andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-03 00:02:36 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix llm guardrail import and docs

Browse Source
This commit is contained in:
João Moura
2025-05-22 21:47:23 -07:00
parent 2d6deee753
commit beddc72189
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/concepts/tasks.mdx
View File

@@ -380,7 +380,7 @@ The `LLMGuardrail` class offers a robust mechanism for validating task outputs.
1. **Structured Error Responses**: 1. **Structured Error Responses**:
```python Code ```python Code
from crewai import TaskOutput from crewai import TaskOutput, LLMGuardrail
def validate_with_context(result: TaskOutput) -> Tuple[bool, Any]: def validate_with_context(result: TaskOutput) -> Tuple[bool, Any]:
try: try:

2
src/crewai/__init__.py
View File

@@ -9,6 +9,7 @@ from crewai.llm import LLM
from crewai.llms.base_llm import BaseLLM from crewai.llms.base_llm import BaseLLM
from crewai.process import Process from crewai.process import Process
from crewai.task import Task from crewai.task import Task
from crewai.tasks.llm_guardrail import LLMGuardrail
from crewai.tasks.task_output import TaskOutput from crewai.tasks.task_output import TaskOutput
warnings.filterwarnings( warnings.filterwarnings(
@@ -29,4 +30,5 @@ __all__ = [
"Flow", "Flow",
"Knowledge", "Knowledge",
"TaskOutput", "TaskOutput",
"LLMGuardrail",
] ]