mirror of
https://github.com/microsoft/graphrag.git
synced 2026-02-12 14:04:30 +08:00
c02ab0984a
* Remove create_final_nodes * Rename final entity output to "entities" * Remove duplicate code from graph extraction * Rename create_final_relationships output to "relationships" * Rename create_final_communities output to "communities" * Combine compute_communities and create_final_communities * Rename create_final_covariates output to "covariates" * Rename create_final_community_reports output to "community_reports" * Rename create_final_text_units output to "text_units" * Rename create_final_documents output to "documents" * Remove transient snapshots config * Move create_final_entities to finalize_entities operation * Move create_final_relationships flow to finalize_relationships operation * Reuse some community report functions * Collapse most of graph and text unit-based report generation * Unify schemas files * Move community reports extractor * Move NLP report prompt to prompts folder * Fix a few pandas warnings * Rename embeddings config to embed_text * Rename claim_extraction config to extract_claims * Remove nltk from standard graph extraction * Fix verb tests * Fix extract graph config naming * Fix moved file reference * Create v1-to-v2 migration notebook * Semver * Fix smoke test artifact count * Raise tpm/rpm on smoke tests * Update drift settings for smoke tests * Reuse project directory var in api notebook * Format * Format
122 lines
3.5 KiB
YAML
122 lines
3.5 KiB
YAML
name: Python Smoke Tests
|
|
on:
|
|
push:
|
|
branches:
|
|
- "**/main" # match branches like feature/main
|
|
- "main" # match the main branch
|
|
pull_request:
|
|
types:
|
|
- opened
|
|
- reopened
|
|
- synchronize
|
|
- ready_for_review
|
|
branches:
|
|
- "**/main"
|
|
- "main"
|
|
paths-ignore:
|
|
- "**/*.md"
|
|
- ".semversioner/**"
|
|
|
|
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:
|
|
# skip draft PRs
|
|
if: github.event.pull_request.draft == false
|
|
strategy:
|
|
matrix:
|
|
python-version: ["3.10"]
|
|
os: [ubuntu-latest, windows-latest]
|
|
fail-fast: false # Continue running all jobs even if one fails
|
|
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_CONTAINER_NAME: "cicache"
|
|
GRAPHRAG_CACHE_BASE_DIR": "cache"
|
|
GRAPHRAG_LLM_MODEL: ${{ secrets.GRAPHRAG_LLM_MODEL }}
|
|
GRAPHRAG_EMBEDDING_MODEL: ${{ secrets.GRAPHRAG_EMBEDDING_MODEL }}
|
|
# We have Windows + Linux runners in 3.10 and 3.11, so we need to divide the rate limits by 4
|
|
GRAPHRAG_LLM_TPM: 100_000 # 400_000 / 4
|
|
GRAPHRAG_LLM_RPM: 500 # 2_000 / 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/actions-poetry@v3.0.0
|
|
with:
|
|
poetry-version: $POETRY_VERSION
|
|
|
|
- name: Install dependencies
|
|
shell: bash
|
|
run: |
|
|
poetry self add setuptools wheel
|
|
poetry run python -m pip install gensim
|
|
poetry install
|
|
|
|
- name: Build
|
|
run: |
|
|
poetry build
|
|
|
|
- name: Verb Test
|
|
run: |
|
|
poetry run poe test_verbs
|
|
|
|
- name: Install Azurite
|
|
id: azuright
|
|
uses: potatoqualitee/azuright@v1.1
|
|
|
|
- name: Smoke Test
|
|
if: steps.changes.outputs.python == 'true'
|
|
run: |
|
|
poetry run poe test_smoke
|
|
|
|
- uses: actions/upload-artifact@v4
|
|
if: always()
|
|
with:
|
|
name: smoke-test-artifacts-${{ matrix.python-version }}-${{ matrix.poetry-version }}-${{ runner.os }}
|
|
path: tests/fixtures/*/output
|