Merge branch 'main' into fix/embedder-doc

This update includes a note in the documentation instructing users to create a ./knowldge folder. All source files (such as .txt, .pdf, .xlsx, .json) should be placed in this folder for centralized management. This change aims to streamline file organization and improve accessibility across projects.

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>

docs/concepts/knowledge.mdx

@@ -150,6 +150,8 @@ result = crew.kickoff(
 
 Here are examples of how to use different types of knowledge sources:
 
+Note: Please ensure that you create the ./knowldge folder. All source files (e.g., .txt, .pdf, .xlsx, .json) should be placed in this folder for centralized management.
+
 ### Text File Knowledge Source
 ```python
 from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
@@ -460,12 +462,12 @@ class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
             data = response.json()
             articles = data.get('results', [])
 
-            formatted_data = self._format_articles(articles)
+            formatted_data = self.validate_content(articles)
             return {self.api_endpoint: formatted_data}
         except Exception as e:
             raise ValueError(f"Failed to fetch space news: {str(e)}")
 
-    def _format_articles(self, articles: list) -> str:
+    def validate_content(self, articles: list) -> str:
         """Format articles into readable text."""
         formatted = "Space News Articles:\n\n"
         for article in articles:

docs/concepts/llms.mdx

@@ -158,7 +158,11 @@ In this section, you'll find detailed examples that help you select, configure,
 
   <Accordion title="Anthropic">
     ```toml Code
+    # Required
     ANTHROPIC_API_KEY=sk-ant-...
+
+    # Optional
+    ANTHROPIC_API_BASE=<custom-base-url>
     ```
 
     Example usage in your CrewAI project:
@@ -250,6 +254,40 @@ In this section, you'll find detailed examples that help you select, configure,
         model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
     )
     ```
+
+    Before using Amazon Bedrock, make sure you have boto3 installed in your environment
+
+    [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html) is a managed service that provides access to multiple foundation models from top AI companies through a unified API, enabling secure and responsible AI application development.
+
+    | Model                   | Context Window       | Best For                                                          |
+    |-------------------------|----------------------|-------------------------------------------------------------------|
+    | Amazon Nova Pro         | Up to 300k tokens    | High-performance, model balancing accuracy, speed, and cost-effectiveness across diverse tasks. |
+    | Amazon Nova Micro       | Up to 128k tokens    | High-performance, cost-effective text-only model optimized for lowest latency responses. |
+    | Amazon Nova Lite        | Up to 300k tokens    | High-performance, affordable multimodal processing for images, video, and text with real-time capabilities. |
+    | Claude 3.7 Sonnet       | Up to 128k tokens    | High-performance, best for complex reasoning, coding & AI agents |
+    | Claude 3.5 Sonnet v2    | Up to 200k tokens    | State-of-the-art model specialized in software engineering, agentic capabilities, and computer interaction at optimized cost. |
+    | Claude 3.5 Sonnet       | Up to 200k tokens    | High-performance model delivering superior intelligence and reasoning across diverse tasks with optimal speed-cost balance. |
+    | Claude 3.5 Haiku        | Up to 200k tokens    | Fast, compact multimodal model optimized for quick responses and seamless human-like interactions |
+    | Claude 3 Sonnet         | Up to 200k tokens    | Multimodal model balancing intelligence and speed for high-volume deployments. |
+    | Claude 3 Haiku          | Up to 200k tokens    | Compact, high-speed multimodal model optimized for quick responses and natural conversational interactions |
+    | Claude 3 Opus           | Up to 200k tokens    | Most advanced multimodal model excelling at complex tasks with human-like reasoning and superior contextual understanding. |
+    | Claude 2.1              | Up to 200k tokens    | Enhanced version with expanded context window, improved reliability, and reduced hallucinations for long-form and RAG applications |
+    | Claude                  | Up to 100k tokens    | Versatile model excelling in sophisticated dialogue, creative content, and precise instruction following. |
+    | Claude Instant          | Up to 100k tokens    | Fast, cost-effective model for everyday tasks like dialogue, analysis, summarization, and document Q&A |
+    | Llama 3.1 405B Instruct | Up to 128k tokens    | Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks. |
+    | Llama 3.1 70B Instruct  | Up to 128k tokens    | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
+    | Llama 3.1 8B Instruct   | Up to 128k tokens    | Advanced state-of-the-art model with language understanding, superior reasoning, and text generation. |
+    | Llama 3 70B Instruct    | Up to 8k tokens      | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
+    | Llama 3 8B Instruct     | Up to 8k tokens      | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
+    | Titan Text G1 - Lite    | Up to 4k tokens      | Lightweight, cost-effective model optimized for English tasks and fine-tuning with focus on summarization and content generation. |
+    | Titan Text G1 - Express | Up to 8k tokens      | Versatile model for general language tasks, chat, and RAG applications with support for English and 100+ languages. |
+    | Cohere Command          | Up to 4k tokens      | Model specialized in following user commands and delivering practical enterprise solutions. |
+    | Jurassic-2 Mid          | Up to 8,191 tokens   | Cost-effective model balancing quality and affordability for diverse language tasks like Q&A, summarization, and content generation. |
+    | Jurassic-2 Ultra        | Up to 8,191 tokens   | Model for advanced text generation and comprehension, excelling in complex tasks like analysis and content creation. |
+    | Jamba-Instruct          | Up to 256k tokens    | Model with extended context window optimized for cost-effective text generation, summarization, and Q&A. |
+    | Mistral 7B Instruct     | Up to 32k tokens     | This LLM follows instructions, completes requests, and generates creative text. |
+    | Mistral 8x7B Instruct   | Up to 32k tokens     | An MOE LLM that follows instructions, completes requests, and generates creative text. |
+
   </Accordion>
   
   <Accordion title="Amazon SageMaker">

docs/concepts/memory.mdx

@@ -60,7 +60,8 @@ my_crew = Crew(
 ```python Code
 from crewai import Crew, Process
 from crewai.memory import LongTermMemory, ShortTermMemory, EntityMemory
-from crewai.memory.storage import LTMSQLiteStorage, RAGStorage
+from crewai.memory.storage.rag_storage import RAGStorage
+from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
 from typing import List, Optional
 
 # Assemble your crew with memory capabilities
@@ -119,7 +120,7 @@ Example using environment variables:
 import os
 from crewai import Crew
 from crewai.memory import LongTermMemory
-from crewai.memory.storage import LTMSQLiteStorage
+from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
 
 # Configure storage path using environment variable
 storage_path = os.getenv("CREWAI_STORAGE_DIR", "./storage")
@@ -148,7 +149,7 @@ crew = Crew(memory=True)  # Uses default storage locations
 ```python
 from crewai import Crew
 from crewai.memory import LongTermMemory
-from crewai.memory.storage import LTMSQLiteStorage
+from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
 
 # Configure custom storage paths
 crew = Crew(

docs/guides/advanced/customizing-prompts.mdx

@@ -1,4 +1,5 @@
----title: Customizing Prompts
+---
+title: Customizing Prompts
 description: Dive deeper into low-level prompt customization for CrewAI, enabling super custom and complex use cases for different models and languages.
 icon: message-pen
 ---

docs/mint.json

@@ -115,6 +115,7 @@
         "concepts/testing",
         "concepts/cli",
         "concepts/tools",
+        "concepts/event-listener",
         "concepts/langchain-tools",
         "concepts/llamaindex-tools"
       ]

docs/tools/jsonsearchtool.mdx

@@ -7,8 +7,10 @@ icon: file-code
 # `JSONSearchTool`
 
 <Note>
-    The JSONSearchTool is currently in an experimental phase. This means the tool is under active development, and users might encounter unexpected behavior or changes. 
-    We highly encourage feedback on any issues or suggestions for improvements.
+  The JSONSearchTool is currently in an experimental phase. This means the tool
+  is under active development, and users might encounter unexpected behavior or
+  changes. We highly encourage feedback on any issues or suggestions for
+  improvements.
 </Note>
 
 ## Description
@@ -60,7 +62,7 @@ tool = JSONSearchTool(
                 # stream=true,
             },
         },
-        "embedder": {
+        "embedding_model": {
             "provider": "google", # or openai, ollama, ...
             "config": {
                 "model": "models/embedding-001",
@@ -70,4 +72,4 @@ tool = JSONSearchTool(
         },
     }
 )
-```
+```

docs/tools/ragtool.mdx

@@ -8,8 +8,8 @@ icon: vector-square
 
 ## Description
 
-The `RagTool` is designed to answer questions by leveraging the power of Retrieval-Augmented Generation (RAG) through EmbedChain. 
-It provides a dynamic knowledge base that can be queried to retrieve relevant information from various data sources. 
+The `RagTool` is designed to answer questions by leveraging the power of Retrieval-Augmented Generation (RAG) through EmbedChain.
+It provides a dynamic knowledge base that can be queried to retrieve relevant information from various data sources.
 This tool is particularly useful for applications that require access to a vast array of information and need to provide contextually relevant answers.
 
 ## Example
@@ -138,7 +138,7 @@ config = {
             "model": "gpt-4",
         }
     },
-    "embedder": {
+    "embedding_model": {
         "provider": "openai",
         "config": {
             "model": "text-embedding-ada-002"
@@ -151,4 +151,4 @@ rag_tool = RagTool(config=config, summarize=True)
 
 ## Conclusion
 
-The `RagTool` provides a powerful way to create and query knowledge bases from various data sources. By leveraging Retrieval-Augmented Generation, it enables agents to access and retrieve relevant information efficiently, enhancing their ability to provide accurate and contextually appropriate responses. 
+The `RagTool` provides a powerful way to create and query knowledge bases from various data sources. By leveraging Retrieval-Augmented Generation, it enables agents to access and retrieve relevant information efficiently, enhancing their ability to provide accurate and contextually appropriate responses.

src/crewai/cli/templates/flow/pyproject.toml

@@ -10,6 +10,7 @@ dependencies = [
 
 [project.scripts]
 kickoff = "{{folder_name}}.main:kickoff"
+run_crew = "{{folder_name}}.main:kickoff"
 plot = "{{folder_name}}.main:plot"
 
 [build-system]

src/crewai/task.py

@@ -9,7 +9,6 @@ from copy import copy
 from hashlib import md5
 from pathlib import Path
 from typing import (
-    TYPE_CHECKING,
     Any,
     Callable,
     ClassVar,
@@ -20,6 +19,8 @@ from typing import (
     Tuple,
     Type,
     Union,
+    get_args,
+    get_origin,
 )
 
 from pydantic import (
@@ -34,9 +35,6 @@ from pydantic_core import PydanticCustomError
 
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.security import Fingerprint, SecurityConfig
-
-if TYPE_CHECKING:
-    from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.guardrail_result import GuardrailResult
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
@@ -182,15 +180,29 @@ class Task(BaseModel):
         """
         if v is not None:
             sig = inspect.signature(v)
-            if len(sig.parameters) != 1:
+            positional_args = [
+                param
+                for param in sig.parameters.values()
+                if param.default is inspect.Parameter.empty
+            ]
+            if len(positional_args) != 1:
                 raise ValueError("Guardrail function must accept exactly one parameter")
 
             # Check return annotation if present, but don't require it
             return_annotation = sig.return_annotation
             if return_annotation != inspect.Signature.empty:
+
+                return_annotation_args = get_args(return_annotation)
                 if not (
-                    return_annotation == Tuple[bool, Any]
-                    or str(return_annotation) == "Tuple[bool, Any]"
+                    get_origin(return_annotation) is tuple
+                    and len(return_annotation_args) == 2
+                    and return_annotation_args[0] is bool
+                    and (
+                        return_annotation_args[1] is Any
+                        or return_annotation_args[1] is str
+                        or return_annotation_args[1] is TaskOutput
+                        or return_annotation_args[1] == Union[str, TaskOutput]
+                    )
                 ):
                     raise ValueError(
                         "If return type is annotated, it must be Tuple[bool, Any]"
@@ -621,17 +633,8 @@ class Task(BaseModel):
 
     def copy(
         self, agents: List["BaseAgent"], task_mapping: Dict[str, "Task"]
-    ) -> Union["Task", "ConditionalTask"]:
-        """
-        Creates a deep copy of the task while preserving its specific type (Task or ConditionalTask).
-        
-        Args:
-            agents: List of agents to search for the agent by role
-            task_mapping: Dictionary mapping task keys to tasks
-            
-        Returns:
-            Union[Task, ConditionalTask]: A copy of the task maintaining its original type.
-        """
+    ) -> "Task":
+        """Create a deep copy of the Task."""
         exclude = {
             "id",
             "agent",
@@ -654,9 +657,7 @@ class Task(BaseModel):
         cloned_agent = get_agent_by_role(self.agent.role) if self.agent else None
         cloned_tools = copy(self.tools) if self.tools else []
 
-        # Use the actual class of the instance being copied, not just Task
-        task_class = self.__class__
-        copied_task = task_class(
+        copied_task = Task(
             **copied_data,
             context=cloned_context,
             agent=cloned_agent,

src/crewai/tasks/conditional_task.py

@@ -1,12 +1,8 @@
-from typing import TYPE_CHECKING, Any, Callable
+from typing import Any, Callable
 
 from pydantic import Field
 
-if TYPE_CHECKING:
-    from crewai.task import Task
-else:
-    # Import the base class at runtime
-    from crewai.task import Task
+from crewai.task import Task
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 

src/crewai/utilities/events/crewai_event_bus.py

@@ -67,15 +67,12 @@ class CrewAIEventsBus:
             source: The object emitting the event
             event: The event instance to emit
         """
-        event_type = type(event)
-        if event_type in self._handlers:
-            for handler in self._handlers[event_type]:
-                handler(source, event)
-        self._signal.send(source, event=event)
+        for event_type, handlers in self._handlers.items():
+            if isinstance(event, event_type):
+                for handler in handlers:
+                    handler(source, event)
 
-    def clear_handlers(self) -> None:
-        """Clear all registered event handlers - useful for testing"""
-        self._handlers.clear()
+        self._signal.send(source, event=event)
 
     def register_handler(
         self, event_type: Type[EventTypes], handler: Callable[[Any, EventTypes], None]

src/crewai/utilities/events/flow_events.py

@@ -1,6 +1,6 @@
 from typing import Any, Dict, Optional, Union
 
-from pydantic import BaseModel
+from pydantic import BaseModel, ConfigDict
 
 from .base_events import CrewEvent
 
@@ -52,9 +52,11 @@ class MethodExecutionFailedEvent(FlowEvent):
 
     flow_name: str
     method_name: str
-    error: Any
+    error: Exception
     type: str = "method_execution_failed"
 
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
 
 class FlowFinishedEvent(FlowEvent):
     """Event emitted when a flow completes execution"""

tests/task_test.py

@@ -3,6 +3,8 @@
 import hashlib
 import json
 import os
+from functools import partial
+from typing import Tuple, Union
 from unittest.mock import MagicMock, patch
 
 import pytest
@@ -215,6 +217,75 @@ def test_multiple_output_type_error():
         )
 
 
+def test_guardrail_type_error():
+    desc = "Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting."
+    expected_output = "Bullet point list of 5 interesting ideas."
+    # Lambda function
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=lambda x: (True, x),
+    )
+
+    # Function
+    def guardrail_fn(x: TaskOutput) -> tuple[bool, TaskOutput]:
+        return (True, x)
+
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=guardrail_fn,
+    )
+
+    class Object:
+        def guardrail_fn(self, x: TaskOutput) -> tuple[bool, TaskOutput]:
+            return (True, x)
+
+        @classmethod
+        def guardrail_class_fn(cls, x: TaskOutput) -> tuple[bool, str]:
+            return (True, x)
+
+        @staticmethod
+        def guardrail_static_fn(x: TaskOutput) -> tuple[bool, Union[str, TaskOutput]]:
+            return (True, x)
+
+    obj = Object()
+    # Method
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=obj.guardrail_fn,
+    )
+    # Class method
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=Object.guardrail_class_fn,
+    )
+    # Static method
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=Object.guardrail_static_fn,
+    )
+
+    def error_fn(x: TaskOutput, y: bool) -> Tuple[bool, TaskOutput]:
+        return (y, x)
+
+    Task(
+        description=desc,
+        expected_output=expected_output,
+        guardrail=partial(error_fn, y=True),
+    )
+
+    with pytest.raises(ValidationError):
+        Task(
+            description=desc,
+            expected_output=expected_output,
+            guardrail=error_fn,
+        )
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_output_pydantic_sequential():
     class ScoreOutput(BaseModel):

tests/test_conditional_task_copy.py

@@ -1,104 +0,0 @@
-import pytest
-
-from crewai import Agent, Crew, Task
-from crewai.tasks.conditional_task import ConditionalTask
-from crewai.tasks.task_output import TaskOutput
-
-
-@pytest.fixture
-def test_agent():
-    """Fixture for creating a test agent."""
-    return Agent(
-        role="Researcher",
-        goal="Research topics",
-        backstory="You are a researcher."
-    )
-
-@pytest.fixture
-def test_task(test_agent):
-    """Fixture for creating a regular task."""
-    return Task(
-        description="Research topic A",
-        expected_output="Research results for topic A",
-        agent=test_agent
-    )
-
-@pytest.fixture
-def test_conditional_task(test_agent):
-    """Fixture for creating a conditional task."""
-    return ConditionalTask(
-        description="Research topic B if topic A was successful",
-        expected_output="Research results for topic B",
-        agent=test_agent,
-        condition=lambda output: "success" in output.raw.lower()
-    )
-
-@pytest.fixture
-def test_crew(test_agent, test_task, test_conditional_task):
-    """Fixture for creating a crew with both regular and conditional tasks."""
-    return Crew(
-        agents=[test_agent],
-        tasks=[test_task, test_conditional_task]
-    )
-
-
-def test_conditional_task_preserved_in_copy(test_crew):
-    """Test that ConditionalTask objects are preserved when copying a Crew."""
-    # Create a copy of the crew
-    crew_copy = test_crew.copy()
-    
-    # Check that the conditional task is still a ConditionalTask in the copied crew
-    assert isinstance(crew_copy.tasks[1], ConditionalTask)
-    assert hasattr(crew_copy.tasks[1], "should_execute")
-    
-def test_conditional_task_preserved_in_kickoff_for_each(test_crew, test_agent):
-    """Test that ConditionalTask objects are preserved when using kickoff_for_each."""
-    from unittest.mock import patch
-    
-    # Mock the kickoff method to avoid actual execution
-    with patch.object(Crew, "kickoff") as mock_kickoff:
-        # Set up the mock to return a TaskOutput
-        mock_output = TaskOutput(
-            description="Mock task output",
-            raw="Success with topic",
-            agent=test_agent.role
-        )
-        mock_kickoff.return_value = mock_output
-        
-        # Call kickoff_for_each with test inputs
-        inputs = [{"topic": "test1"}, {"topic": "test2"}]
-        test_crew.kickoff_for_each(inputs=inputs)
-        
-        # Verify the mock was called with the expected inputs
-        assert mock_kickoff.call_count == len(inputs)
-        
-        # Create a copy of the crew to verify the type preservation
-        # (since we can't directly access the crews created inside kickoff_for_each)
-        crew_copy = test_crew.copy()
-        assert isinstance(crew_copy.tasks[1], ConditionalTask)
-
-
-def test_conditional_task_copy_with_none_values(test_agent, test_task):
-    """Test that ConditionalTask objects are preserved when copying with optional fields."""
-    # Create a conditional task with optional fields
-    conditional_task = ConditionalTask(
-        description="Research topic B if topic A was successful",
-        expected_output="Research results for topic B",  # Required field
-        agent=test_agent,
-        condition=lambda output: "success" in output.raw.lower(),
-        context=None  # Optional field that can be None
-    )
-    
-    # Create a crew with both a regular task and the conditional task
-    crew = Crew(
-        agents=[test_agent],
-        tasks=[test_task, conditional_task]
-    )
-    
-    # Create a copy of the crew
-    crew_copy = crew.copy()
-    
-    # Check that the conditional task is still a ConditionalTask in the copied crew
-    assert isinstance(crew_copy.tasks[1], ConditionalTask)
-    assert hasattr(crew_copy.tasks[1], "should_execute")
-    assert crew_copy.tasks[1].context is None  # Verify None value is preserved

tests/utilities/events/test_crewai_event_bus.py

@@ -0,0 +1,34 @@
+from unittest.mock import Mock
+
+from crewai.utilities.events.base_events import CrewEvent
+from crewai.utilities.events.crewai_event_bus import crewai_event_bus
+
+
+class TestEvent(CrewEvent):
+    pass
+
+
+def test_specific_event_handler():
+    mock_handler = Mock()
+
+    @crewai_event_bus.on(TestEvent)
+    def handler(source, event):
+        mock_handler(source, event)
+
+    event = TestEvent(type="test_event")
+    crewai_event_bus.emit("source_object", event)
+
+    mock_handler.assert_called_once_with("source_object", event)
+
+
+def test_wildcard_event_handler():
+    mock_handler = Mock()
+
+    @crewai_event_bus.on(CrewEvent)
+    def handler(source, event):
+        mock_handler(source, event)
+
+    event = TestEvent(type="test_event")
+    crewai_event_bus.emit("source_object", event)
+
+    mock_handler.assert_called_once_with("source_object", event)