🚀 Upgrade linting to use ruff

.github/workflows/python.yml

@@ -40,10 +40,10 @@ jobs:
           python-version: ${{ env.PYTHON_VERSION }}
           cache: "poetry"
       - run: poetry install
-      - name: Run isort check
-        run: poetry run isort --check .
+      - name: Run lint check
+        run: poetry run ruff check
       - name: Run black check
-        run: poetry run black --check .
+        run: poetry run ruff format --check
 
   mypy:
     runs-on: ubuntu-latest

bananalyzer/__main__.py

@@ -4,17 +4,13 @@
 import argparse
 import ast
 import importlib.util
-import os
 import sys
 from pathlib import Path
 from typing import List
 from urllib.parse import urlparse
 
-import requests
-
 from bananalyzer import AgentRunner
 from bananalyzer.data.examples import (
-    download_examples,
     get_test_examples,
     get_training_examples,
 )
@@ -49,14 +45,14 @@ def print_intro() -> None:
 def parse_args() -> Args:
     file_name = "bananalyzer-agent.py"
     parser = argparse.ArgumentParser(
-        description=f"Run the agent inside a bananalyzer agent definition file "
-        f"against the benchmark",
+        description="Run the agent inside a bananalyzer agent definition file "
+        "against the benchmark",
     )
     parser.add_argument(
         "path", type=str, nargs="?", default=None, help=f"Path to the {file_name} file"
     )
     parser.add_argument(
-        "--headless", action="store_true", help=f"Whether to run headless or not"
+        "--headless", action="store_true", help="Whether to run headless or not"
     )
     parser.add_argument(
         "-s",

bananalyzer/data/generate_examples.py

@@ -6,7 +6,7 @@
 from typing import Any, Dict, List
 
 from openai import OpenAI
-from playwright.async_api import Page, async_playwright
+from playwright.async_api import async_playwright
 from tarsier import GoogleVisionOCRService, Tarsier
 
 from bananalyzer.data.examples import convert_to_crlf

bananalyzer/data/schemas.py

@@ -1,6 +1,5 @@
 from typing import Any, Dict, List, Literal, Optional, Union
 
-import pydantic
 from playwright.async_api import Page
 from pydantic import BaseModel, Field, model_validator
 
@@ -42,18 +41,14 @@ def eval_results(
         if (
             self.type == "json_match"
             and field is not None
-            and type(self.expected) is dict
+            and isinstance(self.expected, dict)
         ):
             return validate_field_match(self.expected, result, field)
 
-        if (
-            self.type == "json_match"
-            and type(self.expected) is dict
-            or type(self.expected) is list
-        ):
+        if self.type == "json_match" and isinstance(self.expected, (list, dict)):
             return validate_json_match(self.expected, result)
 
-        if self.type == "end_url_match" and type(self.expected) is str:
+        if self.type == "end_url_match" and isinstance(self.expected, str):
             return validate_end_url_match(self.expected, page.url)
 
         raise NotImplementedError("No evaluation type implemented")

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "bananalyzer"
-version = "0.7.3"
+version = "0.7.4"
 
 description = "Open source AI Agent evaluation framework for web tasks 🐒🍌"
 authors = ["asim-shrestha <asim.shrestha@hotmail.com>"]
@@ -15,30 +15,23 @@ playwright = "^1.39.0"
 pydantic = "^2.4.2"
 pytest-asyncio = "^0.21.1"
 deepdiff = "^6.7.0"
-pytest-xdist = "^3.4.0"
-black = { extras = ["jupyter"], version = "^23.11.0" }
+pytest = "^7.4.2"
 pytest-html = "^4.1.1"
+pytest-xdist = "^3.4.0"
 tabulate = "^0.9.0"
 requests = "^2.31.0"
 tarsier = "^0.5.0"
 openai = "^1.3.7"
 
 [tool.poetry.group.test.dependencies]
-pytest = "^7.4.2"
 pytest-mock = "^3.11.1"
 pytest-cov = "^4.1.0"
 
 [tool.poetry.group.dev.dependencies]
 mypy = "^1.6.1"
-black = { extras = ["jupyter"], version = "^23.11.0" }
 types-requests = "^2.31.0.10"
-isort = "^5.12.0"
 types-tabulate = "^0.9.0.3"
-
-[tool.isort]
-profile = "black"
-multi_line_output = 3
-src_paths = ["bananalyzer", "tests"]
+ruff = "^0.1.13"
 
 [tool.mypy]
 plugins = [

tests/test_example_eval.py

@@ -105,7 +105,7 @@ def test_url_eval(mocker: MockFixture) -> None:
 
 
 def create_default_example(
-    overrides: Optional[Dict[str, Any]] = None
+    overrides: Optional[Dict[str, Any]] = None,
 ) -> Dict[str, Any]:
     default_example: Dict[str, Any] = {
         "id": "1",