+
+      - name: Deploy to GitHub Pages
+        uses: JamesIves/[email protected]
+        with:
+          branch: gh-pages
+          folder: docsite/_site
+          clean: true

.github/workflows/javascript-ci.yml

@@ -0,0 +1,30 @@
+name: JavaScript CI
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+env:
+  NODE_VERSION: 18.x
+
+jobs:
+  javascript-ci:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+    steps:
+      - name: Use Node ${{ env.NODE_VERSION }}
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+
+      - uses: actions/checkout@v4
+
+      - run: yarn install
+        working-directory: docsite
+        name: Install Dependencies
+
+      - run: yarn build
+        working-directory: docsite
+        name: Build Docsite

.github/workflows/python-ci.yml

@@ -0,0 +1,122 @@
+name: Python CI
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+  pull-requests: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  # Only run the for the latest commit
+  cancel-in-progress: true
+
+env:
+  POETRY_VERSION: 1.8.3
+
+jobs:
+  python-ci:
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+        os: [ubuntu-latest, windows-latest]
+    env:
+      DEBUG: 1
+      GRAPHRAG_LLM_TYPE: "azure_openai_chat"
+      GRAPHRAG_EMBEDDING_TYPE: "azure_openai_embedding"
+      GRAPHRAG_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      GRAPHRAG_API_BASE: ${{ secrets.GRAPHRAG_API_BASE }}
+      GRAPHRAG_API_VERSION: ${{ secrets.GRAPHRAG_API_VERSION }}
+      GRAPHRAG_LLM_DEPLOYMENT_NAME: ${{ secrets.GRAPHRAG_LLM_DEPLOYMENT_NAME }}
+      GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME: ${{ secrets.GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME }}
+      GRAPHRAG_CACHE_TYPE: "blob"
+      GRAPHRAG_CACHE_CONNECTION_STRING: ${{ secrets.BLOB_STORAGE_CONNECTION_STRING }}
+      GRAPHRAG_CACHE_CONTAINER_NAME: "cicache"
+      GRAPHRAG_CACHE_BASE_DIR": "cache"
+      GRAPHRAG_LLM_MODEL: gpt-3.5-turbo-16k
+      GRAPHRAG_EMBEDDING_MODEL: text-embedding-ada-002
+      # We have Windows + Linux runners in 3.10 and 3.11, so we need to divide the rate limits by 4
+      GRAPHRAG_LLM_TPM: 45_000 # 180,000 / 4
+      GRAPHRAG_LLM_RPM: 270 # 1,080 / 4
+      GRAPHRAG_EMBEDDING_TPM: 87_500 # 350,000 / 4
+      GRAPHRAG_EMBEDDING_RPM: 525 # 2,100 / 4
+      GRAPHRAG_CHUNK_SIZE: 1200
+      GRAPHRAG_CHUNK_OVERLAP: 0
+      # Azure AI Search config
+      AZURE_AI_SEARCH_URL_ENDPOINT: ${{ secrets.AZURE_AI_SEARCH_URL_ENDPOINT }}
+      AZURE_AI_SEARCH_API_KEY: ${{ secrets.AZURE_AI_SEARCH_API_KEY }}
+
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: dorny/paths-filter@v3
+        id: changes
+        with:
+          filters: |
+            python:
+              - 'graphrag/**/*'
+              - 'poetry.lock'
+              - 'pyproject.toml'
+              - '**/*.py'
+              - '**/*.toml'
+              - '**/*.ipynb'
+              - '.github/workflows/python*.yml'
+              - 'tests/smoke/*'
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install Poetry
+        uses: abatilo/[email protected]
+        with:
+          poetry-version: $POETRY_VERSION
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry self add setuptools && poetry run python -m pip install gensim && poetry install
+
+      - name: Check Semversioner
+        run: |
+          poetry run semversioner check
+
+      - name: Check
+        run: |
+          poetry run poe check
+
+      - name: Build
+        run: |
+          poetry build
+
+      - name: Install Azurite
+        id: azuright
+        uses: potatoqualitee/[email protected]
+
+      - name: Unit Test
+        run: |
+          poetry run poe test_unit
+
+      - name: Integration Test
+        run: |
+          poetry run poe test_integration
+
+      - name: Smoke Test
+        if: steps.changes.outputs.python == 'true'
+        run: |
+          poetry run poe test_smoke
+
+      - uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: smoke-test-artifacts-${{ matrix.python-version }}-${{ matrix.poetry-version }}-${{ runner.os }}
+          path: tests/fixtures/*/output
+
+      - name: E2E Test
+        if: steps.changes.outputs.python == 'true'
+        run: |
+          ./scripts/e2e-test.sh

.github/workflows/python-publish.yml

@@ -0,0 +1,56 @@
+name: Python Publish
+on:
+  release:
+    types: [created]
+  push:
+    branches: [main]
+
+env:
+  POETRY_VERSION: 1.8.3
+  PYTHON_VERSION: 3.10
+
+jobs:
+  publish:
+    name: Upload release to PyPI
+    if: github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/graphrag
+    permissions:
+        id-token: write  # IMPORTANT: this permission is mandatory for trusted publishing
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: $PYTHON_VERSION
+
+      - name: Install Poetry
+        uses: abatilo/[email protected]
+        with:
+          poetry-version: $POETRY_VERSION
+
+      - name: Add poetry-dynamic-versioning plugin
+        run: poetry self add "poetry-dynamic-versioning[plugin]"
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry install
+
+      - name: Build Distributable
+        shell: bash
+        run: poetry build
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: dist
+          skip-existing: true
+          verbose: true
+

.github/workflows/semver.yml

@@ -0,0 +1,15 @@
+name: Semver Check
+on:
+  pull_request:
+    branches: [main]
+
+jobs:
+    semver:
+        runs-on: ubuntu-latest
+        steps:
+        - uses: actions/checkout@v4
+          with:
+            fetch-depth: 0
+
+        - name: Check Semver
+          run: ./scripts/semver-check.sh

.github/workflows/spellcheck.yml

@@ -0,0 +1,15 @@
+name: Spellcheck
+on:
+  push:
+    branches: [main]
+  pull_request:
+    paths:
+      - '**/*'
+jobs:
+  spellcheck:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Spellcheck
+        run: ./scripts/spellcheck.sh