Skip to content

Turn agent_eval into a proper module to include it in Python package #5491

Turn agent_eval into a proper module to include it in Python package

Turn agent_eval into a proper module to include it in Python package #5491

Workflow file for this run

# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
name: ContribTests
on:
pull_request:
branches: ["main"]
paths:
- "autogen/**"
- "test/agentchat/contrib/**"
- "test/test_browser_utils.py"
- "test/test_retrieve_utils.py"
- ".github/workflows/contrib-tests.yml"
- "setup.py"
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref }}
cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
permissions:
{}
# actions: read
# checks: read
# contents: read
# deployments: read
jobs:
RetrieveChatTest:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [macos-latest, windows-2019]
python-version: ["3.9", "3.10", "3.11"]
exclude:
- os: macos-latest
python-version: "3.9"
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install qdrant_client when python-version is 3.10
if: matrix.python-version == '3.10'
run: |
pip install -e .[retrievechat-qdrant]
- name: Install packages and dependencies for RetrieveChat
run: |
pip install -e .[retrievechat]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/test_retrieve_utils.py test/agentchat/contrib/retrievechat/test_retrievechat.py test/agentchat/contrib/retrievechat/test_qdrant_retrievechat.py test/agentchat/contrib/vectordb --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
RetrieveChatTest-Ubuntu:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: ["3.9", "3.10", "3.11"]
services:
pgvector:
image: ankane/pgvector
env:
POSTGRES_DB: postgres
POSTGRES_USER: postgres
POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
POSTGRES_HOST_AUTH_METHOD: trust
options: >-
--health-cmd pg_isready
--health-interval 10s
--health-timeout 5s
--health-retries 5
ports:
- 5432:5432
mongodb:
image: mongodb/mongodb-atlas-local:latest
ports:
- 27017:27017
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest
- name: Install qdrant_client when python-version is 3.10
if: matrix.python-version == '3.10'
run: |
pip install -e .[retrievechat-qdrant]
- name: Install pgvector when on linux
run: |
pip install -e .[retrievechat-pgvector]
- name: Install mongodb when on linux
run: |
pip install -e .[retrievechat-mongodb]
- name: Install unstructured when python-version is 3.9 and on linux
if: matrix.python-version == '3.9'
run: |
sudo apt-get update
sudo apt-get install -y tesseract-ocr poppler-utils
pip install --no-cache-dir unstructured[all-docs]==0.13.0
- name: Install packages and dependencies for RetrieveChat
run: |
pip install -e .[retrievechat]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
- name: Coverage
run: |
pip install pytest-cov>=5
pytest test/test_retrieve_utils.py test/agentchat/contrib/retrievechat test/agentchat/contrib/vectordb --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
AgentEvalTest:
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest]
python-version: ["3.10"]
runs-on: ${{ matrix.os }}
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for AgentEval
run: |
pip install -e .
- name: Coverage
run: |
pytest test/agentchat/contrib/agent_eval/ --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
GPTAssistantAgent:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.10"]
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for GPTAssistantAgent
run: |
pip install -e .
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/agentchat/contrib/test_gpt_assistant.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
TeachableAgent:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.11"]
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for Teachability
run: |
pip install -e .[teachable]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/agentchat/contrib/capabilities/test_teachable_agent.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
WebSurfer:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.12"]
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for WebSurfer
run: |
pip install -e .[websurfer]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/test_browser_utils.py test/agentchat/contrib/test_web_surfer.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
LMMTest:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.12"]
steps:
- uses: actions/checkout@v4
with:
lfs: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for LMM
run: |
pip install -e .[lmm]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/agentchat/contrib/test_img_utils.py test/agentchat/contrib/test_lmm.py test/agentchat/contrib/test_llava.py test/agentchat/contrib/capabilities/test_vision_capability.py --skip-openai
- name: Image Gen Coverage
if: ${{ matrix.os != 'windows-2019' && matrix.python-version != '3.12' }}
run: |
pytest test/agentchat/contrib/capabilities/test_image_generation_capability.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
GeminiTest:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.9", "3.10", "3.11", "3.12"]
exclude:
- os: macos-latest
python-version: "3.9"
steps:
- uses: actions/checkout@v4
with:
lfs: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for Gemini
run: |
pip install -e .[gemini,test]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/oai/test_gemini.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
TransformMessages:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.11"]
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for Transform Messages
run: |
pip install -e '.[long-context]'
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/agentchat/contrib/capabilities/test_transform_messages.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittest
LlamaIndexAgent:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.11"]
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for LlamaIndexConverableAgent
run: |
pip install -e .
pip install llama-index
pip install llama-index-llms-openai
- name: Coverage
run: |
pytest test/agentchat/contrib/test_llamaindex_conversable_agent.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
AnthropicTest:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: ["ubuntu-latest", "windows-latest", "macos-latest"]
python-version: ["3.9", "3.10", "3.11", "3.12"]
steps:
- uses: actions/checkout@v4
with:
lfs: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for Anthropic
run: |
pip install -e .[test]
pip install -e .[anthropic]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/oai/test_anthropic.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
MistralTest:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.9", "3.10", "3.11", "3.12"]
exclude:
- os: macos-latest
python-version: "3.9"
steps:
- uses: actions/checkout@v4
with:
lfs: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for Mistral
run: |
pip install -e .[mistral,test]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/oai/test_mistral.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
TogetherTest:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.9", "3.10", "3.11", "3.12"]
exclude:
- os: macos-latest
python-version: "3.9"
steps:
- uses: actions/checkout@v4
with:
lfs: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for Together
run: |
pip install -e .[together,test]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/oai/test_together.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
GroqTest:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.9", "3.10", "3.11", "3.12"]
exclude:
- os: macos-latest
python-version: "3.9"
steps:
- uses: actions/checkout@v4
with:
lfs: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for Groq
run: |
pip install -e .[groq,test]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/oai/test_groq.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
CohereTest:
runs-on: ${{ matrix.os }}
strategy:
matrix:
os: [ubuntu-latest, macos-latest, windows-latest]
python-version: ["3.9", "3.10", "3.11", "3.12"]
steps:
- uses: actions/checkout@v4
with:
lfs: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for Cohere
run: |
pip install -e .[cohere,test]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/oai/test_cohere.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests
BedrockTest:
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, macos-latest, windows-2019]
python-version: ["3.9", "3.10", "3.11", "3.12"]
exclude:
- os: macos-latest
python-version: "3.9"
steps:
- uses: actions/checkout@v4
with:
lfs: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install packages and dependencies for all tests
run: |
python -m pip install --upgrade pip wheel
pip install pytest-cov>=5
- name: Install packages and dependencies for Amazon Bedrock
run: |
pip install -e .[boto3,test]
- name: Set AUTOGEN_USE_DOCKER based on OS
shell: bash
run: |
if [[ ${{ matrix.os }} != ubuntu-latest ]]; then
echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
fi
- name: Coverage
run: |
pytest test/oai/test_bedrock.py --skip-openai
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v3
with:
file: ./coverage.xml
flags: unittests