andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-15 02:58:30 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge branch 'main' into brandon/eng-266-conversation-crew-v1

Browse Source
This commit is contained in:
Brandon Hancock
2025-01-03 15:24:19 -05:00
parent 9e5d4972b9 30bd79390a
commit 104e8bc167
10 changed files with 596 additions and 205 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
src/crewai/knowledge/source/crew_docling_source.py
View File

@@ -2,11 +2,16 @@ from pathlib import Path
from typing import Iterator, List, Optional, Union
from urllib.parse import urlparse
from docling.datamodel.base_models import InputFormat
from docling.document_converter import DocumentConverter
from docling.exceptions import ConversionError
from docling_core.transforms.chunker.hierarchical_chunker import HierarchicalChunker
from docling_core.types.doc.document import DoclingDocument
try:
from docling.datamodel.base_models import InputFormat
from docling.document_converter import DocumentConverter
from docling.exceptions import ConversionError
from docling_core.transforms.chunker.hierarchical_chunker import HierarchicalChunker
from docling_core.types.doc.document import DoclingDocument
DOCLING_AVAILABLE = True
except ImportError:
DOCLING_AVAILABLE = False
from pydantic import Field
from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
@@ -19,6 +24,14 @@ class CrewDoclingSource(BaseKnowledgeSource):
This will auto support PDF, DOCX, and TXT, XLSX, Images, and HTML files without any additional dependencies and follows the docling package as the source of truth.
"""
def __init__(self, *args, **kwargs):
if not DOCLING_AVAILABLE:
raise ImportError(
"The docling package is required to use CrewDoclingSource. "
"Please install it using: uv add docling"
)
super().__init__(*args, **kwargs)
_logger: Logger = Logger(verbose=True)
file_path: Optional[List[Union[Path, str]]] = Field(default=None)

2
src/crewai/project/crew_base.py
View File

@@ -218,5 +218,5 @@ def CrewBase(cls: T) -> T:
# Include base class (qual)name in the wrapper class (qual)name.
WrappedClass.__name__ = CrewBase.__name__ + "(" + cls.__name__ + ")"
WrappedClass.__qualname__ = CrewBase.__qualname__ + "(" + cls.__name__ + ")"
return cast(T, WrappedClass)

62
src/crewai/task.py
View File

@@ -136,6 +136,13 @@ class Task(BaseModel):
)
retry_count: int = Field(default=0, description="Current number of retries")
start_time: Optional[datetime.datetime] = Field(
default=None, description="Start time of the task execution"
)
end_time: Optional[datetime.datetime] = Field(
default=None, description="End time of the task execution"
)
@field_validator("guardrail")
@classmethod
def validate_guardrail_function(cls, v: Optional[Callable]) -> Optional[Callable]:
@@ -184,7 +191,6 @@ class Task(BaseModel):
_original_expected_output: Optional[str] = PrivateAttr(default=None)
_original_output_file: Optional[str] = PrivateAttr(default=None)
_thread: Optional[threading.Thread] = PrivateAttr(default=None)
_execution_time: Optional[float] = PrivateAttr(default=None)
@model_validator(mode="before")
@classmethod
@@ -209,25 +215,19 @@ class Task(BaseModel):
"may_not_set_field", "This field is not to be set by the user.", {}
)
def _set_start_execution_time(self) -> float:
return datetime.datetime.now().timestamp()
def _set_end_execution_time(self, start_time: float) -> None:
self._execution_time = datetime.datetime.now().timestamp() - start_time
@field_validator("output_file")
@classmethod
def output_file_validation(cls, value: Optional[str]) -> Optional[str]:
"""Validate the output file path.
Args:
value: The output file path to validate. Can be None or a string.
If the path contains template variables (e.g. {var}), leading slashes are preserved.
For regular paths, leading slashes are stripped.
Returns:
The validated and potentially modified path, or None if no path was provided.
Raises:
ValueError: If the path contains invalid characters, path traversal attempts,
or other security concerns.
@@ -237,18 +237,24 @@ class Task(BaseModel):
# Basic security checks
if ".." in value:
raise ValueError("Path traversal attempts are not allowed in output_file paths")
raise ValueError(
"Path traversal attempts are not allowed in output_file paths"
)
# Check for shell expansion first
if value.startswith('~') or value.startswith('$'):
raise ValueError("Shell expansion characters are not allowed in output_file paths")
if value.startswith("~") or value.startswith("$"):
raise ValueError(
"Shell expansion characters are not allowed in output_file paths"
)
# Then check other shell special characters
if any(char in value for char in ['|', '>', '<', '&', ';']):
raise ValueError("Shell special characters are not allowed in output_file paths")
if any(char in value for char in ["|", ">", "<", "&", ";"]):
raise ValueError(
"Shell special characters are not allowed in output_file paths"
)
# Don't strip leading slash if it's a template path with variables
if "{" in value or "}" in value:
if "{" in value or "}" in value:
# Validate template variable format
template_vars = [part.split("}")[0] for part in value.split("{")[1:]]
for var in template_vars:
@@ -305,6 +311,12 @@ class Task(BaseModel):
return md5("|".join(source).encode(), usedforsecurity=False).hexdigest()
@property
def execution_duration(self) -> float | None:
if not self.start_time or not self.end_time:
return None
return (self.end_time - self.start_time).total_seconds()
def execute_async(
self,
agent: BaseAgent | None = None,
@@ -345,7 +357,7 @@ class Task(BaseModel):
f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
)
start_time = self._set_start_execution_time()
self.start_time = datetime.datetime.now()
self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
self.prompt_context = context
@@ -404,8 +416,8 @@ class Task(BaseModel):
task_output = guardrail_result.result
self.output = task_output
self.end_time = datetime.datetime.now()
self._set_end_execution_time(start_time)
if self.callback:
self.callback(self.output)
@@ -417,7 +429,9 @@ class Task(BaseModel):
content = (
json_output
if json_output
else pydantic_output.model_dump_json() if pydantic_output else result
else pydantic_output.model_dump_json()
if pydantic_output
else result
)
self._save_file(content)
@@ -445,7 +459,7 @@ class Task(BaseModel):
Args:
inputs: Dictionary mapping template variables to their values.
Supported value types are strings, integers, and floats.
Raises:
ValueError: If a required template variable is missing from inputs.
"""
@@ -462,7 +476,9 @@ class Task(BaseModel):
try:
self.description = self._original_description.format(**inputs)
except KeyError as e:
raise ValueError(f"Missing required template variable '{e.args[0]}' in description") from e
raise ValueError(
f"Missing required template variable '{e.args[0]}' in description"
) from e
except ValueError as e:
raise ValueError(f"Error interpolating description: {str(e)}") from e

2
src/crewai/tools/tool_usage.py
View File

@@ -169,7 +169,7 @@ class ToolUsage:
if calling.arguments:
try:
acceptable_args = tool.args_schema.schema()["properties"].keys() # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "schema"
acceptable_args = tool.args_schema.model_json_schema()["properties"].keys() # type: ignore
arguments = {
k: v
for k, v in calling.arguments.items()

4
src/crewai/utilities/evaluators/crew_evaluator_handler.py
View File

@@ -180,12 +180,12 @@ class CrewEvaluator:
self._test_result_span = self._telemetry.individual_test_result_span(
self.crew,
evaluation_result.pydantic.quality,
current_task._execution_time,
current_task.execution_duration,
self.openai_model_name,
)
self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
self.run_execution_times[self.iteration].append(
current_task._execution_time
current_task.execution_duration
)
else:
raise ValueError("Evaluation result is not in the expected format")