mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-04-22 10:52:37 +00:00
Compare commits
8 Commits
devin/1739
...
devin/1745
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
d1ca108e26 | ||
|
|
4b116638ff | ||
|
|
cd7deed7d8 | ||
|
|
85a408577c | ||
|
|
288668f1d9 | ||
|
|
f095f3e6c8 | ||
|
|
2995478a69 | ||
|
|
200ec42613 |
@@ -28,7 +28,7 @@ def create_flow(name):
|
||||
(project_root / "tests").mkdir(exist_ok=True)
|
||||
|
||||
# Create .env file
|
||||
with open(project_root / ".env", "w") as file:
|
||||
with open(project_root / ".env", "w", encoding="utf-8", newline="\n") as file:
|
||||
file.write("OPENAI_API_KEY=YOUR_API_KEY")
|
||||
|
||||
package_dir = Path(__file__).parent
|
||||
@@ -58,7 +58,7 @@ def create_flow(name):
|
||||
content = content.replace("{{flow_name}}", class_name)
|
||||
content = content.replace("{{folder_name}}", folder_name)
|
||||
|
||||
with open(dst_file, "w") as file:
|
||||
with open(dst_file, "w", encoding="utf-8", newline="\n") as file:
|
||||
file.write(content)
|
||||
|
||||
# Copy and process root template files
|
||||
|
||||
@@ -138,17 +138,22 @@ def load_provider_data(cache_file, cache_expiry):
|
||||
|
||||
def read_cache_file(cache_file):
|
||||
"""
|
||||
Reads and returns the JSON content from a cache file. Returns None if the file contains invalid JSON.
|
||||
Reads and returns the JSON content from a cache file. Returns None if the file contains invalid JSON
|
||||
or if there's an encoding error.
|
||||
|
||||
Args:
|
||||
- cache_file (Path): The path to the cache file.
|
||||
|
||||
Returns:
|
||||
- dict or None: The JSON content of the cache file or None if the JSON is invalid.
|
||||
- dict or None: The JSON content of the cache file or None if the JSON is invalid or there's an encoding error.
|
||||
"""
|
||||
try:
|
||||
with open(cache_file, "r") as f:
|
||||
with open(cache_file, "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
except UnicodeDecodeError as e:
|
||||
click.secho(f"Error reading cache file: Unicode decode error - {e}", fg="red")
|
||||
click.secho("This may be due to file encoding issues. Try deleting the cache file and trying again.", fg="yellow")
|
||||
return None
|
||||
except json.JSONDecodeError:
|
||||
return None
|
||||
|
||||
@@ -167,13 +172,16 @@ def fetch_provider_data(cache_file):
|
||||
response = requests.get(JSON_URL, stream=True, timeout=60)
|
||||
response.raise_for_status()
|
||||
data = download_data(response)
|
||||
with open(cache_file, "w") as f:
|
||||
with open(cache_file, "w", encoding="utf-8", newline="\n") as f:
|
||||
json.dump(data, f)
|
||||
return data
|
||||
except requests.RequestException as e:
|
||||
click.secho(f"Error fetching provider data: {e}", fg="red")
|
||||
except json.JSONDecodeError:
|
||||
click.secho("Error parsing provider data. Invalid JSON format.", fg="red")
|
||||
except UnicodeDecodeError as e:
|
||||
click.secho(f"Unicode decode error when processing provider data: {e}", fg="red")
|
||||
click.secho("This may be due to encoding issues with the downloaded data.", fg="yellow")
|
||||
return None
|
||||
|
||||
|
||||
|
||||
@@ -18,19 +18,24 @@ console = Console()
|
||||
|
||||
def copy_template(src, dst, name, class_name, folder_name):
|
||||
"""Copy a file from src to dst."""
|
||||
with open(src, "r") as file:
|
||||
content = file.read()
|
||||
try:
|
||||
with open(src, "r", encoding="utf-8") as file:
|
||||
content = file.read()
|
||||
|
||||
# Interpolate the content
|
||||
content = content.replace("{{name}}", name)
|
||||
content = content.replace("{{crew_name}}", class_name)
|
||||
content = content.replace("{{folder_name}}", folder_name)
|
||||
# Interpolate the content
|
||||
content = content.replace("{{name}}", name)
|
||||
content = content.replace("{{crew_name}}", class_name)
|
||||
content = content.replace("{{folder_name}}", folder_name)
|
||||
|
||||
# Write the interpolated content to the new file
|
||||
with open(dst, "w") as file:
|
||||
file.write(content)
|
||||
# Write the interpolated content to the new file
|
||||
with open(dst, "w", encoding="utf-8", newline="\n") as file:
|
||||
file.write(content)
|
||||
|
||||
click.secho(f" - Created {dst}", fg="green")
|
||||
click.secho(f" - Created {dst}", fg="green")
|
||||
except UnicodeDecodeError as e:
|
||||
click.secho(f"Error reading template file {src}: Unicode decode error - {e}", fg="red")
|
||||
click.secho("This may be due to file encoding issues. Please ensure all template files use UTF-8 encoding.", fg="yellow")
|
||||
raise
|
||||
|
||||
|
||||
def read_toml(file_path: str = "pyproject.toml"):
|
||||
@@ -78,7 +83,7 @@ def _get_project_attribute(
|
||||
attribute = None
|
||||
|
||||
try:
|
||||
with open(pyproject_path, "r") as f:
|
||||
with open(pyproject_path, "r", encoding="utf-8") as f:
|
||||
pyproject_content = parse_toml(f.read())
|
||||
|
||||
dependencies = (
|
||||
@@ -119,7 +124,7 @@ def fetch_and_json_env_file(env_file_path: str = ".env") -> dict:
|
||||
"""Fetch the environment variables from a .env file and return them as a dictionary."""
|
||||
try:
|
||||
# Read the .env file
|
||||
with open(env_file_path, "r") as f:
|
||||
with open(env_file_path, "r", encoding="utf-8") as f:
|
||||
env_content = f.read()
|
||||
|
||||
# Parse the .env file content to a dictionary
|
||||
@@ -133,6 +138,9 @@ def fetch_and_json_env_file(env_file_path: str = ".env") -> dict:
|
||||
|
||||
except FileNotFoundError:
|
||||
print(f"Error: {env_file_path} not found.")
|
||||
except UnicodeDecodeError as e:
|
||||
click.secho(f"Error reading .env file: Unicode decode error - {e}", fg="red")
|
||||
click.secho("This may be due to file encoding issues. Please ensure the .env file uses UTF-8 encoding.", fg="yellow")
|
||||
except Exception as e:
|
||||
print(f"Error reading the .env file: {e}")
|
||||
|
||||
@@ -158,10 +166,15 @@ def tree_find_and_replace(directory, find, replace):
|
||||
for filename in files:
|
||||
filepath = os.path.join(path, filename)
|
||||
|
||||
with open(filepath, "r") as file:
|
||||
contents = file.read()
|
||||
with open(filepath, "w") as file:
|
||||
file.write(contents.replace(find, replace))
|
||||
try:
|
||||
with open(filepath, "r", encoding="utf-8") as file:
|
||||
contents = file.read()
|
||||
with open(filepath, "w", encoding="utf-8", newline="\n") as file:
|
||||
file.write(contents.replace(find, replace))
|
||||
except UnicodeDecodeError as e:
|
||||
click.secho(f"Error processing file {filepath}: Unicode decode error - {e}", fg="red")
|
||||
click.secho("This may be due to file encoding issues. Skipping this file.", fg="yellow")
|
||||
continue
|
||||
|
||||
if find in filename:
|
||||
new_filename = filename.replace(find, replace)
|
||||
@@ -189,11 +202,15 @@ def load_env_vars(folder_path):
|
||||
env_file_path = folder_path / ".env"
|
||||
env_vars = {}
|
||||
if env_file_path.exists():
|
||||
with open(env_file_path, "r") as file:
|
||||
for line in file:
|
||||
key, _, value = line.strip().partition("=")
|
||||
if key and value:
|
||||
env_vars[key] = value
|
||||
try:
|
||||
with open(env_file_path, "r", encoding="utf-8") as file:
|
||||
for line in file:
|
||||
key, _, value = line.strip().partition("=")
|
||||
if key and value:
|
||||
env_vars[key] = value
|
||||
except UnicodeDecodeError as e:
|
||||
click.secho(f"Error reading .env file: Unicode decode error - {e}", fg="red")
|
||||
click.secho("This may be due to file encoding issues. Please ensure the .env file uses UTF-8 encoding.", fg="yellow")
|
||||
return env_vars
|
||||
|
||||
|
||||
@@ -244,6 +261,11 @@ def write_env_file(folder_path, env_vars):
|
||||
- env_vars (dict): A dictionary of environment variables to write.
|
||||
"""
|
||||
env_file_path = folder_path / ".env"
|
||||
with open(env_file_path, "w") as file:
|
||||
for key, value in env_vars.items():
|
||||
file.write(f"{key}={value}\n")
|
||||
try:
|
||||
with open(env_file_path, "w", encoding="utf-8", newline="\n") as file:
|
||||
for key, value in env_vars.items():
|
||||
file.write(f"{key}={value}\n")
|
||||
except Exception as e:
|
||||
click.secho(f"Error writing .env file: {e}", fg="red")
|
||||
click.secho("This may be due to file system permissions or other issues.", fg="yellow")
|
||||
raise
|
||||
|
||||
@@ -4,7 +4,6 @@ import uuid
|
||||
import warnings
|
||||
from concurrent.futures import Future
|
||||
from hashlib import md5
|
||||
from crewai.llm import LLM
|
||||
from typing import Any, Callable, Dict, List, Optional, Tuple, Union
|
||||
|
||||
from pydantic import (
|
||||
@@ -1076,36 +1075,19 @@ class Crew(BaseModel):
|
||||
def test(
|
||||
self,
|
||||
n_iterations: int,
|
||||
llm: Union[str, LLM],
|
||||
openai_model_name: Optional[str] = None,
|
||||
inputs: Optional[Dict[str, Any]] = None,
|
||||
) -> None:
|
||||
"""Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures.
|
||||
|
||||
Args:
|
||||
n_iterations: Number of test iterations to run
|
||||
llm: Language model to use for evaluation. Can be either a model name string (e.g. "gpt-4")
|
||||
or an LLM instance for custom implementations
|
||||
inputs: Optional dictionary of input values to use for task execution
|
||||
|
||||
Example:
|
||||
```python
|
||||
# Using model name string
|
||||
crew.test(n_iterations=3, llm="gpt-4")
|
||||
|
||||
# Using custom LLM implementation
|
||||
custom_llm = LLM(model="custom-model")
|
||||
crew.test(n_iterations=3, llm=custom_llm)
|
||||
```
|
||||
"""
|
||||
"""Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
|
||||
test_crew = self.copy()
|
||||
|
||||
self._test_execution_span = test_crew._telemetry.test_execution_span(
|
||||
test_crew,
|
||||
n_iterations,
|
||||
inputs,
|
||||
str(llm) if isinstance(llm, LLM) else llm,
|
||||
)
|
||||
evaluator = CrewEvaluator(test_crew, llm)
|
||||
openai_model_name, # type: ignore[arg-type]
|
||||
) # type: ignore[arg-type]
|
||||
evaluator = CrewEvaluator(test_crew, openai_model_name) # type: ignore[arg-type]
|
||||
|
||||
for i in range(1, n_iterations + 1):
|
||||
evaluator.set_iteration(i)
|
||||
|
||||
@@ -1,16 +1,10 @@
|
||||
from collections import defaultdict
|
||||
from typing import Any, Dict, List, Optional, TypeVar, Union
|
||||
from typing import DefaultDict # Separate import to avoid circular imports
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
from rich.box import HEAVY_EDGE
|
||||
from rich.console import Console
|
||||
from rich.table import Table
|
||||
|
||||
from crewai.llm import LLM
|
||||
|
||||
T = TypeVar('T', bound=LLM)
|
||||
|
||||
from crewai.agent import Agent
|
||||
from crewai.task import Task
|
||||
from crewai.tasks.task_output import TaskOutput
|
||||
@@ -34,47 +28,14 @@ class CrewEvaluator:
|
||||
iteration (int): The current iteration of the evaluation.
|
||||
"""
|
||||
|
||||
_tasks_scores: DefaultDict[int, List[float]] = Field(
|
||||
default_factory=lambda: defaultdict(list))
|
||||
_run_execution_times: DefaultDict[int, List[float]] = Field(
|
||||
default_factory=lambda: defaultdict(list))
|
||||
tasks_scores: defaultdict = defaultdict(list)
|
||||
run_execution_times: defaultdict = defaultdict(list)
|
||||
iteration: int = 0
|
||||
|
||||
@property
|
||||
def tasks_scores(self) -> DefaultDict[int, List[float]]:
|
||||
return self._tasks_scores
|
||||
|
||||
@tasks_scores.setter
|
||||
def tasks_scores(self, value: Dict[int, List[float]]) -> None:
|
||||
self._tasks_scores = defaultdict(list, value)
|
||||
|
||||
@property
|
||||
def run_execution_times(self) -> DefaultDict[int, List[float]]:
|
||||
return self._run_execution_times
|
||||
|
||||
@run_execution_times.setter
|
||||
def run_execution_times(self, value: Dict[int, List[float]]) -> None:
|
||||
self._run_execution_times = defaultdict(list, value)
|
||||
|
||||
def __init__(self, crew, llm: Union[str, T]):
|
||||
"""Initialize the CrewEvaluator.
|
||||
|
||||
Args:
|
||||
crew: The Crew instance to evaluate
|
||||
llm: Language model to use for evaluation. Can be either a model name string
|
||||
or an LLM instance for custom implementations
|
||||
|
||||
Raises:
|
||||
ValueError: If llm is None or invalid
|
||||
"""
|
||||
if not llm:
|
||||
raise ValueError("Invalid LLM configuration")
|
||||
|
||||
def __init__(self, crew, openai_model_name: str):
|
||||
self.crew = crew
|
||||
self.llm = LLM(model=llm) if isinstance(llm, str) else llm
|
||||
self.openai_model_name = openai_model_name
|
||||
self._telemetry = Telemetry()
|
||||
self._tasks_scores = defaultdict(list)
|
||||
self._run_execution_times = defaultdict(list)
|
||||
self._setup_for_evaluating()
|
||||
|
||||
def _setup_for_evaluating(self) -> None:
|
||||
@@ -90,7 +51,7 @@ class CrewEvaluator:
|
||||
),
|
||||
backstory="Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed",
|
||||
verbose=False,
|
||||
llm=self.llm,
|
||||
llm=self.openai_model_name,
|
||||
)
|
||||
|
||||
def _evaluation_task(
|
||||
@@ -220,19 +181,11 @@ class CrewEvaluator:
|
||||
self.crew,
|
||||
evaluation_result.pydantic.quality,
|
||||
current_task._execution_time,
|
||||
self._get_llm_identifier(),
|
||||
self.openai_model_name,
|
||||
)
|
||||
self._tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
|
||||
self._run_execution_times[self.iteration].append(
|
||||
self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
|
||||
self.run_execution_times[self.iteration].append(
|
||||
current_task._execution_time
|
||||
)
|
||||
else:
|
||||
raise ValueError("Evaluation result is not in the expected format")
|
||||
|
||||
def _get_llm_identifier(self) -> str:
|
||||
"""Get a string identifier for the LLM instance.
|
||||
|
||||
Returns:
|
||||
String representation of the LLM for telemetry
|
||||
"""
|
||||
return str(self.llm) if isinstance(self.llm, LLM) else self.llm
|
||||
|
||||
77
tests/cli/test_create_crew.py
Normal file
77
tests/cli/test_create_crew.py
Normal file
@@ -0,0 +1,77 @@
|
||||
import os
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
import click
|
||||
from click.testing import CliRunner
|
||||
|
||||
from crewai.cli.cli import create
|
||||
from crewai.cli.create_crew import create_crew
|
||||
|
||||
|
||||
class TestCreateCrew(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.runner = CliRunner()
|
||||
self.temp_dir = tempfile.TemporaryDirectory()
|
||||
self.test_dir = Path(self.temp_dir.name)
|
||||
|
||||
def tearDown(self):
|
||||
self.temp_dir.cleanup()
|
||||
|
||||
@patch("crewai.cli.create_crew.get_provider_data")
|
||||
@patch("crewai.cli.create_crew.select_provider")
|
||||
@patch("crewai.cli.create_crew.select_model")
|
||||
@patch("crewai.cli.create_crew.write_env_file")
|
||||
@patch("crewai.cli.create_crew.load_env_vars")
|
||||
@patch("click.confirm")
|
||||
def test_create_crew_handles_unicode(self, mock_confirm, mock_load_env,
|
||||
mock_write_env, mock_select_model,
|
||||
mock_select_provider, mock_get_provider_data):
|
||||
"""Test that create_crew command handles Unicode properly."""
|
||||
mock_confirm.return_value = True
|
||||
mock_load_env.return_value = {}
|
||||
mock_get_provider_data.return_value = {"openai": ["gpt-4"]}
|
||||
mock_select_provider.return_value = "openai"
|
||||
mock_select_model.return_value = "gpt-4"
|
||||
|
||||
templates_dir = Path("src/crewai/cli/templates/crew")
|
||||
templates_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
template_content = """
|
||||
Hello {{name}}! Unicode test: 你好, こんにちは, Привет 🚀
|
||||
Class: {{crew_name}}
|
||||
Folder: {{folder_name}}
|
||||
"""
|
||||
|
||||
(templates_dir / "tools").mkdir(exist_ok=True)
|
||||
(templates_dir / "config").mkdir(exist_ok=True)
|
||||
|
||||
for file_name in [".gitignore", "pyproject.toml", "README.md", "__init__.py", "main.py", "crew.py"]:
|
||||
with open(templates_dir / file_name, "w", encoding="utf-8") as f:
|
||||
f.write(template_content)
|
||||
|
||||
(templates_dir / "knowledge").mkdir(exist_ok=True)
|
||||
with open(templates_dir / "knowledge" / "user_preference.txt", "w", encoding="utf-8") as f:
|
||||
f.write(template_content)
|
||||
|
||||
for file_path in ["tools/custom_tool.py", "tools/__init__.py", "config/agents.yaml", "config/tasks.yaml"]:
|
||||
(templates_dir / file_path).parent.mkdir(exist_ok=True, parents=True)
|
||||
with open(templates_dir / file_path, "w", encoding="utf-8") as f:
|
||||
f.write(template_content)
|
||||
|
||||
with patch("crewai.cli.create_crew.Path") as mock_path:
|
||||
mock_path.return_value = self.test_dir
|
||||
mock_path.side_effect = lambda x: self.test_dir / x if isinstance(x, str) else x
|
||||
|
||||
create_crew("test_crew", skip_provider=True)
|
||||
|
||||
crew_dir = self.test_dir / "test_crew"
|
||||
for root, _, files in os.walk(crew_dir):
|
||||
for file in files:
|
||||
file_path = os.path.join(root, file)
|
||||
with open(file_path, "r", encoding="utf-8") as f:
|
||||
content = f.read()
|
||||
self.assertIn("你好", content, f"Unicode characters not preserved in {file_path}")
|
||||
self.assertIn("🚀", content, f"Emoji not preserved in {file_path}")
|
||||
89
tests/cli/test_encoding.py
Normal file
89
tests/cli/test_encoding.py
Normal file
@@ -0,0 +1,89 @@
|
||||
import os
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
from crewai.cli.provider import fetch_provider_data, read_cache_file
|
||||
from crewai.cli.utils import (
|
||||
copy_template,
|
||||
load_env_vars,
|
||||
tree_find_and_replace,
|
||||
write_env_file,
|
||||
)
|
||||
|
||||
|
||||
class TestEncoding(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.temp_dir = tempfile.TemporaryDirectory()
|
||||
self.test_dir = Path(self.temp_dir.name)
|
||||
|
||||
self.unicode_content = "Hello Unicode: 你好, こんにちは, Привет, مرحبا, 안녕하세요 🚀"
|
||||
self.src_file = self.test_dir / "src_file.txt"
|
||||
self.dst_file = self.test_dir / "dst_file.txt"
|
||||
|
||||
with open(self.src_file, "w", encoding="utf-8") as f:
|
||||
f.write(self.unicode_content)
|
||||
|
||||
def tearDown(self):
|
||||
self.temp_dir.cleanup()
|
||||
|
||||
def test_copy_template_handles_unicode(self):
|
||||
"""Test that copy_template handles Unicode characters properly in all environments."""
|
||||
copy_template(
|
||||
self.src_file,
|
||||
self.dst_file,
|
||||
"test_name",
|
||||
"TestClass",
|
||||
"test_folder"
|
||||
)
|
||||
|
||||
with open(self.dst_file, "r", encoding="utf-8") as f:
|
||||
content = f.read()
|
||||
|
||||
self.assertIn("你好", content)
|
||||
self.assertIn("こんにちは", content)
|
||||
self.assertIn("🚀", content)
|
||||
|
||||
def test_env_vars_handle_unicode(self):
|
||||
"""Test that environment variable functions handle Unicode characters properly."""
|
||||
test_env_path = self.test_dir / ".env"
|
||||
test_env_vars = {
|
||||
"KEY1": "Value with Unicode: 你好",
|
||||
"KEY2": "More Unicode: こんにちは 🚀"
|
||||
}
|
||||
|
||||
write_env_file(self.test_dir, test_env_vars)
|
||||
|
||||
loaded_vars = load_env_vars(self.test_dir)
|
||||
|
||||
self.assertEqual(loaded_vars["KEY1"], "Value with Unicode: 你好")
|
||||
self.assertEqual(loaded_vars["KEY2"], "More Unicode: こんにちは 🚀")
|
||||
|
||||
def test_tree_find_and_replace_handles_unicode(self):
|
||||
"""Test that tree_find_and_replace handles Unicode characters properly."""
|
||||
test_file = self.test_dir / "replace_test.txt"
|
||||
with open(test_file, "w", encoding="utf-8") as f:
|
||||
f.write("Replace this: PLACEHOLDER with Unicode: 你好")
|
||||
|
||||
tree_find_and_replace(self.test_dir, "PLACEHOLDER", "🚀")
|
||||
|
||||
with open(test_file, "r", encoding="utf-8") as f:
|
||||
content = f.read()
|
||||
|
||||
self.assertIn("Replace this: 🚀 with Unicode: 你好", content)
|
||||
|
||||
@patch("crewai.cli.provider.requests.get")
|
||||
def test_provider_functions_handle_unicode(self, mock_get):
|
||||
"""Test that provider data functions handle Unicode properly."""
|
||||
mock_response = unittest.mock.Mock()
|
||||
mock_response.iter_content.return_value = [self.unicode_content.encode("utf-8")]
|
||||
mock_response.headers.get.return_value = str(len(self.unicode_content))
|
||||
mock_get.return_value = mock_response
|
||||
|
||||
cache_file = self.test_dir / "cache.json"
|
||||
with open(cache_file, "w", encoding="utf-8") as f:
|
||||
f.write('{"model": "Unicode test: 你好 🚀"}')
|
||||
|
||||
cache_data = read_cache_file(cache_file)
|
||||
self.assertEqual(cache_data["model"], "Unicode test: 你好 🚀")
|
||||
@@ -10,7 +10,6 @@ import instructor
|
||||
import pydantic_core
|
||||
import pytest
|
||||
|
||||
from crewai.llm import LLM
|
||||
from crewai.agent import Agent
|
||||
from crewai.agents.cache import CacheHandler
|
||||
from crewai.crew import Crew
|
||||
@@ -1124,7 +1123,7 @@ def test_kickoff_for_each_empty_input():
|
||||
assert results == []
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headeruvs=["authorization"])
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_kickoff_for_each_invalid_input():
|
||||
"""Tests if kickoff_for_each raises TypeError for invalid input types."""
|
||||
|
||||
@@ -2829,7 +2828,7 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
|
||||
copy_mock.return_value = crew
|
||||
|
||||
n_iterations = 2
|
||||
crew.test(n_iterations, llm="gpt-4o-mini", inputs={"topic": "AI"})
|
||||
crew.test(n_iterations, openai_model_name="gpt-4o-mini", inputs={"topic": "AI"})
|
||||
|
||||
# Ensure kickoff is called on the copied crew
|
||||
kickoff_mock.assert_has_calls(
|
||||
@@ -2845,32 +2844,6 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
|
||||
]
|
||||
)
|
||||
|
||||
@mock.patch("crewai.crew.CrewEvaluator")
|
||||
@mock.patch("crewai.crew.Crew.copy")
|
||||
@mock.patch("crewai.crew.Crew.kickoff")
|
||||
def test_crew_testing_with_custom_llm(kickoff_mock, copy_mock, crew_evaluator):
|
||||
task = Task(
|
||||
description="Test task",
|
||||
expected_output="Test output",
|
||||
agent=researcher,
|
||||
)
|
||||
crew = Crew(agents=[researcher], tasks=[task])
|
||||
copy_mock.return_value = crew
|
||||
custom_llm = LLM(model="gpt-4")
|
||||
|
||||
crew.test(2, llm=custom_llm, inputs={"topic": "AI"})
|
||||
|
||||
kickoff_mock.assert_has_calls([
|
||||
mock.call(inputs={"topic": "AI"}),
|
||||
mock.call(inputs={"topic": "AI"})
|
||||
])
|
||||
crew_evaluator.assert_has_calls([
|
||||
mock.call(crew, custom_llm),
|
||||
mock.call().set_iteration(1),
|
||||
mock.call().set_iteration(2),
|
||||
mock.call().print_crew_evaluation_result(),
|
||||
])
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_hierarchical_verbose_manager_agent():
|
||||
@@ -3152,4 +3125,4 @@ def test_multimodal_agent_live_image_analysis():
|
||||
# Verify we got a meaningful response
|
||||
assert isinstance(result.raw, str)
|
||||
assert len(result.raw) > 100 # Expecting a detailed analysis
|
||||
assert "error" not in result.raw.lower() # No error messages in response
|
||||
assert "error" not in result.raw.lower() # No error messages in response
|
||||
@@ -2,7 +2,6 @@ from unittest import mock
|
||||
|
||||
import pytest
|
||||
|
||||
from crewai.llm import LLM
|
||||
from crewai.agent import Agent
|
||||
from crewai.crew import Crew
|
||||
from crewai.task import Task
|
||||
@@ -24,7 +23,7 @@ class TestCrewEvaluator:
|
||||
)
|
||||
crew = Crew(agents=[agent], tasks=[task])
|
||||
|
||||
return CrewEvaluator(crew, llm="gpt-4o-mini")
|
||||
return CrewEvaluator(crew, openai_model_name="gpt-4o-mini")
|
||||
|
||||
def test_setup_for_evaluating(self, crew_planner):
|
||||
crew_planner._setup_for_evaluating()
|
||||
@@ -48,25 +47,6 @@ class TestCrewEvaluator:
|
||||
assert agent.verbose is False
|
||||
assert agent.llm.model == "gpt-4o-mini"
|
||||
|
||||
@pytest.mark.parametrize("llm_input,expected_model", [
|
||||
(LLM(model="gpt-4"), "gpt-4"),
|
||||
("gpt-4", "gpt-4"),
|
||||
])
|
||||
def test_evaluator_with_llm_types(self, crew_planner, llm_input, expected_model):
|
||||
evaluator = CrewEvaluator(crew_planner.crew, llm_input)
|
||||
agent = evaluator._evaluator_agent()
|
||||
assert agent.llm.model == expected_model
|
||||
|
||||
def test_evaluator_with_invalid_llm(self, crew_planner):
|
||||
with pytest.raises(ValueError, match="Invalid LLM configuration"):
|
||||
CrewEvaluator(crew_planner.crew, None)
|
||||
|
||||
def test_evaluator_with_string_llm(self, crew_planner):
|
||||
evaluator = CrewEvaluator(crew_planner.crew, "gpt-4")
|
||||
agent = evaluator._evaluator_agent()
|
||||
assert isinstance(agent.llm, LLM)
|
||||
assert agent.llm.model == "gpt-4"
|
||||
|
||||
def test_evaluation_task(self, crew_planner):
|
||||
evaluator_agent = Agent(
|
||||
role="Evaluator Agent",
|
||||
|
||||
Reference in New Issue
Block a user