Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

fix llm guardrail import and docs

João Mourabeddc7218900
diff --git a/docs/concepts/tasks.mdx b/docs/concepts/tasks.mdx
index 63b95fecb..0952203d4 100644
--- a/docs/concepts/tasks.mdx
+++ b/docs/concepts/tasks.mdx
@@ -369,7 +369,7 @@ blog_task = Task(
- Type hints are recommended but optional
2. **Return Values**:
- - On success: it returns a tuple of `(bool, Any)`. For example: `(True, validated_result)`
+ - On success: it returns a tuple of `(bool, Any)`. For example: `(True, validated_result)`
- On Failure: it returns a tuple of `(bool, str)`. For example: `(False, "Error message explain the failure")`
### LLMGuardrail
@@ -380,7 +380,7 @@ The `LLMGuardrail` class offers a robust mechanism for validating task outputs.
1. **Structured Error Responses**:
```python Code
-from crewai import TaskOutput
+from crewai import TaskOutput, LLMGuardrail
def validate_with_context(result: TaskOutput) -> Tuple[bool, Any]:
try:
diff --git a/src/crewai/__init__.py b/src/crewai/__init__.py
index c256db73e..3501a1a1b 100644
--- a/src/crewai/__init__.py
+++ b/src/crewai/__init__.py
@@ -9,6 +9,7 @@ from crewai.llm import LLM
from crewai.llms.base_llm import BaseLLM
from crewai.process import Process
from crewai.task import Task
+from crewai.tasks.llm_guardrail import LLMGuardrail
from crewai.tasks.task_output import TaskOutput
warnings.filterwarnings(
@@ -29,4 +30,5 @@ __all__ = [
"Flow",
"Knowledge",
"TaskOutput",
+ "LLMGuardrail",
]