2023-10-26 15:26:55 +00:00
|
|
|
name: Hackathon
|
|
|
|
|
|
|
|
on:
|
|
|
|
workflow_dispatch:
|
|
|
|
inputs:
|
|
|
|
agents:
|
|
|
|
description: "Agents to run (comma-separated)"
|
|
|
|
required: false
|
2023-11-16 13:48:41 +00:00
|
|
|
default: "autogpt" # Default agents if none are specified
|
2023-10-26 15:26:55 +00:00
|
|
|
|
|
|
|
jobs:
|
|
|
|
matrix-setup:
|
|
|
|
runs-on: ubuntu-latest
|
2023-11-16 13:48:41 +00:00
|
|
|
# Service containers to run with `matrix-setup`
|
|
|
|
services:
|
|
|
|
# Label used to access the service container
|
|
|
|
postgres:
|
|
|
|
# Docker Hub image
|
|
|
|
image: postgres
|
|
|
|
# Provide the password for postgres
|
|
|
|
env:
|
|
|
|
POSTGRES_PASSWORD: postgres
|
|
|
|
# Set health checks to wait until postgres has started
|
|
|
|
options: >-
|
|
|
|
--health-cmd pg_isready
|
|
|
|
--health-interval 10s
|
|
|
|
--health-timeout 5s
|
|
|
|
--health-retries 5
|
|
|
|
ports:
|
|
|
|
# Maps tcp port 5432 on service container to the host
|
|
|
|
- 5432:5432
|
2023-10-26 15:26:55 +00:00
|
|
|
outputs:
|
|
|
|
matrix: ${{ steps.set-matrix.outputs.matrix }}
|
|
|
|
env-name: ${{ steps.set-matrix.outputs.env-name }}
|
|
|
|
steps:
|
|
|
|
- id: set-matrix
|
|
|
|
run: |
|
|
|
|
if [ "${{ github.event_name }}" == "schedule" ]; then
|
|
|
|
echo "::set-output name=env-name::production"
|
2023-11-16 13:48:41 +00:00
|
|
|
echo "::set-output name=matrix::[ 'irrelevant']"
|
2023-10-26 15:26:55 +00:00
|
|
|
elif [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
|
|
|
|
IFS=',' read -ra matrix_array <<< "${{ github.event.inputs.agents }}"
|
|
|
|
matrix_string="[ \"$(echo "${matrix_array[@]}" | sed 's/ /", "/g')\" ]"
|
|
|
|
echo "::set-output name=env-name::production"
|
|
|
|
echo "::set-output name=matrix::$matrix_string"
|
|
|
|
else
|
|
|
|
echo "::set-output name=env-name::testing"
|
2023-11-16 13:48:41 +00:00
|
|
|
echo "::set-output name=matrix::[ 'irrelevant' ]"
|
2023-10-26 15:26:55 +00:00
|
|
|
fi
|
|
|
|
|
|
|
|
tests:
|
|
|
|
environment:
|
|
|
|
name: "${{ needs.matrix-setup.outputs.env-name }}"
|
|
|
|
needs: matrix-setup
|
|
|
|
env:
|
|
|
|
min-python-version: "3.10"
|
|
|
|
name: "${{ matrix.agent-name }}"
|
|
|
|
runs-on: ubuntu-latest
|
2023-11-16 13:48:41 +00:00
|
|
|
services:
|
|
|
|
# Label used to access the service container
|
|
|
|
postgres:
|
|
|
|
# Docker Hub image
|
|
|
|
image: postgres
|
|
|
|
# Provide the password for postgres
|
|
|
|
env:
|
|
|
|
POSTGRES_PASSWORD: postgres
|
|
|
|
# Set health checks to wait until postgres has started
|
|
|
|
options: >-
|
|
|
|
--health-cmd pg_isready
|
|
|
|
--health-interval 10s
|
|
|
|
--health-timeout 5s
|
|
|
|
--health-retries 5
|
|
|
|
ports:
|
|
|
|
# Maps tcp port 5432 on service container to the host
|
|
|
|
- 5432:5432
|
2023-10-26 15:26:55 +00:00
|
|
|
timeout-minutes: 50
|
|
|
|
strategy:
|
|
|
|
fail-fast: false
|
|
|
|
matrix:
|
|
|
|
agent-name: ${{fromJson(needs.matrix-setup.outputs.matrix)}}
|
|
|
|
steps:
|
|
|
|
- name: Print Environment Name
|
|
|
|
run: |
|
|
|
|
echo "Matrix Setup Environment Name: ${{ needs.matrix-setup.outputs.env-name }}"
|
|
|
|
|
2023-11-16 13:48:41 +00:00
|
|
|
- name: Check Docker Container
|
|
|
|
id: check
|
|
|
|
run: docker ps
|
|
|
|
|
2023-10-26 15:26:55 +00:00
|
|
|
- name: Checkout repository
|
2024-02-17 12:59:13 +00:00
|
|
|
uses: actions/checkout@v4
|
2023-10-26 15:26:55 +00:00
|
|
|
with:
|
|
|
|
fetch-depth: 0
|
|
|
|
submodules: true
|
|
|
|
|
|
|
|
- name: Set up Python ${{ env.min-python-version }}
|
2024-02-17 12:59:13 +00:00
|
|
|
uses: actions/setup-python@v5
|
2023-10-26 15:26:55 +00:00
|
|
|
with:
|
|
|
|
python-version: ${{ env.min-python-version }}
|
|
|
|
|
|
|
|
- id: get_date
|
|
|
|
name: Get date
|
|
|
|
run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
|
|
|
|
|
|
|
|
- name: Install Poetry
|
|
|
|
run: |
|
|
|
|
curl -sSL https://install.python-poetry.org | python -
|
|
|
|
|
2023-11-16 13:48:41 +00:00
|
|
|
- name: Install Node.js
|
2024-02-17 12:59:13 +00:00
|
|
|
uses: actions/setup-node@v4
|
2023-11-16 13:48:41 +00:00
|
|
|
with:
|
|
|
|
node-version: v18.15
|
|
|
|
|
2023-10-27 14:21:29 +00:00
|
|
|
- name: Run benchmark
|
2023-10-26 15:26:55 +00:00
|
|
|
run: |
|
2023-10-27 14:21:29 +00:00
|
|
|
link=$(jq -r '.["github_repo_url"]' arena/$AGENT_NAME.json)
|
|
|
|
branch=$(jq -r '.["branch_to_benchmark"]' arena/$AGENT_NAME.json)
|
2023-10-27 14:27:43 +00:00
|
|
|
git clone "$link" -b "$branch" "$AGENT_NAME"
|
2023-10-27 14:21:29 +00:00
|
|
|
cd $AGENT_NAME
|
2024-05-22 12:08:54 +00:00
|
|
|
cp ./$AGENT_NAME/.env.example ./$AGENT_NAME/.env || echo "file not found"
|
2023-10-27 14:21:29 +00:00
|
|
|
./run agent start $AGENT_NAME
|
2023-11-16 13:48:41 +00:00
|
|
|
cd ../benchmark
|
2023-10-27 14:27:43 +00:00
|
|
|
poetry install
|
AGBenchmark codebase clean-up (#6650)
* refactor(benchmark): Deduplicate configuration loading logic
- Move the configuration loading logic to a separate `load_agbenchmark_config` function in `agbenchmark/config.py` module.
- Replace the duplicate loading logic in `conftest.py`, `generate_test.py`, `ReportManager.py`, `reports.py`, and `__main__.py` with calls to `load_agbenchmark_config` function.
* fix(benchmark): Fix type errors, linting errors, and clean up CLI validation in __main__.py
- Fixed type errors and linting errors in `__main__.py`
- Improved the readability of CLI argument validation by introducing a separate function for it
* refactor(benchmark): Lint and typefix app.py
- Rearranged and cleaned up import statements
- Fixed type errors caused by improper use of `psutil` objects
- Simplified a number of `os.path` usages by converting to `pathlib`
- Use `Task` and `TaskRequestBody` classes from `agent_protocol_client` instead of `.schema`
* refactor(benchmark): Replace `.agent_protocol_client` by `agent-protcol-client`, clean up schema.py
- Remove `agbenchmark.agent_protocol_client` (an offline copy of `agent-protocol-client`).
- Add `agent-protocol-client` as a dependency and change imports to `agent_protocol_client`.
- Fix type annotation on `agent_api_interface.py::upload_artifacts` (`ApiClient` -> `AgentApi`).
- Remove all unused types from schema.py (= most of them).
* refactor(benchmark): Use pathlib in agent_interface.py and agent_api_interface.py
* refactor(benchmark): Improve typing, response validation, and readability in app.py
- Simplified response generation by leveraging type checking and conversion by FastAPI.
- Introduced use of `HTTPException` for error responses.
- Improved naming, formatting, and typing in `app.py::create_evaluation`.
- Updated the docstring on `app.py::create_agent_task`.
- Fixed return type annotations of `create_single_test` and `create_challenge` in generate_test.py.
- Added default values to optional attributes on models in report_types_v2.py.
- Removed unused imports in `generate_test.py`
* refactor(benchmark): Clean up logging and print statements
- Introduced use of the `logging` library for unified logging and better readability.
- Converted most print statements to use `logger.debug`, `logger.warning`, and `logger.error`.
- Improved descriptiveness of log statements.
- Removed unnecessary print statements.
- Added log statements to unspecific and non-verbose `except` blocks.
- Added `--debug` flag, which sets the log level to `DEBUG` and enables a more comprehensive log format.
- Added `.utils.logging` module with `configure_logging` function to easily configure the logging library.
- Converted raw escape sequences in `.utils.challenge` to use `colorama`.
- Renamed `generate_test.py::generate_tests` to `load_challenges`.
* refactor(benchmark): Remove unused server.py and agent_interface.py::run_agent
- Remove unused server.py file
- Remove unused run_agent function from agent_interface.py
* refactor(benchmark): Clean up conftest.py
- Fix and add type annotations
- Rewrite docstrings
- Disable or remove unused code
- Fix definition of arguments and their types in `pytest_addoption`
* refactor(benchmark): Clean up generate_test.py file
- Refactored the `create_single_test` function for clarity and readability
- Removed unused variables
- Made creation of `Challenge` subclasses more straightforward
- Made bare `except` more specific
- Renamed `Challenge.setup_challenge` method to `run_challenge`
- Updated type hints and annotations
- Made minor code/readability improvements in `load_challenges`
- Added a helper function `_add_challenge_to_module` for attaching a Challenge class to the current module
* fix(benchmark): Fix and add type annotations in execute_sub_process.py
* refactor(benchmark): Simplify const determination in agent_interface.py
- Simplify the logic that determines the value of `HELICONE_GRAPHQL_LOGS`
* fix(benchmark): Register category markers to prevent warnings
- Use the `pytest_configure` hook to register the known challenge categories as markers. Otherwise, Pytest will raise "unknown marker" warnings at runtime.
* refactor(benchmark/challenges): Fix indentation in 4_revenue_retrieval_2/data.json
* refactor(benchmark): Update agent_api_interface.py
- Add type annotations to `copy_agent_artifacts_into_temp_folder` function
- Add note about broken endpoint in the `agent_protocol_client` library
- Remove unused variable in `run_api_agent` function
- Improve readability and resolve linting error
* feat(benchmark): Improve and centralize pathfinding
- Search path hierarchy for applicable `agbenchmark_config`, rather than assuming it's in the current folder.
- Create `agbenchmark.utils.path_manager` with `AGBenchmarkPathManager` and exporting a `PATH_MANAGER` const.
- Replace path constants defined in __main__.py with usages of `PATH_MANAGER`.
* feat(benchmark/cli): Clean up and improve CLI
- Updated commands, options, and their descriptions to be more intuitive and consistent
- Moved slow imports into the entrypoints that use them to speed up application startup
- Fixed type hints to match output types of Click options
- Hid deprecated `agbenchmark start` command
- Refactored code to improve readability and maintainability
- Moved main entrypoint into `run` subcommand
- Fixed `version` and `serve` subcommands
- Added `click-default-group` package to allow using `run` implicitly (for backwards compatibility)
- Renamed `--no_dep` to `--no-dep` for consistency
- Fixed string formatting issues in log statements
* refactor(benchmark/config): Move AgentBenchmarkConfig and related functions to config.py
- Move the `AgentBenchmarkConfig` class from `utils/data_types.py` to `config.py`.
- Extract the `calculate_info_test_path` function from `utils/data_types.py` and move it to `config.py` as a private helper function `_calculate_info_test_path`.
- Move `load_agent_benchmark_config()` to `AgentBenchmarkConfig.load()`.
- Changed simple getter methods on `AgentBenchmarkConfig` to calculated properties.
- Update all code references according to the changes mentioned above.
* refactor(benchmark): Fix ReportManager init parameter types and use pathlib
- Fix the type annotation of the `benchmark_start_time` parameter in `ReportManager.__init__`, was mistyped as `str` instead of `datetime`.
- Change the type of the `filename` parameter in the `ReportManager.__init__` method from `str` to `Path`.
- Rename `self.filename` with `self.report_file` in `ReportManager`.
- Change the way the report file is created, opened and saved to use the `Path` object.
* refactor(benchmark): Improve typing surrounding ChallengeData and clean up its implementation
- Use `ChallengeData` objects instead of untyped `dict` in app.py, generate_test.py, reports.py.
- Remove unnecessary methods `serialize`, `get_data`, `get_json_from_path`, `deserialize` from `ChallengeData` class.
- Remove unused methods `challenge_from_datum` and `challenge_from_test_data` from `ChallengeData class.
- Update function signatures and annotations of `create_challenge` and `generate_single_test` functions in generate_test.py.
- Add types to function signatures of `generate_single_call_report` and `finalize_reports` in reports.py.
- Remove unnecessary `challenge_data` parameter (in generate_test.py) and fixture (in conftest.py).
* refactor(benchmark): Clean up generate_test.py, conftest.py and __main__.py
- Cleaned up generate_test.py and conftest.py
- Consolidated challenge creation logic in the `Challenge` class itself, most notably the new `Challenge.from_challenge_spec` method.
- Moved challenge selection logic from generate_test.py to the `pytest_collection_modifyitems` hook in conftest.py.
- Converted methods in the `Challenge` class to class methods where appropriate.
- Improved argument handling in the `run_benchmark` function in `__main__.py`.
* refactor(benchmark/config): Merge AGBenchmarkPathManager into AgentBenchmarkConfig and reduce fragmented/global state
- Merge the functionality of `AGBenchmarkPathManager` into `AgentBenchmarkConfig` to consolidate the configuration management.
- Remove the `.path_manager` module containing `AGBenchmarkPathManager`.
- Pass the `AgentBenchmarkConfig` and its attributes through function arguments to reduce global state and improve code clarity.
* feat(benchmark/serve): Configurable port for `serve` subcommand
- Added `--port` option to `serve` subcommand to allow for specifying the port to run the API on.
- If no `--port` option is provided, the port will default to the value specified in the `PORT` environment variable, or 8080 if not set.
* feat(benchmark/cli): Add `config` subcommand
- Added a new subcommand `config` to the AGBenchmark CLI, to display information about the present AGBenchmark config.
* fix(benchmark): Gracefully handle incompatible challenge spec files in app.py
- Added a check to skip deprecated challenges
- Added logging to allow debugging of the loading process
- Added handling of validation errors when parsing challenge spec files
- Added missing `spec_file` attribute to `ChallengeData`
* refactor(benchmark): Move `run_benchmark` entrypoint to main.py, use it in `/reports` endpoint
- Move `run_benchmark` and `validate_args` from __main__.py to main.py
- Replace agbenchmark subprocess in `app.py:run_single_test` with `run_benchmark`
- Move `get_unique_categories` from __main__.py to challenges/__init__.py
- Move `OPTIONAL_CATEGORIES` from __main__.py to challenge.py
- Reduce operations on updates.json (including `initialize_updates_file`) outside of API
* refactor(benchmark): Remove unused `/updates` endpoint and all related code
- Remove `updates_json_file` attribute from `AgentBenchmarkConfig`
- Remove `get_updates` and `_initialize_updates_file` in app.py
- Remove `append_updates_file` and `create_update_json` functions in agent_api_interface.py
- Remove call to `append_updates_file` in challenge.py
* refactor(benchmark/config): Clean up and update docstrings on `AgentBenchmarkConfig`
- Add and update docstrings
- Change base class from `BaseModel` to `BaseSettings`, allow extras for backwards compatibility
- Make naming of path attributes on `AgentBenchmarkConfig` more consistent
- Remove unused `agent_home_directory` attribute
- Remove unused `workspace` attribute
* fix(benchmark): Restore mechanism to select (optional) categories in agent benchmark config
* fix(benchmark): Update agent-protocol-client to v1.1.0
- Fixes issue with fetching task artifact listings
2024-01-02 21:23:09 +00:00
|
|
|
poetry run agbenchmark --no-dep
|
2023-10-26 15:26:55 +00:00
|
|
|
env:
|
|
|
|
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
2023-11-16 13:48:41 +00:00
|
|
|
SERP_API_KEY: ${{ secrets.SERP_API_KEY }}
|
|
|
|
SERPAPI_API_KEY: ${{ secrets.SERP_API_KEY }}
|
|
|
|
WEAVIATE_API_KEY: ${{ secrets.WEAVIATE_API_KEY }}
|
|
|
|
WEAVIATE_URL: ${{ secrets.WEAVIATE_URL }}
|
|
|
|
GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
|
|
|
|
GOOGLE_CUSTOM_SEARCH_ENGINE_ID: ${{ secrets.GOOGLE_CUSTOM_SEARCH_ENGINE_ID }}
|
2023-11-21 09:58:54 +00:00
|
|
|
AGENT_NAME: ${{ matrix.agent-name }}
|