Merge branch 'main' into bugfix/restrict-python-version-compatibility

* drop 3.13

* revert

* Drop test cassette that was causing error

* trying to fix failing test

* adding thiago changes

* resolve final tests

* Drop skip

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -65,7 +65,6 @@ body:
         - '3.10'
         - '3.11'
         - '3.12'
-        - '3.13'
     validations:
       required: true
   - type: input
@@ -113,4 +112,4 @@ body:
       label: Additional context
       description: Add any other context about the problem here.
     validations:
-      required: true
+      required: true

.github/workflows/tests.yml

@@ -23,7 +23,7 @@ jobs:
 
 
       - name: Set up Python
-        run: uv python install 3.11.9
+        run: uv python install 3.12.8
 
       - name: Install the project
         run: uv sync --dev --all-extras

README.md

@@ -44,7 +44,7 @@ To get started with CrewAI, follow these simple steps:
 
 ### 1. Installation
 
-Ensure you have Python >=3.10 <=3.13 installed on your system. CrewAI uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+Ensure you have Python >=3.10 <=3.12 installed on your system. CrewAI uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
 
 First, install CrewAI:
 

docs/concepts/cli.mdx

@@ -28,20 +28,19 @@ crewai [COMMAND] [OPTIONS] [ARGUMENTS]
 
 ### 1. Create
 
-Create a new crew or pipeline.
+Create a new crew or flow.
 
 ```shell
 crewai create [OPTIONS] TYPE NAME
 ```
 
-- `TYPE`: Choose between "crew" or "pipeline"
-- `NAME`: Name of the crew or pipeline
-- `--router`: (Optional) Create a pipeline with router functionality
+- `TYPE`: Choose between "crew" or "flow"
+- `NAME`: Name of the crew or flow
 
 Example:
 ```shell
 crewai create crew my_new_crew
-crewai create pipeline my_new_pipeline --router
+crewai create flow my_new_flow
 ```
 
 ### 2. Version

docs/concepts/crews.mdx

@@ -41,6 +41,155 @@ A crew in crewAI represents a collaborative group of agents working together to
 **Crew Max RPM**: The `max_rpm` attribute sets the maximum number of requests per minute the crew can perform to avoid rate limits and will override individual agents' `max_rpm` settings if you set it.
 </Tip>
 
+## Creating Crews
+
+There are two ways to create crews in CrewAI: using **YAML configuration (recommended)** or defining them **directly in code**.
+
+### YAML Configuration (Recommended)
+
+Using YAML configuration provides a cleaner, more maintainable way to define crews and is consistent with how agents and tasks are defined in CrewAI projects.
+
+After creating your CrewAI project as outlined in the [Installation](/installation) section, you can define your crew in a class that inherits from `CrewBase` and uses decorators to define agents, tasks, and the crew itself.
+
+#### Example Crew Class with Decorators
+
+```python code
+from crewai import Agent, Crew, Task, Process
+from crewai.project import CrewBase, agent, task, crew, before_kickoff, after_kickoff
+
+
+@CrewBase
+class YourCrewName:
+    """Description of your crew"""
+
+    # Paths to your YAML configuration files
+    # To see an example agent and task defined in YAML, checkout the following:
+    # - Task: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
+    # - Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
+    agents_config = 'config/agents.yaml' 
+    tasks_config = 'config/tasks.yaml' 
+
+    @before_kickoff
+    def prepare_inputs(self, inputs):
+        # Modify inputs before the crew starts
+        inputs['additional_data'] = "Some extra information"
+        return inputs
+
+    @after_kickoff
+    def process_output(self, output):
+        # Modify output after the crew finishes
+        output.raw += "\nProcessed after kickoff."
+        return output
+
+    @agent
+    def agent_one(self) -> Agent:
+        return Agent(
+            config=self.agents_config['agent_one'],
+            verbose=True
+        )
+
+    @agent
+    def agent_two(self) -> Agent:
+        return Agent(
+            config=self.agents_config['agent_two'],
+            verbose=True
+        )
+
+    @task
+    def task_one(self) -> Task:
+        return Task(
+            config=self.tasks_config['task_one']
+        )
+
+    @task
+    def task_two(self) -> Task:
+        return Task(
+            config=self.tasks_config['task_two']
+        )
+
+    @crew
+    def crew(self) -> Crew:
+        return Crew(
+            agents=self.agents,  # Automatically collected by the @agent decorator
+            tasks=self.tasks,    # Automatically collected by the @task decorator. 
+            process=Process.sequential,
+            verbose=True,
+        )
+```
+
+<Note>
+Tasks will be executed in the order they are defined.
+</Note>
+
+The `CrewBase` class, along with these decorators, automates the collection of agents and tasks, reducing the need for manual management.
+
+#### Decorators overview from `annotations.py`
+
+CrewAI provides several decorators in the `annotations.py` file that are used to mark methods within your crew class for special handling:
+
+- `@CrewBase`: Marks the class as a crew base class.
+- `@agent`: Denotes a method that returns an `Agent` object.
+- `@task`: Denotes a method that returns a `Task` object.
+- `@crew`: Denotes the method that returns the `Crew` object.
+- `@before_kickoff`: (Optional) Marks a method to be executed before the crew starts.
+- `@after_kickoff`: (Optional) Marks a method to be executed after the crew finishes.
+
+These decorators help in organizing your crew's structure and automatically collecting agents and tasks without manually listing them.
+
+### Direct Code Definition (Alternative)
+
+Alternatively, you can define the crew directly in code without using YAML configuration files.
+
+```python code
+from crewai import Agent, Crew, Task, Process
+from crewai_tools import YourCustomTool
+
+class YourCrewName:
+    def agent_one(self) -> Agent:
+        return Agent(
+            role="Data Analyst",
+            goal="Analyze data trends in the market",
+            backstory="An experienced data analyst with a background in economics",
+            verbose=True,
+            tools=[YourCustomTool()]
+        )
+
+    def agent_two(self) -> Agent:
+        return Agent(
+            role="Market Researcher",
+            goal="Gather information on market dynamics",
+            backstory="A diligent researcher with a keen eye for detail",
+            verbose=True
+        )
+
+    def task_one(self) -> Task:
+        return Task(
+            description="Collect recent market data and identify trends.",
+            expected_output="A report summarizing key trends in the market.",
+            agent=self.agent_one()
+        )
+
+    def task_two(self) -> Task:
+        return Task(
+            description="Research factors affecting market dynamics.",
+            expected_output="An analysis of factors influencing the market.",
+            agent=self.agent_two()
+        )
+
+    def crew(self) -> Crew:
+        return Crew(
+            agents=[self.agent_one(), self.agent_two()],
+            tasks=[self.task_one(), self.task_two()],
+            process=Process.sequential,
+            verbose=True
+        )
+```
+
+In this example:
+
+- Agents and tasks are defined directly within the class without decorators.
+- We manually create and manage the list of agents and tasks.
+- This approach provides more control but can be less maintainable for larger projects.
 
 ## Crew Output
 
@@ -188,4 +337,4 @@ Then, to replay from a specific task, use:
 crewai replay -t <task_id>
 ```
 
-These commands let you replay from your latest kickoff tasks, still retaining context from previously executed tasks.
+These commands let you replay from your latest kickoff tasks, still retaining context from previously executed tasks.

docs/concepts/knowledge.mdx

@@ -1,6 +1,6 @@
 ---
 title: Knowledge
-description: Understand what knowledge is in CrewAI and how to effectively use it.
+description: What is knowledge in CrewAI and how to use it.
 icon: book
 ---
 
@@ -8,7 +8,8 @@ icon: book
 
 ## What is Knowledge?
 
-Knowledge in CrewAI is a powerful system that allows AI agents to access and utilize external information sources during their tasks. Think of it as giving your agents a reference library they can consult while working.
+Knowledge in CrewAI is a powerful system that allows AI agents to access and utilize external information sources during their tasks.
+Think of it as giving your agents a reference library they can consult while working.
 
 <Info>
   Key benefits of using Knowledge:
@@ -37,151 +38,267 @@ CrewAI supports various types of knowledge sources out of the box:
 
 ## Quick Start
 
-Here's a simple example using string-based knowledge:
+Here's an example using string-based knowledge:
 
-```python
-from crewai import Agent, Task, Crew
-from crewai.knowledge import StringKnowledgeSource
+```python Code
+from crewai import Agent, Task, Crew, Process, LLM
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 
-# 1. Create a knowledge source
-product_info = StringKnowledgeSource(
-    content="""Our product X1000 has the following features:
-    - 10-hour battery life
-    - Water-resistant
-    - Available in black and silver
-    Price: $299.99""",
-    metadata={"category": "product"}
+# Create a knowledge source
+content = "Users name is John. He is 30 years old and lives in San Francisco."
+string_source = StringKnowledgeSource(
+    content=content,
 )
 
-# 2. Create an agent with knowledge
-sales_agent = Agent(
-    role="Sales Representative",
-    goal="Accurately answer customer questions about products",
-    backstory="Expert in product features and customer service",
-    knowledge_sources=[product_info]  # Attach knowledge to agent
+# Create an LLM with a temperature of 0 to ensure deterministic outputs
+llm = LLM(model="gpt-4o-mini", temperature=0)
+
+# Create an agent with the knowledge store
+agent = Agent(
+    role="About User",
+    goal="You know everything about the user.",
+    backstory="""You are a master at understanding people and their preferences.""",
+    verbose=True,
+    allow_delegation=False,
+    llm=llm,
+)
+task = Task(
+    description="Answer the following questions about the user: {question}",
+    expected_output="An answer to the question.",
+    agent=agent,
 )
 
-# 3. Create a task
-answer_task = Task(
-    description="Answer: What colors is the X1000 available in and how much does it cost?",
-    agent=sales_agent
-)
-
-# 4. Create and run the crew
 crew = Crew(
-    agents=[sales_agent],
-    tasks=[answer_task]
+    agents=[agent],
+    tasks=[task],
+    verbose=True,
+    process=Process.sequential,
+    knowledge_sources=[string_source], # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
 )
 
-result = crew.kickoff()
+result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})
 ```
 
 ## Knowledge Configuration
 
-### Collection Names
-
-Knowledge sources are organized into collections for better management:
-
-```python
-# Create knowledge sources with specific collections
-tech_specs = StringKnowledgeSource(
-    content="Technical specifications...",
-    collection_name="product_tech_specs"
-)
-
-pricing_info = StringKnowledgeSource(
-    content="Pricing information...",
-    collection_name="product_pricing"
-)
-```
-
-### Metadata and Filtering
-
-Add metadata to organize and filter knowledge:
-
-```python
-knowledge_source = StringKnowledgeSource(
-    content="Product details...",
-    metadata={
-        "category": "electronics",
-        "product_line": "premium",
-        "last_updated": "2024-03"
-    }
-)
-```
-
 ### Chunking Configuration
 
-Control how your content is split for processing:
+Control how content is split for processing by setting the chunk size and overlap.
 
-```python
-knowledge_source = PDFKnowledgeSource(
-    file_path="product_manual.pdf",
-    chunk_size=2000,     # Characters per chunk
-    chunk_overlap=200    # Overlap between chunks
+```python Code
+knowledge_source = StringKnowledgeSource(
+    content="Long content...",
+    chunk_size=4000,     # Characters per chunk (default)
+    chunk_overlap=200    # Overlap between chunks (default)
 )
 ```
 
-## Advanced Usage
+## Embedder Configuration
 
-### Custom Knowledge Sources
+You can also configure the embedder for the knowledge store. This is useful if you want to use a different embedder for the knowledge store than the one used for the agents.
 
-Create your own knowledge source by extending the base class:
-
-```python
-from crewai.knowledge.source import BaseKnowledgeSource
-
-class APIKnowledgeSource(BaseKnowledgeSource):
-    def __init__(self, api_endpoint: str, **kwargs):
-        super().__init__(**kwargs)
-        self.api_endpoint = api_endpoint
-    
-    def load_content(self):
-        # Implement API data fetching
-        response = requests.get(self.api_endpoint)
-        return response.json()
-    
-    def add(self):
-        content = self.load_content()
-        # Process and store content
-        self.save_documents({"source": "api"})
-```
-
-### Embedder Configuration
-
-Customize the embedding process:
-
-```python
+```python Code
+...
+string_source = StringKnowledgeSource(
+    content="Users name is John. He is 30 years old and lives in San Francisco.",
+)
 crew = Crew(
-    agents=[agent],
-    tasks=[task],
-    knowledge_sources=[source],
+    ...
+    knowledge_sources=[string_source],
     embedder={
-        "provider": "ollama",
-        "config": {"model": "nomic-embed-text:latest"},
-    }
+        "provider": "openai",
+        "config": {"model": "text-embedding-3-small"},
+    },
 )
 ```
 
-### Referencing Sources
+## Clearing Knowledge
 
-You can reference knowledge sources by their collection name or metadata.
+If you need to clear the knowledge stored in CrewAI, you can use the `crewai reset-memories` command with the `--knowledge` option.
 
-* Add a directory to your crew project called `knowledge`:
-* File paths in knowledge can be referenced relative to the `knowledge` directory.
+```bash Command
+crewai reset-memories --knowledge
+```
 
-Example:
-A file inside the `knowledge` directory called `example.txt` can be referenced as `example.txt`.
+This is useful when you've updated your knowledge sources and want to ensure that the agents are using the most recent information.
+
+## Custom Knowledge Sources
+
+CrewAI allows you to create custom knowledge sources for any type of data by extending the `BaseKnowledgeSource` class. Let's create a practical example that fetches and processes space news articles.
+
+#### Space News Knowledge Source Example
+
+<CodeGroup>
+
+```python Code
+from crewai import Agent, Task, Crew, Process, LLM
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+import requests
+from datetime import datetime
+from typing import Dict, Any
+from pydantic import BaseModel, Field
+
+class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
+    """Knowledge source that fetches data from Space News API."""
+
+    api_endpoint: str = Field(description="API endpoint URL")
+    limit: int = Field(default=10, description="Number of articles to fetch")
+
+    def load_content(self) -> Dict[Any, str]:
+        """Fetch and format space news articles."""
+        try:
+            response = requests.get(
+                f"{self.api_endpoint}?limit={self.limit}"
+            )
+            response.raise_for_status()
+
+            data = response.json()
+            articles = data.get('results', [])
+
+            formatted_data = self._format_articles(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:
+        """Format articles into readable text."""
+        formatted = "Space News Articles:\n\n"
+        for article in articles:
+            formatted += f"""
+                Title: {article['title']}
+                Published: {article['published_at']}
+                Summary: {article['summary']}
+                News Site: {article['news_site']}
+                URL: {article['url']}
+                -------------------"""
+        return formatted
+
+    def add(self) -> None:
+        """Process and store the articles."""
+        content = self.load_content()
+        for _, text in content.items():
+            chunks = self._chunk_text(text)
+            self.chunks.extend(chunks)
+
+        self._save_documents()
+
+# Create knowledge source
+recent_news = SpaceNewsKnowledgeSource(
+    api_endpoint="https://api.spaceflightnewsapi.net/v4/articles",
+    limit=10,
+)
+
+# Create specialized agent
+space_analyst = Agent(
+    role="Space News Analyst",
+    goal="Answer questions about space news accurately and comprehensively",
+    backstory="""You are a space industry analyst with expertise in space exploration,
+    satellite technology, and space industry trends. You excel at answering questions
+    about space news and providing detailed, accurate information.""",
+    knowledge_sources=[recent_news],
+    llm=LLM(model="gpt-4", temperature=0.0)
+)
+
+# Create task that handles user questions
+analysis_task = Task(
+    description="Answer this question about space news: {user_question}",
+    expected_output="A detailed answer based on the recent space news articles",
+    agent=space_analyst
+)
+
+# Create and run the crew
+crew = Crew(
+    agents=[space_analyst],
+    tasks=[analysis_task],
+    verbose=True,
+    process=Process.sequential
+)
+
+# Example usage
+result = crew.kickoff(
+    inputs={"user_question": "What are the latest developments in space exploration?"}
+)
+```
+
+```output Output
+# Agent: Space News Analyst
+## Task: Answer this question about space news: What are the latest developments in space exploration?
+
+
+# Agent: Space News Analyst
+## Final Answer:
+The latest developments in space exploration, based on recent space news articles, include the following:
+
+1. SpaceX has received the final regulatory approvals to proceed with the second integrated Starship/Super Heavy launch, scheduled for as soon as the morning of Nov. 17, 2023. This is a significant step in SpaceX's ambitious plans for space exploration and colonization. [Source: SpaceNews](https://spacenews.com/starship-cleared-for-nov-17-launch/)
+
+2. SpaceX has also informed the US Federal Communications Commission (FCC) that it plans to begin launching its first next-generation Starlink Gen2 satellites. This represents a major upgrade to the Starlink satellite internet service, which aims to provide high-speed internet access worldwide. [Source: Teslarati](https://www.teslarati.com/spacex-first-starlink-gen2-satellite-launch-2022/)
+
+3. AI startup Synthetaic has raised $15 million in Series B funding. The company uses artificial intelligence to analyze data from space and air sensors, which could have significant applications in space exploration and satellite technology. [Source: SpaceNews](https://spacenews.com/ai-startup-synthetaic-raises-15-million-in-series-b-funding/)
+
+4. The Space Force has formally established a unit within the U.S. Indo-Pacific Command, marking a permanent presence in the Indo-Pacific region. This could have significant implications for space security and geopolitics. [Source: SpaceNews](https://spacenews.com/space-force-establishes-permanent-presence-in-indo-pacific-region/)
+
+5. Slingshot Aerospace, a space tracking and data analytics company, is expanding its network of ground-based optical telescopes to increase coverage of low Earth orbit. This could improve our ability to track and analyze objects in low Earth orbit, including satellites and space debris. [Source: SpaceNews](https://spacenews.com/slingshots-space-tracking-network-to-extend-coverage-of-low-earth-orbit/)
+
+6. The National Natural Science Foundation of China has outlined a five-year project for researchers to study the assembly of ultra-large spacecraft. This could lead to significant advancements in spacecraft technology and space exploration capabilities. [Source: SpaceNews](https://spacenews.com/china-researching-challenges-of-kilometer-scale-ultra-large-spacecraft/)
+
+7. The Center for AEroSpace Autonomy Research (CAESAR) at Stanford University is focusing on spacecraft autonomy. The center held a kickoff event on May 22, 2024, to highlight the industry, academia, and government collaboration it seeks to foster. This could lead to significant advancements in autonomous spacecraft technology. [Source: SpaceNews](https://spacenews.com/stanford-center-focuses-on-spacecraft-autonomy/)
+```
+
+</CodeGroup>
+#### Key Components Explained
+
+1. **Custom Knowledge Source (`SpaceNewsKnowledgeSource`)**:
+
+   - Extends `BaseKnowledgeSource` for integration with CrewAI
+   - Configurable API endpoint and article limit
+   - Implements three key methods:
+     - `load_content()`: Fetches articles from the API
+     - `_format_articles()`: Structures the articles into readable text
+     - `add()`: Processes and stores the content
+
+2. **Agent Configuration**:
+
+   - Specialized role as a Space News Analyst
+   - Uses the knowledge source to access space news
+
+3. **Task Setup**:
+
+   - Takes a user question as input through `{user_question}`
+   - Designed to provide detailed answers based on the knowledge source
+
+4. **Crew Orchestration**:
+   - Manages the workflow between agent and task
+   - Handles input/output through the kickoff method
+
+This example demonstrates how to:
+
+- Create a custom knowledge source that fetches real-time data
+- Process and format external data for AI consumption
+- Use the knowledge source to answer specific user questions
+- Integrate everything seamlessly with CrewAI's agent system
+
+#### About the Spaceflight News API
+
+The example uses the [Spaceflight News API](https://api.spaceflightnewsapi.net/v4/docs/), which:
+
+- Provides free access to space-related news articles
+- Requires no authentication
+- Returns structured data about space news
+- Supports pagination and filtering
+
+You can customize the API query by modifying the endpoint URL:
 
 ```python
-source = TextFileKnowledgeSource(
-    file_path="example.txt", # or /example.txt
-    collection_name="example"
+# Fetch more articles
+recent_news = SpaceNewsKnowledgeSource(
+    api_endpoint="https://api.spaceflightnewsapi.net/v4/articles",
+    limit=20,  # Increase the number of articles
 )
-crew = Crew(
-    agents=[agent],
-    tasks=[task],
-    knowledge_sources=[source],
+
+# Add search parameters
+recent_news = SpaceNewsKnowledgeSource(
+    api_endpoint="https://api.spaceflightnewsapi.net/v4/articles?search=NASA", # Search for NASA news
+    limit=10,
 )
 ```
 
@@ -189,43 +306,14 @@ crew = Crew(
 
 <AccordionGroup>
   <Accordion title="Content Organization">
-    - Use meaningful collection names
-    - Add detailed metadata for filtering
-    - Keep chunk sizes appropriate for your content
+    - Keep chunk sizes appropriate for your content type
     - Consider content overlap for context preservation
+    - Organize related information into separate knowledge sources
   </Accordion>
-  
+
   <Accordion title="Performance Tips">
-    - Use smaller chunk sizes for precise retrieval
-    - Implement metadata filtering for faster searches
-    - Choose appropriate embedding models for your use case
-    - Cache frequently accessed knowledge
-  </Accordion>
-  
-  <Accordion title="Error Handling">
-    - Validate knowledge source content
-    - Handle missing or corrupted files
-    - Monitor embedding generation
-    - Implement fallback options
-  </Accordion>
-</AccordionGroup>
-
-## Common Issues and Solutions
-
-<AccordionGroup>
-  <Accordion title="Content Not Found">
-    If agents can't find relevant information:
-    - Check chunk sizes
-    - Verify knowledge source loading
-    - Review metadata filters
-    - Test with simpler queries first
-  </Accordion>
-  
-  <Accordion title="Performance Issues">
-    If knowledge retrieval is slow:
-    - Reduce chunk sizes
-    - Optimize metadata filtering
-    - Consider using a lighter embedding model
-    - Cache frequently accessed content
+    - Adjust chunk sizes based on content complexity 
+    - Configure appropriate embedding models
+    - Consider using local embedding providers for faster processing
   </Accordion>
 </AccordionGroup>

docs/concepts/tools.mdx

@@ -172,6 +172,48 @@ def my_tool(question: str) -> str:
     return "Result from your custom tool"
 ```
 
+### Structured Tools
+
+The `StructuredTool` class wraps functions as tools, providing flexibility and validation while reducing boilerplate. It supports custom schemas and dynamic logic for seamless integration of complex functionalities.
+
+#### Example:
+Using `StructuredTool.from_function`, you can wrap a function that interacts with an external API or system, providing a structured interface. This enables robust validation and consistent execution, making it easier to integrate complex functionalities into your applications as demonstrated in the following example:
+
+```python
+from crewai.tools.structured_tool import CrewStructuredTool
+from pydantic import BaseModel
+
+# Define the schema for the tool's input using Pydantic
+class APICallInput(BaseModel):
+    endpoint: str
+    parameters: dict
+
+# Wrapper function to execute the API call
+def tool_wrapper(*args, **kwargs):
+    # Here, you would typically call the API using the parameters
+    # For demonstration, we'll return a placeholder string
+    return f"Call the API at {kwargs['endpoint']} with parameters {kwargs['parameters']}"
+
+# Create and return the structured tool
+def create_structured_tool():
+    return CrewStructuredTool.from_function(
+        name='Wrapper API',
+        description="A tool to wrap API calls with structured input.",
+        args_schema=APICallInput,
+        func=tool_wrapper,
+    )
+
+# Example usage
+structured_tool = create_structured_tool()
+
+# Execute the tool with structured input
+result = structured_tool._run(**{
+    "endpoint": "https://example.com/api",
+    "parameters": {"key1": "value1", "key2": "value2"}
+})
+print(result)  # Output: Call the API at https://example.com/api with parameters {'key1': 'value1', 'key2': 'value2'}
+```
+
 ### Custom Caching Mechanism
 
 <Tip>

docs/how-to/agentops-observability.mdx

@@ -57,7 +57,7 @@ This feature is useful for debugging and understanding how agents interact with
    <Step title="Install AgentOps">
       Install AgentOps with:
       ```bash
-      pip install crewai[agentops]
+      pip install 'crewai[agentops]'
       ```
       or
       ```bash

docs/how-to/llm-connections.mdx

@@ -32,6 +32,7 @@ LiteLLM supports a wide range of providers, including but not limited to:
 - Cloudflare Workers AI
 - DeepInfra
 - Groq
+- [NVIDIA NIMs](https://docs.api.nvidia.com/nim/reference/models-1)
 - And many more!
 
 For a complete and up-to-date list of supported providers, please refer to the [LiteLLM Providers documentation](https://docs.litellm.ai/docs/providers).

docs/installation.mdx

@@ -7,7 +7,7 @@ icon: wrench
 <Note>
   **Python Version Requirements**
   
-  CrewAI requires `Python >=3.10 and <=3.13`. Here's how to check your version:
+  CrewAI requires `Python >=3.10 and <=3.12`. Here's how to check your version:
   ```bash
   python3 --version
   ```

mkdocs.yml

@@ -129,7 +129,6 @@ nav:
     - Processes: 'core-concepts/Processes.md'
     - Crews: 'core-concepts/Crews.md'
     - Collaboration: 'core-concepts/Collaboration.md'
-    - Pipeline: 'core-concepts/Pipeline.md'
     - Training: 'core-concepts/Training-Crew.md'
     - Memory: 'core-concepts/Memory.md'
     - Planning: 'core-concepts/Planning.md'

pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "crewai"
-version = "0.85.0"
+version = "0.86.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
-requires-python = ">=3.10,<=3.13"
+requires-python = ">=3.10,<=3.12"
 authors = [
     { name = "Joao Moura", email = "joao@crewai.com" }
 ]
@@ -15,7 +15,7 @@ dependencies = [
     "opentelemetry-exporter-otlp-proto-http>=1.22.0",
     "instructor>=1.3.3",
     "regex>=2024.9.11",
-    "crewai-tools>=0.14.0",
+    "crewai-tools>=0.17.0",
     "click>=8.1.7",
     "python-dotenv>=1.0.0",
     "appdirs>=1.4.4",

src/crewai/__init__.py

@@ -5,9 +5,7 @@ from crewai.crew import Crew
 from crewai.flow.flow import Flow
 from crewai.knowledge.knowledge import Knowledge
 from crewai.llm import LLM
-from crewai.pipeline import Pipeline
 from crewai.process import Process
-from crewai.routers import Router
 from crewai.task import Task
 
 warnings.filterwarnings(
@@ -16,14 +14,12 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.85.0"
+__version__ = "0.86.0"
 __all__ = [
     "Agent",
     "Crew",
     "Process",
     "Task",
-    "Pipeline",
-    "Router",
     "LLM",
     "Flow",
     "Knowledge",

src/crewai/agent.py

@@ -8,7 +8,7 @@ from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 from crewai.agents import CacheHandler
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
-from crewai.cli.constants import ENV_VARS
+from crewai.cli.constants import ENV_VARS, LITELLM_PARAMS
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.utils.knowledge_utils import extract_knowledge_context
@@ -181,20 +181,11 @@ class Agent(BaseAgent):
                         if key_name and key_name not in unaccepted_attributes:
                             env_value = os.environ.get(key_name)
                             if env_value:
-                                # Map key names containing "API_KEY" to "api_key"
-                                key_name = (
-                                    "api_key" if "API_KEY" in key_name else key_name
-                                )
-                                # Map key names containing "API_BASE" to "api_base"
-                                key_name = (
-                                    "api_base" if "API_BASE" in key_name else key_name
-                                )
-                                # Map key names containing "API_VERSION" to "api_version"
-                                key_name = (
-                                    "api_version"
-                                    if "API_VERSION" in key_name
-                                    else key_name
-                                )
+                                key_name = key_name.lower()
+                                for pattern in LITELLM_PARAMS:
+                                    if pattern in key_name:
+                                        key_name = pattern
+                                        break
                                 llm_params[key_name] = env_value
                         # Check for default values if the environment variable is not set
                         elif env_var.get("default", False):

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -3,16 +3,15 @@ from typing import TYPE_CHECKING, Optional
 
 from crewai.memory.entity.entity_memory_item import EntityMemoryItem
 from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
+from crewai.utilities import I18N
 from crewai.utilities.converter import ConverterError
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
-from crewai.utilities import I18N
 from crewai.utilities.printer import Printer
 
-
 if TYPE_CHECKING:
+    from crewai.agents.agent_builder.base_agent import BaseAgent
     from crewai.crew import Crew
     from crewai.task import Task
-    from crewai.agents.agent_builder.base_agent import BaseAgent
 
 
 class CrewAgentExecutorMixin:
@@ -100,14 +99,19 @@ class CrewAgentExecutorMixin:
                 print(f"Failed to add to long term memory: {e}")
                 pass
 
-    def _ask_human_input(self, final_answer: dict) -> str:
+    def _ask_human_input(self, final_answer: str) -> str:
         """Prompt human input for final decision making."""
         self._printer.print(
             content=f"\033[1m\033[95m ## Final Result:\033[00m \033[92m{final_answer}\033[00m"
         )
 
         self._printer.print(
-            content="\n\n=====\n## Please provide feedback on the Final Result and the Agent's actions:",
+            content=(
+                "\n\n=====\n"
+                "## Please provide feedback on the Final Result and the Agent's actions. "
+                "Respond with 'looks good' or a similar phrase when you're satisfied.\n"
+                "=====\n"
+            ),
             color="bold_yellow",
         )
         return input()

src/crewai/agents/crew_agent_executor.py

@@ -16,7 +16,7 @@ from crewai.agents.tools_handler import ToolsHandler
 from crewai.tools.base_tool import BaseTool
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N, Printer
-from crewai.utilities.constants import TRAINING_DATA_FILE
+from crewai.utilities.constants import MAX_LLM_RETRY, TRAINING_DATA_FILE
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
@@ -90,7 +90,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         if "system" in self.prompt:
             system_prompt = self._format_prompt(self.prompt.get("system", ""), inputs)
             user_prompt = self._format_prompt(self.prompt.get("user", ""), inputs)
-
             self.messages.append(self._format_msg(system_prompt, role="system"))
             self.messages.append(self._format_msg(user_prompt))
         else:
@@ -103,17 +102,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         formatted_answer = self._invoke_loop()
 
         if self.ask_for_human_input:
-            human_feedback = self._ask_human_input(formatted_answer.output)
-            if self.crew and self.crew._train:
-                self._handle_crew_training_output(formatted_answer, human_feedback)
+            formatted_answer = self._handle_human_feedback(formatted_answer)
 
-            # Making sure we only ask for it once, so disabling for the next thought loop
-            self.ask_for_human_input = False
-            self.messages.append(self._format_msg(f"Feedback: {human_feedback}"))
-            formatted_answer = self._invoke_loop()
-
-            if self.crew and self.crew._train:
-                self._handle_crew_training_output(formatted_answer)
         self._create_short_term_memory(formatted_answer)
         self._create_long_term_memory(formatted_answer)
         return {"output": formatted_answer.output}
@@ -153,6 +143,9 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         tool_result = self._execute_tool_and_check_finality(
                             formatted_answer
                         )
+                        if self.step_callback:
+                          self.step_callback(tool_result)
+
                         formatted_answer.text += f"\nObservation: {tool_result.result}"
                         formatted_answer.result = tool_result.result
                         if tool_result.result_as_answer:
@@ -309,7 +302,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         self._i18n.slice("summarizer_system_message"), role="system"
                     ),
                     self._format_msg(
-                        self._i18n.slice("sumamrize_instruction").format(group=group),
+                        self._i18n.slice("summarize_instruction").format(group=group),
                     ),
                 ],
                 callbacks=self.callbacks,
@@ -326,16 +319,14 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
 
     def _handle_context_length(self) -> None:
         if self.respect_context_window:
-            self._logger.log(
-                "debug",
-                "Context length exceeded. Summarizing content to fit the model context window.",
+            self._printer.print(
+                content="Context length exceeded. Summarizing content to fit the model context window.",
                 color="yellow",
             )
             self._summarize_messages()
         else:
-            self._logger.log(
-                "debug",
-                "Context length exceeded. Consider using smaller text or RAG tools from crewai_tools.",
+            self._printer.print(
+                content="Context length exceeded. Consider using smaller text or RAG tools from crewai_tools.",
                 color="red",
             )
             raise SystemExit(
@@ -362,15 +353,13 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                     ] = result.output
                     training_handler.save(training_data)
                 else:
-                    self._logger.log(
-                        "error",
-                        "Invalid train iteration type or agent_id not in training data.",
+                    self._printer.print(
+                        content="Invalid train iteration type or agent_id not in training data.",
                         color="red",
                     )
             else:
-                self._logger.log(
-                    "error",
-                    "Crew is None or does not have _train_iteration attribute.",
+                self._printer.print(
+                    content="Crew is None or does not have _train_iteration attribute.",
                     color="red",
                 )
 
@@ -388,15 +377,13 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         train_iteration, agent_id, training_data
                     )
                 else:
-                    self._logger.log(
-                        "error",
-                        "Invalid train iteration type. Expected int.",
+                    self._printer.print(
+                        content="Invalid train iteration type. Expected int.",
                         color="red",
                     )
             else:
-                self._logger.log(
-                    "error",
-                    "Crew is None or does not have _train_iteration attribute.",
+                self._printer.print(
+                    content="Crew is None or does not have _train_iteration attribute.",
                     color="red",
                 )
 
@@ -412,3 +399,82 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
     def _format_msg(self, prompt: str, role: str = "user") -> Dict[str, str]:
         prompt = prompt.rstrip()
         return {"role": role, "content": prompt}
+
+    def _handle_human_feedback(self, formatted_answer: AgentFinish) -> AgentFinish:
+        """
+        Handles the human feedback loop, allowing the user to provide feedback
+        on the agent's output and determining if additional iterations are needed.
+
+        Parameters:
+            formatted_answer (AgentFinish): The initial output from the agent.
+
+        Returns:
+            AgentFinish: The final output after incorporating human feedback.
+        """
+        while self.ask_for_human_input:
+            human_feedback = self._ask_human_input(formatted_answer.output)
+            print("Human feedback: ", human_feedback)
+
+            if self.crew and self.crew._train:
+                self._handle_crew_training_output(formatted_answer, human_feedback)
+
+            # Make an LLM call to verify if additional changes are requested based on human feedback
+            additional_changes_prompt = self._i18n.slice(
+                "human_feedback_classification"
+            ).format(feedback=human_feedback)
+
+            retry_count = 0
+            llm_call_successful = False
+            additional_changes_response = None
+
+            while retry_count < MAX_LLM_RETRY and not llm_call_successful:
+                try:
+                    additional_changes_response = (
+                        self.llm.call(
+                            [
+                                self._format_msg(
+                                    additional_changes_prompt, role="system"
+                                )
+                            ],
+                            callbacks=self.callbacks,
+                        )
+                        .strip()
+                        .lower()
+                    )
+                    llm_call_successful = True
+                except Exception as e:
+                    retry_count += 1
+
+                    self._printer.print(
+                        content=f"Error during LLM call to classify human feedback: {e}. Retrying... ({retry_count}/{MAX_LLM_RETRY})",
+                        color="red",
+                    )
+
+            if not llm_call_successful:
+                self._printer.print(
+                    content="Error processing feedback after multiple attempts.",
+                    color="red",
+                )
+                self.ask_for_human_input = False
+                break
+
+            if additional_changes_response == "false":
+                self.ask_for_human_input = False
+            elif additional_changes_response == "true":
+                self.ask_for_human_input = True
+                # Add human feedback to messages
+                self.messages.append(self._format_msg(f"Feedback: {human_feedback}"))
+                # Invoke the loop again with updated messages
+                formatted_answer = self._invoke_loop()
+
+                if self.crew and self.crew._train:
+                    self._handle_crew_training_output(formatted_answer)
+            else:
+                # Unexpected response
+                self._printer.print(
+                    content=f"Unexpected response from LLM: '{additional_changes_response}'. Assuming no additional changes requested.",
+                    color="red",
+                )
+                self.ask_for_human_input = False
+
+        return formatted_answer

src/crewai/cli/cli.py

@@ -6,7 +6,6 @@ import pkg_resources
 from crewai.cli.add_crew_to_flow import add_crew_to_flow
 from crewai.cli.create_crew import create_crew
 from crewai.cli.create_flow import create_flow
-from crewai.cli.create_pipeline import create_pipeline
 from crewai.memory.storage.kickoff_task_outputs_storage import (
     KickoffTaskOutputsSQLiteStorage,
 )
@@ -26,27 +25,24 @@ from .update_crew import update_crew
 
 
 @click.group()
+@click.version_option(pkg_resources.get_distribution("crewai").version)
 def crewai():
     """Top-level command group for crewai."""
 
 
 @crewai.command()
-@click.argument("type", type=click.Choice(["crew", "pipeline", "flow"]))
+@click.argument("type", type=click.Choice(["crew", "flow"]))
 @click.argument("name")
 @click.option("--provider", type=str, help="The provider to use for the crew")
 @click.option("--skip_provider", is_flag=True, help="Skip provider validation")
 def create(type, name, provider, skip_provider=False):
-    """Create a new crew, pipeline, or flow."""
+    """Create a new crew, or flow."""
     if type == "crew":
         create_crew(name, provider, skip_provider)
-    elif type == "pipeline":
-        create_pipeline(name)
     elif type == "flow":
         create_flow(name)
     else:
-        click.secho(
-            "Error: Invalid type. Must be 'crew', 'pipeline', or 'flow'.", fg="red"
-        )
+        click.secho("Error: Invalid type. Must be 'crew' or 'flow'.", fg="red")
 
 
 @crewai.command()
@@ -55,7 +51,10 @@ def create(type, name, provider, skip_provider=False):
 )
 def version(tools):
     """Show the installed version of crewai."""
-    crewai_version = pkg_resources.get_distribution("crewai").version
+    try:
+        crewai_version = pkg_resources.get_distribution("crewai").version
+    except Exception:
+        crewai_version = "unknown version"
     click.echo(f"crewai version: {crewai_version}")
 
     if tools:

src/crewai/cli/constants.py

@@ -159,3 +159,6 @@ MODELS = {
 }
 
 JSON_URL = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"
+
+
+LITELLM_PARAMS = ["api_key", "api_base", "api_version"]

src/crewai/cli/create_pipeline.py

@@ -1,107 +0,0 @@
-import shutil
-from pathlib import Path
-
-import click
-
-
-def create_pipeline(name, router=False):
-    """Create a new pipeline project."""
-    folder_name = name.replace(" ", "_").replace("-", "_").lower()
-    class_name = name.replace("_", " ").replace("-", " ").title().replace(" ", "")
-
-    click.secho(f"Creating pipeline {folder_name}...", fg="green", bold=True)
-
-    project_root = Path(folder_name)
-    if project_root.exists():
-        click.secho(f"Error: Folder {folder_name} already exists.", fg="red")
-        return
-
-    # Create directory structure
-    (project_root / "src" / folder_name).mkdir(parents=True)
-    (project_root / "src" / folder_name / "pipelines").mkdir(parents=True)
-    (project_root / "src" / folder_name / "crews").mkdir(parents=True)
-    (project_root / "src" / folder_name / "tools").mkdir(parents=True)
-    (project_root / "tests").mkdir(exist_ok=True)
-
-    # Create .env file
-    with open(project_root / ".env", "w") as file:
-        file.write("OPENAI_API_KEY=YOUR_API_KEY")
-
-    package_dir = Path(__file__).parent
-    template_folder = "pipeline_router" if router else "pipeline"
-    templates_dir = package_dir / "templates" / template_folder
-
-    # List of template files to copy
-    root_template_files = [".gitignore", "pyproject.toml", "README.md"]
-    src_template_files = ["__init__.py", "main.py"]
-    tools_template_files = ["tools/__init__.py", "tools/custom_tool.py"]
-
-    if router:
-        crew_folders = [
-            "classifier_crew",
-            "normal_crew",
-            "urgent_crew",
-        ]
-        pipelines_folders = [
-            "pipelines/__init__.py",
-            "pipelines/pipeline_classifier.py",
-            "pipelines/pipeline_normal.py",
-            "pipelines/pipeline_urgent.py",
-        ]
-    else:
-        crew_folders = [
-            "research_crew",
-            "write_linkedin_crew",
-            "write_x_crew",
-        ]
-        pipelines_folders = ["pipelines/__init__.py", "pipelines/pipeline.py"]
-
-    def process_file(src_file, dst_file):
-        with open(src_file, "r") as file:
-            content = file.read()
-
-        content = content.replace("{{name}}", name)
-        content = content.replace("{{crew_name}}", class_name)
-        content = content.replace("{{folder_name}}", folder_name)
-        content = content.replace("{{pipeline_name}}", class_name)
-
-        with open(dst_file, "w") as file:
-            file.write(content)
-
-    # Copy and process root template files
-    for file_name in root_template_files:
-        src_file = templates_dir / file_name
-        dst_file = project_root / file_name
-        process_file(src_file, dst_file)
-
-    # Copy and process src template files
-    for file_name in src_template_files:
-        src_file = templates_dir / file_name
-        dst_file = project_root / "src" / folder_name / file_name
-        process_file(src_file, dst_file)
-
-    # Copy tools files
-    for file_name in tools_template_files:
-        src_file = templates_dir / file_name
-        dst_file = project_root / "src" / folder_name / file_name
-        shutil.copy(src_file, dst_file)
-
-    # Copy pipelines folders
-    for file_name in pipelines_folders:
-        src_file = templates_dir / file_name
-        dst_file = project_root / "src" / folder_name / file_name
-        process_file(src_file, dst_file)
-
-    # Copy crew folders
-    for crew_folder in crew_folders:
-        src_crew_folder = templates_dir / "crews" / crew_folder
-        dst_crew_folder = project_root / "src" / folder_name / "crews" / crew_folder
-        if src_crew_folder.exists():
-            shutil.copytree(src_crew_folder, dst_crew_folder)
-        else:
-            click.secho(
-                f"Warning: Crew folder {crew_folder} not found in template.",
-                fg="yellow",
-            )
-
-    click.secho(f"Pipeline {name} created successfully!", fg="green", bold=True)

src/crewai/cli/templates/crew/README.md

@@ -4,7 +4,7 @@ Welcome to the {{crew_name}} Crew project, powered by [crewAI](https://crewai.co
 
 ## Installation
 
-Ensure you have Python >=3.10 <=3.13 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+Ensure you have Python >=3.10 <=3.12 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
 
 First, if you haven't already, install uv:
 

src/crewai/cli/templates/crew/config/tasks.yaml

@@ -12,6 +12,6 @@ reporting_task:
     Review the context you got and expand each topic into a full section for a report.
     Make sure the report is detailed and contains any and all relevant information.
   expected_output: >
-    A fully fledge reports with the mains topics, each with a full section of information.
+    A fully fledged report with the main topics, each with a full section of information.
     Formatted as markdown without '```'
   agent: reporting_analyst

src/crewai/cli/templates/crew/crew.py

@@ -1,37 +1,26 @@
 from crewai import Agent, Crew, Process, Task
-from crewai.project import CrewBase, agent, crew, task, before_kickoff, after_kickoff
-# Uncomment the following line to use an example of a custom tool
-# from {{folder_name}}.tools.custom_tool import MyCustomTool
-# Uncomment the following line to use an example of a knowledge source
-# from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
+from crewai.project import CrewBase, agent, crew, task
 
-# Check our tools documentations for more information on how to use them
-# from crewai_tools import SerperDevTool
+# If you want to run a snippet of code before or after the crew starts, 
+# you can use the @before_kickoff and @after_kickoff decorators
+# https://docs.crewai.com/concepts/crews#example-crew-class-with-decorators
 
 @CrewBase
 class {{crew_name}}():
 	"""{{crew_name}} crew"""
 
+	# Learn more about YAML configuration files here:
+	# Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
+	# Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
 	agents_config = 'config/agents.yaml'
 	tasks_config = 'config/tasks.yaml'
 
-	@before_kickoff # Optional hook to be executed before the crew starts
-	def pull_data_example(self, inputs):
-		# Example of pulling data from an external API, dynamically changing the inputs
-		inputs['extra_data'] = "This is extra data"
-		return inputs
-
-	@after_kickoff # Optional hook to be executed after the crew has finished
-	def log_results(self, output):
-		# Example of logging results, dynamically changing the output
-		print(f"Results: {output}")
-		return output
-
+	# If you would like to add tools to your agents, you can learn more about it here:
+	# https://docs.crewai.com/concepts/agents#agent-tools
 	@agent
 	def researcher(self) -> Agent:
 		return Agent(
 			config=self.agents_config['researcher'],
-			# tools=[MyCustomTool()], # Example of custom tool, loaded on the beginning of file
 			verbose=True
 		)
 
@@ -42,6 +31,9 @@ class {{crew_name}}():
 			verbose=True
 		)
 
+	# To learn more about structured task outputs, 
+	# task dependencies, and task callbacks, check out the documentation:
+	# https://docs.crewai.com/concepts/tasks#overview-of-a-task
 	@task
 	def research_task(self) -> Task:
 		return Task(
@@ -58,14 +50,8 @@ class {{crew_name}}():
 	@crew
 	def crew(self) -> Crew:
 		"""Creates the {{crew_name}} crew"""
-		# You can add knowledge sources here
-		# knowledge_path = "user_preference.txt"
-		# sources = [
-		# 	TextFileKnowledgeSource(
-		# 		file_path="knowledge/user_preference.txt",
-		# 		metadata={"preference": "personal"}
-		# 	),
-		# ]
+		# To learn how to add knowledge sources to your crew, check out the documentation:
+		# https://docs.crewai.com/concepts/knowledge#what-is-knowledge
 
 		return Crew(
 			agents=self.agents, # Automatically created by the @agent decorator
@@ -73,5 +59,4 @@ class {{crew_name}}():
 			process=Process.sequential,
 			verbose=True,
 			# process=Process.hierarchical, # In case you wanna use that instead https://docs.crewai.com/how-to/Hierarchical/
-			# knowledge_sources=sources, # In the case you want to add knowledge sources
 		)

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

@@ -3,9 +3,9 @@ name = "{{folder_name}}"
 version = "0.1.0"
 description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
-requires-python = ">=3.10,<=3.13"
+requires-python = ">=3.10,<=3.12"
 dependencies = [
-    "crewai[tools]>=0.85.0,<1.0.0"
+    "crewai[tools]>=0.86.0,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/README.md

@@ -4,7 +4,7 @@ Welcome to the {{crew_name}} Crew project, powered by [crewAI](https://crewai.co
 
 ## Installation
 
-Ensure you have Python >=3.10 <=3.13 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+Ensure you have Python >=3.10 <=3.12 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
 
 First, if you haven't already, install uv:
 

src/crewai/cli/templates/flow/crews/poem_crew/poem_crew.py

@@ -1,31 +1,47 @@
 from crewai import Agent, Crew, Process, Task
 from crewai.project import CrewBase, agent, crew, task
 
+# If you want to run a snippet of code before or after the crew starts,
+# you can use the @before_kickoff and @after_kickoff decorators
+# https://docs.crewai.com/concepts/crews#example-crew-class-with-decorators
+
+
 @CrewBase
-class PoemCrew():
-	"""Poem Crew"""
+class PoemCrew:
+    """Poem Crew"""
 
-	agents_config = 'config/agents.yaml'
-	tasks_config = 'config/tasks.yaml'
+    # Learn more about YAML configuration files here:
+    # Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
+    # Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
+    agents_config = "config/agents.yaml"
+    tasks_config = "config/tasks.yaml"
 
-	@agent
-	def poem_writer(self) -> Agent:
-		return Agent(
-			config=self.agents_config['poem_writer'],
-		)
+    # If you would lik to add tools to your crew, you can learn more about it here:
+    # https://docs.crewai.com/concepts/agents#agent-tools
+    @agent
+    def poem_writer(self) -> Agent:
+        return Agent(
+            config=self.agents_config["poem_writer"],
+        )
 
-	@task
-	def write_poem(self) -> Task:
-		return Task(
-			config=self.tasks_config['write_poem'],
-		)
+    # To learn more about structured task outputs,
+    # task dependencies, and task callbacks, check out the documentation:
+    # https://docs.crewai.com/concepts/tasks#overview-of-a-task
+    @task
+    def write_poem(self) -> Task:
+        return Task(
+            config=self.tasks_config["write_poem"],
+        )
 
-	@crew
-	def crew(self) -> Crew:
-		"""Creates the Research Crew"""
-		return Crew(
-			agents=self.agents, # Automatically created by the @agent decorator
-			tasks=self.tasks, # Automatically created by the @task decorator
-			process=Process.sequential,
-			verbose=True,
-		)
+    @crew
+    def crew(self) -> Crew:
+        """Creates the Research Crew"""
+        # To learn how to add knowledge sources to your crew, check out the documentation:
+        # https://docs.crewai.com/concepts/knowledge#what-is-knowledge
+
+        return Crew(
+            agents=self.agents,  # Automatically created by the @agent decorator
+            tasks=self.tasks,  # Automatically created by the @task decorator
+            process=Process.sequential,
+            verbose=True,
+        )

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

@@ -3,9 +3,9 @@ name = "{{folder_name}}"
 version = "0.1.0"
 description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
-requires-python = ">=3.10,<=3.13"
+requires-python = ">=3.10,<=3.12"
 dependencies = [
-    "crewai[tools]>=0.85.0,<1.0.0",
+    "crewai[tools]>=0.86.0,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/pipeline/.gitignore

@@ -1,2 +0,0 @@
-.env
-__pycache__/

src/crewai/cli/templates/pipeline/README.md

@@ -1,57 +0,0 @@
-# {{crew_name}} Crew
-
-Welcome to the {{crew_name}} Crew project, powered by [crewAI](https://crewai.com). This template is designed to help you set up a multi-agent AI system with ease, leveraging the powerful and flexible framework provided by crewAI. Our goal is to enable your agents to collaborate effectively on complex tasks, maximizing their collective intelligence and capabilities.
-
-## Installation
-
-Ensure you have Python >=3.10 <=3.13 installed on your system. This project uses [Poetry](https://python-poetry.org/) for dependency management and package handling, offering a seamless setup and execution experience.
-
-First, if you haven't already, install Poetry:
-
-```bash
-pip install poetry
-```
-
-Next, navigate to your project directory and install the dependencies:
-
-1. First lock the dependencies and then install them:
-
-```bash
-crewai install
-```
-
-### Customizing
-
-**Add your `OPENAI_API_KEY` into the `.env` file**
-
-- Modify `src/{{folder_name}}/config/agents.yaml` to define your agents
-- Modify `src/{{folder_name}}/config/tasks.yaml` to define your tasks
-- Modify `src/{{folder_name}}/crew.py` to add your own logic, tools and specific args
-- Modify `src/{{folder_name}}/main.py` to add custom inputs for your agents and tasks
-
-## Running the Project
-
-To kickstart your crew of AI agents and begin task execution, run this from the root folder of your project:
-
-```bash
-crewai run
-```
-
-This command initializes the {{name}} Crew, assembling the agents and assigning them tasks as defined in your configuration.
-
-This example, unmodified, will run the create a `report.md` file with the output of a research on LLMs in the root folder.
-
-## Understanding Your Crew
-
-The {{name}} Crew is composed of multiple AI agents, each with unique roles, goals, and tools. These agents collaborate on a series of tasks, defined in `config/tasks.yaml`, leveraging their collective skills to achieve complex objectives. The `config/agents.yaml` file outlines the capabilities and configurations of each agent in your crew.
-
-## Support
-
-For support, questions, or feedback regarding the {{crew_name}} Crew or crewAI.
-
-- Visit our [documentation](https://docs.crewai.com)
-- Reach out to us through our [GitHub repository](https://github.com/joaomdmoura/crewai)
-- [Join our Discord](https://discord.com/invite/X4JWnZnxPb)
-- [Chat with our docs](https://chatg.pt/DWjSBZn)
-
-Let's create wonders together with the power and simplicity of crewAI.

src/crewai/cli/templates/pipeline/crews/research_crew/config/agents.yaml

@@ -1,19 +0,0 @@
-researcher:
-  role: >
-    {topic} Senior Data Researcher
-  goal: >
-    Uncover cutting-edge developments in {topic}
-  backstory: >
-    You're a seasoned researcher with a knack for uncovering the latest
-    developments in {topic}. Known for your ability to find the most relevant
-    information and present it in a clear and concise manner.
-
-reporting_analyst:
-  role: >
-    {topic} Reporting Analyst
-  goal: >
-    Create detailed reports based on {topic} data analysis and research findings
-  backstory: >
-    You're a meticulous analyst with a keen eye for detail. You're known for
-    your ability to turn complex data into clear and concise reports, making
-    it easy for others to understand and act on the information you provide.

src/crewai/cli/templates/pipeline/crews/research_crew/config/tasks.yaml

@@ -1,16 +0,0 @@
-research_task:
-  description: >
-    Conduct a thorough research about {topic}
-    Make sure you find any interesting and relevant information given
-    the current year is 2024.
-  expected_output: >
-    A list with 10 bullet points of the most relevant information about {topic}
-  agent: researcher
-
-reporting_task:
-  description: >
-    Review the context you got and expand each topic into a full section for a report.
-    Make sure the report is detailed and contains any and all relevant information.
-  expected_output: >
-    A fully fledge reports with a title, mains topics, each with a full section of information.
-  agent: reporting_analyst

src/crewai/cli/templates/pipeline/crews/research_crew/research_crew.py

@@ -1,58 +0,0 @@
-from pydantic import BaseModel
-from crewai import Agent, Crew, Process, Task
-from crewai.project import CrewBase, agent, crew, task
-
-# Uncomment the following line to use an example of a custom tool
-# from demo_pipeline.tools.custom_tool import MyCustomTool
-
-# Check our tools documentations for more information on how to use them
-# from crewai_tools import SerperDevTool
-
-
-class ResearchReport(BaseModel):
-	"""Research Report"""
-	title: str
-	body: str
-
-@CrewBase
-class ResearchCrew():
-	"""Research Crew"""
-	agents_config = 'config/agents.yaml'
-	tasks_config = 'config/tasks.yaml'
-
-	@agent
-	def researcher(self) -> Agent:
-		return Agent(
-			config=self.agents_config['researcher'],
-			verbose=True
-		)
-
-	@agent
-	def reporting_analyst(self) -> Agent:
-		return Agent(
-			config=self.agents_config['reporting_analyst'],
-			verbose=True
-		)
-
-	@task
-	def research_task(self) -> Task:
-		return Task(
-			config=self.tasks_config['research_task'],
-		)
-
-	@task
-	def reporting_task(self) -> Task:
-		return Task(
-			config=self.tasks_config['reporting_task'],
-			output_pydantic=ResearchReport
-		)
-
-	@crew
-	def crew(self) -> Crew:
-		"""Creates the Research Crew"""
-		return Crew(
-			agents=self.agents, # Automatically created by the @agent decorator
-			tasks=self.tasks, # Automatically created by the @task decorator
-			process=Process.sequential,
-			verbose=True,
-		)

src/crewai/cli/templates/pipeline/crews/write_linkedin_crew/write_linkedin_crew.py

@@ -1,51 +0,0 @@
-from crewai import Agent, Crew, Process, Task
-from crewai.project import CrewBase, agent, crew, task
-
-# Uncomment the following line to use an example of a custom tool
-# from {{folder_name}}.tools.custom_tool import MyCustomTool
-
-# Check our tools documentations for more information on how to use them
-# from crewai_tools import SerperDevTool
-
-@CrewBase
-class WriteLinkedInCrew():
-	"""Research Crew"""
-	agents_config = 'config/agents.yaml'
-	tasks_config = 'config/tasks.yaml'
-
-	@agent
-	def researcher(self) -> Agent:
-		return Agent(
-			config=self.agents_config['researcher'],
-			verbose=True
-		)
-
-	@agent
-	def reporting_analyst(self) -> Agent:
-		return Agent(
-			config=self.agents_config['reporting_analyst'],
-			verbose=True
-		)
-
-	@task
-	def research_task(self) -> Task:
-		return Task(
-			config=self.tasks_config['research_task'],
-		)
-
-	@task
-	def reporting_task(self) -> Task:
-		return Task(
-			config=self.tasks_config['reporting_task'],
-			output_file='report.md'
-		)
-
-	@crew
-	def crew(self) -> Crew:
-		"""Creates the {{crew_name}} crew"""
-		return Crew(
-			agents=self.agents, # Automatically created by the @agent decorator
-			tasks=self.tasks, # Automatically created by the @task decorator
-			process=Process.sequential,
-			verbose=True,
-		)

src/crewai/cli/templates/pipeline/crews/write_x_crew/config/agents.yaml

@@ -1,14 +0,0 @@
-x_writer_agent:
-  role: >
-    Expert Social Media Content Creator specializing in short form written content
-  goal: >
-    Create viral-worthy, engaging short form posts that distill complex {topic} information
-    into compelling 280-character messages
-  backstory: >
-    You're a social media virtuoso with a particular talent for short form content. Your posts
-    consistently go viral due to your ability to craft hooks that stop users mid-scroll.
-    You've studied the techniques of social media masters like Justin Welsh, Dickie Bush,
-    Nicolas Cole, and Shaan Puri, incorporating their best practices into your own unique style.
-    Your superpower is taking intricate {topic} concepts and transforming them into
-    bite-sized, shareable content that resonates with a wide audience. You know exactly
-    how to structure a post for maximum impact and engagement.

src/crewai/cli/templates/pipeline/crews/write_x_crew/config/tasks.yaml

@@ -1,22 +0,0 @@
-write_x_task:
-  description: >
-    Using the research report provided, create an engaging short form post about {topic}.
-    Your post should have a great hook, summarize key points, and be structured for easy
-    consumption on a digital platform. The post must be under 280 characters.
-    Follow these guidelines:
-    1. Start with an attention-grabbing hook
-    2. Condense the main insights from the research
-    3. Use clear, concise language
-    4. Include a call-to-action or thought-provoking question if space allows
-    5. Ensure the post flows well and is easy to read quickly
-
-    Here is the title of the research report you will be using
-
-    Title: {title}
-    Research: 
-    {body}
-
-  expected_output: >
-    A compelling X post under 280 characters that effectively summarizes the key findings
-    about {topic}, starts with a strong hook, and is optimized for engagement on the platform.
-  agent: x_writer_agent

src/crewai/cli/templates/pipeline/crews/write_x_crew/write_x_crew.py

@@ -1,36 +0,0 @@
-from crewai import Agent, Crew, Process, Task
-from crewai.project import CrewBase, agent, crew, task
-
-# Uncomment the following line to use an example of a custom tool
-# from demo_pipeline.tools.custom_tool import MyCustomTool
-
-# Check our tools documentations for more information on how to use them
-# from crewai_tools import SerperDevTool
-
-
-@CrewBase
-class WriteXCrew:
-    """Research Crew"""
-
-    agents_config = "config/agents.yaml"
-    tasks_config = "config/tasks.yaml"
-
-    @agent
-    def x_writer_agent(self) -> Agent:
-        return Agent(config=self.agents_config["x_writer_agent"], verbose=True)
-
-    @task
-    def write_x_task(self) -> Task:
-        return Task(
-            config=self.tasks_config["write_x_task"],
-        )
-
-    @crew
-    def crew(self) -> Crew:
-        """Creates the Write X Crew"""
-        return Crew(
-            agents=self.agents,  # Automatically created by the @agent decorator
-            tasks=self.tasks,  # Automatically created by the @task decorator
-            process=Process.sequential,
-            verbose=True,
-        )

src/crewai/cli/templates/pipeline/main.py

@@ -1,26 +0,0 @@
-#!/usr/bin/env python
-import asyncio
-from {{folder_name}}.pipelines.pipeline import {{pipeline_name}}Pipeline
-
-async def run():
-    """
-    Run the pipeline.
-    """
-    inputs = [
-        {"topic": "AI wearables"},
-    ]
-    pipeline = {{pipeline_name}}Pipeline()
-    results = await pipeline.kickoff(inputs)
-    
-    # Process and print results
-    for result in results:
-        print(f"Raw output: {result.raw}")
-        if result.json_dict:
-            print(f"JSON output: {result.json_dict}")
-        print("\n")
-
-def main():
-    asyncio.run(run())
-
-if __name__ == "__main__":
-    main()

src/crewai/cli/templates/pipeline/pipelines/pipeline.py

@@ -1,87 +0,0 @@
-"""
-This pipeline file includes two different examples to demonstrate the flexibility of crewAI pipelines.
-
-Example 1: Two-Stage Pipeline
------------------------------
-This pipeline consists of two crews:
-1. ResearchCrew: Performs research on a given topic.
-2. WriteXCrew: Generates an X (Twitter) post based on the research findings.
-
-Key features:
-- The ResearchCrew's final task uses output_json to store all research findings in a JSON object.
-- This JSON object is then passed to the WriteXCrew, where tasks can access the research findings.
-
-Example 2: Two-Stage Pipeline with Parallel Execution
--------------------------------------------------------
-This pipeline consists of three crews:
-1. ResearchCrew: Performs research on a given topic.
-2. WriteXCrew and WriteLinkedInCrew: Run in parallel, using the research findings to generate posts for X and LinkedIn, respectively.
-
-Key features:
-- Demonstrates the ability to run multiple crews in parallel.
-- Shows how to structure a pipeline with both sequential and parallel stages.
-
-Usage:
-- To switch between examples, comment/uncomment the respective code blocks below.
-- Ensure that you have implemented all necessary crew classes (ResearchCrew, WriteXCrew, WriteLinkedInCrew) before running.
-"""
-
-# Common imports for both examples
-from crewai import Pipeline
-
-
-
-# Uncomment the crews you need for your chosen example
-from ..crews.research_crew.research_crew import ResearchCrew
-from ..crews.write_x_crew.write_x_crew import WriteXCrew
-# from .crews.write_linkedin_crew.write_linkedin_crew import WriteLinkedInCrew  # Uncomment for Example 2
-
-# EXAMPLE 1: Two-Stage Pipeline
-# -----------------------------
-# Uncomment the following code block to use Example 1
-
-class {{pipeline_name}}Pipeline:
-    def __init__(self):
-        # Initialize crews
-        self.research_crew = ResearchCrew().crew()
-        self.write_x_crew = WriteXCrew().crew()
-    
-    def create_pipeline(self):
-        return Pipeline(
-            stages=[
-                self.research_crew,
-                self.write_x_crew
-            ]
-        )
-    
-    async def kickoff(self, inputs):
-        pipeline = self.create_pipeline()
-        results = await pipeline.kickoff(inputs)
-        return results
-
-
-# EXAMPLE 2: Two-Stage Pipeline with Parallel Execution
-# -------------------------------------------------------
-# Uncomment the following code block to use Example 2
-
-# @PipelineBase
-# class {{pipeline_name}}Pipeline:
-#     def __init__(self):
-#         # Initialize crews
-#         self.research_crew = ResearchCrew().crew()
-#         self.write_x_crew = WriteXCrew().crew()
-#         self.write_linkedin_crew = WriteLinkedInCrew().crew()
-    
-#     @pipeline
-#     def create_pipeline(self):
-#         return Pipeline(
-#             stages=[
-#                 self.research_crew,
-#                 [self.write_x_crew, self.write_linkedin_crew]  # Parallel execution
-#             ]
-#         )
-
-#     async def run(self, inputs):
-#         pipeline = self.create_pipeline()
-#         results = await pipeline.kickoff(inputs)
-#         return results

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

@@ -1,17 +0,0 @@
-[tool.poetry]
-name = "{{folder_name}}"
-version = "0.1.0"
-description = "{{name}} using crewAI"
-authors = ["Your Name <you@example.com>"]
-
-[tool.poetry.dependencies]
-python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = ">=0.85.0,<1.0.0" }
-asyncio = "*"
-
-[tool.poetry.scripts]
-{{folder_name}} = "{{folder_name}}.main:main"
-
-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"

src/crewai/cli/templates/pipeline/tools/custom_tool.py

@@ -1,19 +0,0 @@
-from typing import Type
-from crewai.tools import BaseTool
-from pydantic import BaseModel, Field
-
-
-class MyCustomToolInput(BaseModel):
-    """Input schema for MyCustomTool."""
-    argument: str = Field(..., description="Description of the argument.")
-
-class MyCustomTool(BaseTool):
-    name: str = "Name of my tool"
-    description: str = (
-        "Clear description for what this tool is useful for, you agent will need this information to use it."
-    )
-    args_schema: Type[BaseModel] = MyCustomToolInput
-
-    def _run(self, argument: str) -> str:
-        # Implementation goes here
-        return "this is an example of a tool output, ignore it and move along."

src/crewai/cli/templates/pipeline_router/.gitignore

@@ -1,2 +0,0 @@
-.env
-__pycache__/

src/crewai/cli/templates/pipeline_router/README.md

@@ -1,54 +0,0 @@
-# {{crew_name}} Crew
-
-Welcome to the {{crew_name}} Crew project, powered by [crewAI](https://crewai.com). This template is designed to help you set up a multi-agent AI system with ease, leveraging the powerful and flexible framework provided by crewAI. Our goal is to enable your agents to collaborate effectively on complex tasks, maximizing their collective intelligence and capabilities.
-
-## Installation
-
-Ensure you have Python >=3.10 <=3.13 installed on your system. This project uses [Poetry](https://python-poetry.org/) for dependency management and package handling, offering a seamless setup and execution experience.
-
-First, if you haven't already, install Poetry:
-
-```bash
-pip install poetry
-```
-
-Next, navigate to your project directory and install the dependencies:
-
-1. First lock the dependencies and then install them:
-```bash
-crewai install
-```
-### Customizing
-
-**Add your `OPENAI_API_KEY` into the `.env` file**
-
-- Modify `src/{{folder_name}}/config/agents.yaml` to define your agents
-- Modify `src/{{folder_name}}/config/tasks.yaml` to define your tasks
-- Modify `src/{{folder_name}}/crew.py` to add your own logic, tools and specific args
-- Modify `src/{{folder_name}}/main.py` to add custom inputs for your agents and tasks
-
-## Running the Project
-
-To kickstart your crew of AI agents and begin task execution, run this from the root folder of your project:
-
-```bash
-crewai run
-```
-
-This command initializes the {{name}} Crew, assembling the agents and assigning them tasks as defined in your configuration.
-
-This example, unmodified, will run the create a `report.md` file with the output of a research on LLMs in the root folder.
-
-## Understanding Your Crew
-
-The {{name}} Crew is composed of multiple AI agents, each with unique roles, goals, and tools. These agents collaborate on a series of tasks, defined in `config/tasks.yaml`, leveraging their collective skills to achieve complex objectives. The `config/agents.yaml` file outlines the capabilities and configurations of each agent in your crew.
-
-## Support
-
-For support, questions, or feedback regarding the {{crew_name}} Crew or crewAI.
-- Visit our [documentation](https://docs.crewai.com)
-- Reach out to us through our [GitHub repository](https://github.com/joaomdmoura/crewai)
-- [Join our Discord](https://discord.com/invite/X4JWnZnxPb)
-- [Chat with our docs](https://chatg.pt/DWjSBZn)
-
-Let's create wonders together with the power and simplicity of crewAI.

src/crewai/cli/templates/pipeline_router/config/agents.yaml

@@ -1,19 +0,0 @@
-researcher:
-  role: >
-    {topic} Senior Data Researcher
-  goal: >
-    Uncover cutting-edge developments in {topic}
-  backstory: >
-    You're a seasoned researcher with a knack for uncovering the latest
-    developments in {topic}. Known for your ability to find the most relevant
-    information and present it in a clear and concise manner.
-
-reporting_analyst:
-  role: >
-    {topic} Reporting Analyst
-  goal: >
-    Create detailed reports based on {topic} data analysis and research findings
-  backstory: >
-    You're a meticulous analyst with a keen eye for detail. You're known for
-    your ability to turn complex data into clear and concise reports, making
-    it easy for others to understand and act on the information you provide.

src/crewai/cli/templates/pipeline_router/config/tasks.yaml

@@ -1,17 +0,0 @@
-research_task:
-  description: >
-    Conduct a thorough research about {topic}
-    Make sure you find any interesting and relevant information given
-    the current year is 2024.
-  expected_output: >
-    A list with 10 bullet points of the most relevant information about {topic}
-  agent: researcher
-
-reporting_task:
-  description: >
-    Review the context you got and expand each topic into a full section for a report.
-    Make sure the report is detailed and contains any and all relevant information.
-  expected_output: >
-    A fully fledge reports with the mains topics, each with a full section of information.
-    Formatted as markdown without '```'
-  agent: reporting_analyst

src/crewai/cli/templates/pipeline_router/crews/classifier_crew/classifier_crew.py

@@ -1,40 +0,0 @@
-from crewai import Agent, Crew, Process, Task
-from crewai.project import CrewBase, agent, crew, task
-from pydantic import BaseModel
-
-# Uncomment the following line to use an example of a custom tool
-# from demo_pipeline.tools.custom_tool import MyCustomTool
-
-# Check our tools documentations for more information on how to use them
-# from crewai_tools import SerperDevTool
-
-class UrgencyScore(BaseModel):
-    urgency_score: int
-
-@CrewBase
-class ClassifierCrew:
-    """Email Classifier Crew"""
-
-    agents_config = "config/agents.yaml"
-    tasks_config = "config/tasks.yaml"
-
-    @agent
-    def classifier(self) -> Agent:
-        return Agent(config=self.agents_config["classifier"], verbose=True)
-
-    @task
-    def urgent_task(self) -> Task:
-        return Task(
-            config=self.tasks_config["classify_email"],
-            output_pydantic=UrgencyScore,
-        )
-
-    @crew
-    def crew(self) -> Crew:
-        """Creates the Email Classifier Crew"""
-        return Crew(
-            agents=self.agents,  # Automatically created by the @agent decorator
-            tasks=self.tasks,  # Automatically created by the @task decorator
-            process=Process.sequential,
-            verbose=True,
-        )

src/crewai/cli/templates/pipeline_router/crews/classifier_crew/config/agents.yaml

@@ -1,7 +0,0 @@
-classifier:
-  role: >
-    Email Classifier
-  goal: >
-    Classify the email: {email} as urgent or normal from a score of 1 to 10, where 1 is not urgent and 10 is urgent. Return the urgency score only.`
-  backstory: >
-    You are a highly efficient and experienced email classifier, trained to quickly assess and classify emails. Your ability to remain calm under pressure and provide concise, actionable responses has made you an invaluable asset in managing normal situations and maintaining smooth operations.

src/crewai/cli/templates/pipeline_router/crews/classifier_crew/config/tasks.yaml

@@ -1,7 +0,0 @@
-classify_email:
-  description: >
-    Classify the email: {email}
-    as urgent or normal.
-  expected_output: >
-    Classify the email from a scale of 1 to 10, where 1 is not urgent and 10 is urgent. Return the urgency score only.
-  agent: classifier

src/crewai/cli/templates/pipeline_router/crews/normal_crew/config/agents.yaml

@@ -1,7 +0,0 @@
-normal_handler:
-  role: >
-    Normal Email Processor
-  goal: >
-    Process normal emails and create an email to respond to the sender.
-  backstory: >
-    You are a highly efficient and experienced normal email handler, trained to quickly assess and respond to normal communications. Your ability to remain calm under pressure and provide concise, actionable responses has made you an invaluable asset in managing normal situations and maintaining smooth operations.

src/crewai/cli/templates/pipeline_router/crews/normal_crew/config/tasks.yaml

@@ -1,6 +0,0 @@
-normal_task:
-  description: >
-    Process and respond to normal email quickly.
-  expected_output: >
-    An email response to the normal email.
-  agent: normal_handler

src/crewai/cli/templates/pipeline_router/crews/normal_crew/normal_crew.py

@@ -1,36 +0,0 @@
-from crewai import Agent, Crew, Process, Task
-from crewai.project import CrewBase, agent, crew, task
-
-# Uncomment the following line to use an example of a custom tool
-# from demo_pipeline.tools.custom_tool import MyCustomTool
-
-# Check our tools documentations for more information on how to use them
-# from crewai_tools import SerperDevTool
-
-
-@CrewBase
-class NormalCrew:
-    """Normal Email Crew"""
-
-    agents_config = "config/agents.yaml"
-    tasks_config = "config/tasks.yaml"
-
-    @agent
-    def normal_handler(self) -> Agent:
-        return Agent(config=self.agents_config["normal_handler"], verbose=True)
-
-    @task
-    def urgent_task(self) -> Task:
-        return Task(
-            config=self.tasks_config["normal_task"],
-        )
-
-    @crew
-    def crew(self) -> Crew:
-        """Creates the Normal Email Crew"""
-        return Crew(
-            agents=self.agents,  # Automatically created by the @agent decorator
-            tasks=self.tasks,  # Automatically created by the @task decorator
-            process=Process.sequential,
-            verbose=True,
-        )

src/crewai/cli/templates/pipeline_router/crews/urgent_crew/config/agents.yaml

@@ -1,7 +0,0 @@
-urgent_handler:
-  role: >
-    Urgent Email Processor
-  goal: >
-    Process urgent emails and create an email to respond to the sender.
-  backstory: >
-    You are a highly efficient and experienced urgent email handler, trained to quickly assess and respond to time-sensitive communications. Your ability to remain calm under pressure and provide concise, actionable responses has made you an invaluable asset in managing critical situations and maintaining smooth operations.

src/crewai/cli/templates/pipeline_router/crews/urgent_crew/config/tasks.yaml

@@ -1,6 +0,0 @@
-urgent_task:
-  description: >
-    Process and respond to urgent email quickly.
-  expected_output: >
-    An email response to the urgent email.
-  agent: urgent_handler

src/crewai/cli/templates/pipeline_router/crews/urgent_crew/urgent_crew.py

@@ -1,36 +0,0 @@
-from crewai import Agent, Crew, Process, Task
-from crewai.project import CrewBase, agent, crew, task
-
-# Uncomment the following line to use an example of a custom tool
-# from demo_pipeline.tools.custom_tool import MyCustomTool
-
-# Check our tools documentations for more information on how to use them
-# from crewai_tools import SerperDevTool
-
-
-@CrewBase
-class UrgentCrew:
-    """Urgent Email Crew"""
-
-    agents_config = "config/agents.yaml"
-    tasks_config = "config/tasks.yaml"
-
-    @agent
-    def urgent_handler(self) -> Agent:
-        return Agent(config=self.agents_config["urgent_handler"], verbose=True)
-
-    @task
-    def urgent_task(self) -> Task:
-        return Task(
-            config=self.tasks_config["urgent_task"],
-        )
-
-    @crew
-    def crew(self) -> Crew:
-        """Creates the Urgent Email Crew"""
-        return Crew(
-            agents=self.agents,  # Automatically created by the @agent decorator
-            tasks=self.tasks,  # Automatically created by the @task decorator
-            process=Process.sequential,
-            verbose=True,
-        )

src/crewai/cli/templates/pipeline_router/main.py

@@ -1,75 +0,0 @@
-#!/usr/bin/env python
-import asyncio
-from crewai.routers.router import Route
-from crewai.routers.router import Router
-
-from {{folder_name}}.pipelines.pipeline_classifier import EmailClassifierPipeline
-from {{folder_name}}.pipelines.pipeline_normal import NormalPipeline
-from {{folder_name}}.pipelines.pipeline_urgent import UrgentPipeline
-
-async def run():
-    """
-    Run the pipeline.
-    """
-    inputs = [
-       {
-        "email": """
-            Subject: URGENT: Marketing Campaign Launch - Immediate Action Required
-            Dear Team,
-            I'm reaching out regarding our upcoming marketing campaign that requires your immediate attention and swift action. We're facing a critical deadline, and our success hinges on our ability to mobilize quickly.
-            Key points:
-            
-            Campaign launch: 48 hours from now
-            Target audience: 250,000 potential customers
-            Expected ROI: 35% increase in Q3 sales
-            
-            What we need from you NOW:
-            
-            Final approval on creative assets (due in 3 hours)
-            Confirmation of media placements (due by end of day)
-            Last-minute budget allocation for paid social media push
-            
-            Our competitors are poised to launch similar campaigns, and we must act fast to maintain our market advantage. Delays could result in significant lost opportunities and potential revenue.
-            Please prioritize this campaign above all other tasks. I'll be available for the next 24 hours to address any concerns or roadblocks.
-            Let's make this happen!
-            [Your Name]
-            Marketing Director
-            P.S. I'll be scheduling an emergency team meeting in 1 hour to discuss our action plan. Attendance is mandatory.
-        """
-       }
-    ]
-
-    pipeline_classifier = EmailClassifierPipeline().create_pipeline()
-    pipeline_urgent = UrgentPipeline().create_pipeline()
-    pipeline_normal = NormalPipeline().create_pipeline()
-
-    router = Router(
-        routes={
-            "high_urgency": Route(
-                condition=lambda x: x.get("urgency_score", 0) > 7,
-                pipeline=pipeline_urgent
-            ),
-            "low_urgency": Route(
-                condition=lambda x: x.get("urgency_score", 0) <= 7,
-                pipeline=pipeline_normal
-            )
-        },
-        default=pipeline_normal
-    )
-
-    pipeline = pipeline_classifier >> router
-
-    results = await pipeline.kickoff(inputs)
-
-    # Process and print results
-    for result in results:
-        print(f"Raw output: {result.raw}")
-        if result.json_dict:
-            print(f"JSON output: {result.json_dict}")
-        print("\n")
-
-def main():
-    asyncio.run(run())
-
-if __name__ == "__main__":
-    main()

src/crewai/cli/templates/pipeline_router/pipelines/pipeline_classifier.py

@@ -1,24 +0,0 @@
-from crewai import Pipeline
-from crewai.project import PipelineBase
-from ..crews.classifier_crew.classifier_crew import ClassifierCrew
-
-
-@PipelineBase
-class EmailClassifierPipeline:
-    def __init__(self):
-        # Initialize crews
-        self.classifier_crew = ClassifierCrew().crew()
-
-    def create_pipeline(self):
-        return Pipeline(
-            stages=[
-                self.classifier_crew
-            ]
-        )
-    
-    async def kickoff(self, inputs):
-        pipeline = self.create_pipeline()
-        results = await pipeline.kickoff(inputs)
-        return results
-
-

src/crewai/cli/templates/pipeline_router/pipelines/pipeline_normal.py

@@ -1,24 +0,0 @@
-from crewai import Pipeline
-from crewai.project import PipelineBase
-from ..crews.normal_crew.normal_crew import NormalCrew
-
-
-@PipelineBase
-class NormalPipeline:
-    def __init__(self):
-        # Initialize crews
-        self.normal_crew = NormalCrew().crew()
-
-    def create_pipeline(self):
-        return Pipeline(
-            stages=[
-                self.normal_crew
-            ]
-        )
-    
-    async def kickoff(self, inputs):
-        pipeline = self.create_pipeline()
-        results = await pipeline.kickoff(inputs)
-        return results
-
-

src/crewai/cli/templates/pipeline_router/pipelines/pipeline_urgent.py

@@ -1,23 +0,0 @@
-from crewai import Pipeline
-from crewai.project import PipelineBase
-from ..crews.urgent_crew.urgent_crew import UrgentCrew
-
-@PipelineBase
-class UrgentPipeline:
-    def __init__(self):
-        # Initialize crews
-        self.urgent_crew = UrgentCrew().crew()
-    
-    def create_pipeline(self):
-        return Pipeline(
-            stages=[
-                self.urgent_crew
-            ]
-        )
-    
-    async def kickoff(self, inputs):
-        pipeline = self.create_pipeline()
-        results = await pipeline.kickoff(inputs)
-        return results
-
-

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

@@ -1,21 +0,0 @@
-[project]
-name = "{{folder_name}}"
-version = "0.1.0"
-description = "{{name}} using crewAI"
-authors = ["Your Name <you@example.com>"]
-requires-python = ">=3.10,<=3.13"
-dependencies = [
-    "crewai[tools]>=0.85.0,<1.0.0"
-]
-
-[project.scripts]
-{{folder_name}} = "{{folder_name}}.main:main"
-run_crew = "{{folder_name}}.main:main"
-train = "{{folder_name}}.main:train"
-replay = "{{folder_name}}.main:replay"
-test = "{{folder_name}}.main:test"
-
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
-

src/crewai/cli/templates/pipeline_router/tools/custom_tool.py

@@ -1,19 +0,0 @@
-from typing import Type
-from crewai.tools import BaseTool
-from pydantic import BaseModel, Field
-
-
-class MyCustomToolInput(BaseModel):
-    """Input schema for MyCustomTool."""
-    argument: str = Field(..., description="Description of the argument.")
-
-class MyCustomTool(BaseTool):
-    name: str = "Name of my tool"
-    description: str = (
-        "Clear description for what this tool is useful for, you agent will need this information to use it."
-    )
-    args_schema: Type[BaseModel] = MyCustomToolInput
-
-    def _run(self, argument: str) -> str:
-        # Implementation goes here
-        return "this is an example of a tool output, ignore it and move along."

src/crewai/cli/templates/tool/README.md

@@ -5,7 +5,7 @@ custom tools to power up your crews.
 
 ## Installing
 
-Ensure you have Python >=3.10 <=3.13 installed on your system. This project
+Ensure you have Python >=3.10 <=3.12 installed on your system. This project
 uses [UV](https://docs.astral.sh/uv/) for dependency management and package
 handling, offering a seamless setup and execution experience.
 

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

@@ -3,8 +3,8 @@ name = "{{folder_name}}"
 version = "0.1.0"
 description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
-requires-python = ">=3.10,<=3.13"
+requires-python = ">=3.10,<=3.12"
 dependencies = [
-    "crewai[tools]>=0.85.0"
+    "crewai[tools]>=0.86.0"
 ]
 

src/crewai/cli/utils.py

@@ -33,26 +33,6 @@ def copy_template(src, dst, name, class_name, folder_name):
     click.secho(f"  - Created {dst}", fg="green")
 
 
-# Drop the simple_toml_parser when we move to python3.11
-def simple_toml_parser(content):
-    result = {}
-    current_section = result
-    for line in content.split("\n"):
-        line = line.strip()
-        if line.startswith("[") and line.endswith("]"):
-            # New section
-            section = line[1:-1].split(".")
-            current_section = result
-            for key in section:
-                current_section = current_section.setdefault(key, {})
-        elif "=" in line:
-            key, value = line.split("=", 1)
-            key = key.strip()
-            value = value.strip().strip('"')
-            current_section[key] = value
-    return result
-
-
 def read_toml(file_path: str = "pyproject.toml"):
     """Read the content of a TOML file and return it as a dictionary."""
     with open(file_path, "rb") as f:
@@ -63,7 +43,7 @@ def read_toml(file_path: str = "pyproject.toml"):
 def parse_toml(content):
     if sys.version_info >= (3, 11):
         return tomllib.loads(content)
-    return simple_toml_parser(content)
+    return tomli.loads(content)
 
 
 def get_project_name(

src/crewai/crew.py

@@ -5,7 +5,7 @@ import uuid
 import warnings
 from concurrent.futures import Future
 from hashlib import md5
-from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Tuple, Union
+from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
 from pydantic import (
     UUID4,
@@ -23,12 +23,12 @@ from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.cache import CacheHandler
 from crewai.crews.crew_output import CrewOutput
+from crewai.knowledge.knowledge import Knowledge
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.llm import LLM
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
-from crewai.knowledge.knowledge import Knowledge
-from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.memory.user.user_memory import UserMemory
 from crewai.process import Process
 from crewai.task import Task
@@ -56,8 +56,6 @@ if os.environ.get("AGENTOPS_API_KEY"):
     except ImportError:
         pass
 
-if TYPE_CHECKING:
-    from crewai.pipeline.pipeline import Pipeline
 
 warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
 
@@ -1073,17 +1071,5 @@ class Crew(BaseModel):
 
         evaluator.print_crew_evaluation_result()
 
-    def __rshift__(self, other: "Crew") -> "Pipeline":
-        """
-        Implements the >> operator to add another Crew to an existing Pipeline.
-        """
-        from crewai.pipeline.pipeline import Pipeline
-
-        if not isinstance(other, Crew):
-            raise TypeError(
-                f"Unsupported operand type for >>: '{type(self).__name__}' and '{type(other).__name__}'"
-            )
-        return Pipeline(stages=[self, other])
-
     def __repr__(self):
         return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"

src/crewai/knowledge/knowledge.py

@@ -1,11 +1,10 @@
 import os
+from typing import Any, Dict, List, Optional
 
-from typing import List, Optional, Dict, Any
 from pydantic import BaseModel, ConfigDict, Field
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
-from crewai.utilities.constants import DEFAULT_SCORE_THRESHOLD
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"  # removes logging from fastembed
 
@@ -46,9 +45,7 @@ class Knowledge(BaseModel):
             source.storage = self.storage
             source.add()
 
-    def query(
-        self, query: List[str], limit: int = 3, preference: Optional[str] = None
-    ) -> List[Dict[str, Any]]:
+    def query(self, query: List[str], limit: int = 3) -> List[Dict[str, Any]]:
         """
         Query across all knowledge sources to find the most relevant information.
         Returns the top_k most relevant chunks.
@@ -57,8 +54,6 @@ class Knowledge(BaseModel):
         results = self.storage.search(
             query,
             limit,
-            filter={"preference": preference} if preference else None,
-            score_threshold=DEFAULT_SCORE_THRESHOLD,
         )
         return results
 

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -1,13 +1,13 @@
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Union, List, Dict, Any
+from typing import Dict, List, Union
 
 from pydantic import Field
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
-from crewai.utilities.logger import Logger
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
+from crewai.utilities.logger import Logger
 
 
 class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
@@ -49,10 +49,9 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
                     color="red",
                 )
 
-    def save_documents(self, metadata: Dict[str, Any]):
+    def _save_documents(self):
         """Save the documents to the storage."""
-        chunk_metadatas = [metadata.copy() for _ in self.chunks]
-        self.storage.save(self.chunks, chunk_metadatas)
+        self.storage.save(self.chunks)
 
     def convert_to_path(self, path: Union[Path, str]) -> Path:
         """Convert a path to a Path object."""

src/crewai/knowledge/source/base_knowledge_source.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import List, Dict, Any, Optional
+from typing import Any, Dict, List, Optional
 
 import numpy as np
 from pydantic import BaseModel, ConfigDict, Field
@@ -17,7 +17,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
     storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
-    metadata: Dict[str, Any] = Field(default_factory=dict)
+    metadata: Dict[str, Any] = Field(default_factory=dict)  # Currently unused
     collection_name: Optional[str] = Field(default=None)
 
     @abstractmethod
@@ -41,9 +41,9 @@ class BaseKnowledgeSource(BaseModel, ABC):
             for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
         ]
 
-    def save_documents(self, metadata: Dict[str, Any]):
+    def _save_documents(self):
         """
         Save the documents to the storage.
         This method should be called after the chunks and embeddings are generated.
         """
-        self.storage.save(self.chunks, metadata)
+        self.storage.save(self.chunks)

src/crewai/knowledge/source/csv_knowledge_source.py

@@ -1,6 +1,6 @@
 import csv
-from typing import Dict, List
 from pathlib import Path
+from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -30,7 +30,7 @@ class CSVKnowledgeSource(BaseFileKnowledgeSource):
         )
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/excel_knowledge_source.py

@@ -1,5 +1,6 @@
-from typing import Dict, List
 from pathlib import Path
+from typing import Dict, List
+
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
 
@@ -44,7 +45,7 @@ class ExcelKnowledgeSource(BaseFileKnowledgeSource):
 
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/json_knowledge_source.py

@@ -1,6 +1,6 @@
 import json
-from typing import Any, Dict, List
 from pathlib import Path
+from typing import Any, Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -42,7 +42,7 @@ class JSONKnowledgeSource(BaseFileKnowledgeSource):
         )
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/pdf_knowledge_source.py

@@ -1,5 +1,5 @@
-from typing import List, Dict
 from pathlib import Path
+from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -43,7 +43,7 @@ class PDFKnowledgeSource(BaseFileKnowledgeSource):
         for _, text in self.content.items():
             new_chunks = self._chunk_text(text)
             self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/string_knowledge_source.py

@@ -24,7 +24,7 @@ class StringKnowledgeSource(BaseKnowledgeSource):
         """Add string content to the knowledge source, chunk it, compute embeddings, and save them."""
         new_chunks = self._chunk_text(self.content)
         self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/source/text_file_knowledge_source.py

@@ -1,5 +1,5 @@
-from typing import Dict, List
 from pathlib import Path
+from typing import Dict, List
 
 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
 
@@ -24,7 +24,7 @@ class TextFileKnowledgeSource(BaseFileKnowledgeSource):
         for _, text in self.content.items():
             new_chunks = self._chunk_text(text)
             self.chunks.extend(new_chunks)
-        self.save_documents(metadata=self.metadata)
+        self._save_documents()
 
     def _chunk_text(self, text: str) -> List[str]:
         """Utility method to split text into chunks."""

src/crewai/knowledge/storage/knowledge_storage.py

@@ -1,18 +1,22 @@
 import contextlib
+import hashlib
 import io
 import logging
-import chromadb
 import os
+import shutil
+from typing import Any, Dict, List, Optional, Union, cast
 
+import chromadb
 import chromadb.errors
-from crewai.utilities.paths import db_storage_path
-from typing import Optional, List, Dict, Any, Union
-from crewai.utilities import EmbeddingConfigurator
-from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
-import hashlib
-from chromadb.config import Settings
 from chromadb.api import ClientAPI
+from chromadb.api.types import OneOrMany
+from chromadb.config import Settings
+
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
+from crewai.utilities import EmbeddingConfigurator
 from crewai.utilities.logger import Logger
+from crewai.utilities.paths import db_storage_path
+from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
 
 
 @contextlib.contextmanager
@@ -103,24 +107,31 @@ class KnowledgeStorage(BaseKnowledgeStorage):
             raise Exception("Failed to create or get collection")
 
     def reset(self):
-        if self.app:
-            self.app.reset()
-        else:
-            base_path = os.path.join(db_storage_path(), "knowledge")
+        base_path = os.path.join(db_storage_path(), KNOWLEDGE_DIRECTORY)
+        if not self.app:
             self.app = chromadb.PersistentClient(
                 path=base_path,
                 settings=Settings(allow_reset=True),
             )
-            self.app.reset()
+
+        self.app.reset()
+        shutil.rmtree(base_path)
+        self.app = None
+        self.collection = None
 
     def save(
         self,
         documents: List[str],
-        metadata: Union[Dict[str, Any], List[Dict[str, Any]]],
+        metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
     ):
         if self.collection:
             try:
-                metadatas = [metadata] if isinstance(metadata, dict) else metadata
+                if metadata is None:
+                    metadatas: Optional[OneOrMany[chromadb.Metadata]] = None
+                elif isinstance(metadata, list):
+                    metadatas = [cast(chromadb.Metadata, m) for m in metadata]
+                else:
+                    metadatas = cast(chromadb.Metadata, metadata)
 
                 ids = [
                     hashlib.sha256(doc.encode("utf-8")).hexdigest() for doc in documents

src/crewai/llm.py

@@ -1,4 +1,5 @@
 import logging
+import os
 import sys
 import threading
 import warnings
@@ -128,6 +129,7 @@ class LLM:
         litellm.drop_params = True
         litellm.set_verbose = False
         self.set_callbacks(callbacks)
+        self.set_env_callbacks()
 
     def call(self, messages: List[Dict[str, str]], callbacks: List[Any] = []) -> str:
         with suppress_warnings():
@@ -202,3 +204,39 @@ class LLM:
                 litellm._async_success_callback.remove(callback)
 
         litellm.callbacks = callbacks
+
+    def set_env_callbacks(self):
+        """
+        Sets the success and failure callbacks for the LiteLLM library from environment variables.
+
+        This method reads the `LITELLM_SUCCESS_CALLBACKS` and `LITELLM_FAILURE_CALLBACKS`
+        environment variables, which should contain comma-separated lists of callback names.
+        It then assigns these lists to `litellm.success_callback` and `litellm.failure_callback`,
+        respectively.
+
+        If the environment variables are not set or are empty, the corresponding callback lists
+        will be set to empty lists.
+
+        Example:
+            LITELLM_SUCCESS_CALLBACKS="langfuse,langsmith"
+            LITELLM_FAILURE_CALLBACKS="langfuse"
+
+        This will set `litellm.success_callback` to ["langfuse", "langsmith"] and
+        `litellm.failure_callback` to ["langfuse"].
+        """
+        success_callbacks_str = os.environ.get("LITELLM_SUCCESS_CALLBACKS", "")
+        success_callbacks = []
+        if success_callbacks_str:
+            success_callbacks = [
+                callback.strip() for callback in success_callbacks_str.split(",")
+            ]
+
+        failure_callbacks_str = os.environ.get("LITELLM_FAILURE_CALLBACKS", "")
+        failure_callbacks = []
+        if failure_callbacks_str:
+            failure_callbacks = [
+                callback.strip() for callback in failure_callbacks_str.split(",")
+            ]
+
+        litellm.success_callback = success_callbacks
+        litellm.failure_callback = failure_callbacks

src/crewai/memory/storage/rag_storage.py

@@ -4,12 +4,14 @@ import logging
 import os
 import shutil
 import uuid
-
 from typing import Any, Dict, List, Optional
+
 from chromadb.api import ClientAPI
+
 from crewai.memory.storage.base_rag_storage import BaseRAGStorage
-from crewai.utilities.paths import db_storage_path
 from crewai.utilities import EmbeddingConfigurator
+from crewai.utilities.constants import MAX_FILE_NAME_LENGTH
+from crewai.utilities.paths import db_storage_path
 
 
 @contextlib.contextmanager
@@ -37,12 +39,15 @@ class RAGStorage(BaseRAGStorage):
 
     app: ClientAPI | None = None
 
-    def __init__(self, type, allow_reset=True, embedder_config=None, crew=None, path=None):
+    def __init__(
+        self, type, allow_reset=True, embedder_config=None, crew=None, path=None
+    ):
         super().__init__(type, allow_reset, embedder_config, crew)
         agents = crew.agents if crew else []
         agents = [self._sanitize_role(agent.role) for agent in agents]
         agents = "_".join(agents)
         self.agents = agents
+        self.storage_file_name = self._build_storage_file_name(type, agents)
 
         self.type = type
 
@@ -60,7 +65,7 @@ class RAGStorage(BaseRAGStorage):
 
         self._set_embedder_config()
         chroma_client = chromadb.PersistentClient(
-            path=self.path if self.path else f"{db_storage_path()}/{self.type}/{self.agents}",
+            path=self.path if self.path else self.storage_file_name,
             settings=Settings(allow_reset=self.allow_reset),
         )
 
@@ -81,6 +86,20 @@ class RAGStorage(BaseRAGStorage):
         """
         return role.replace("\n", "").replace(" ", "_").replace("/", "_")
 
+    def _build_storage_file_name(self, type: str, file_name: str) -> str:
+        """
+        Ensures file name does not exceed max allowed by OS
+        """
+        base_path = f"{db_storage_path()}/{type}"
+
+        if len(file_name) > MAX_FILE_NAME_LENGTH:
+            logging.warning(
+                f"Trimming file name from {len(file_name)} to {MAX_FILE_NAME_LENGTH} characters."
+            )
+            file_name = file_name[:MAX_FILE_NAME_LENGTH]
+
+        return f"{base_path}/{file_name}"
+
     def save(self, value: Any, metadata: Dict[str, Any]) -> None:
         if not hasattr(self, "app") or not hasattr(self, "collection"):
             self._initialize_app()
@@ -131,9 +150,11 @@ class RAGStorage(BaseRAGStorage):
 
     def reset(self) -> None:
         try:
-            shutil.rmtree(f"{db_storage_path()}/{self.type}")
             if self.app:
                 self.app.reset()
+                shutil.rmtree(f"{db_storage_path()}/{self.type}")
+                self.app = None
+                self.collection = None
         except Exception as e:
             if "attempt to write a readonly database" in str(e):
                 # Ignore this specific error

src/crewai/memory/user/user_memory.py

@@ -37,7 +37,7 @@ class UserMemory(Memory):
         limit: int = 3,
         score_threshold: float = 0.35,
     ):
-        results = super().search(
+        results = self.storage.search(
             query=query,
             limit=limit,
             score_threshold=score_threshold,

src/crewai/pipeline/__init__.py

@@ -1,5 +0,0 @@
-from crewai.pipeline.pipeline import Pipeline
-from crewai.pipeline.pipeline_kickoff_result import PipelineKickoffResult
-from crewai.pipeline.pipeline_output import PipelineOutput
-
-__all__ = ["Pipeline", "PipelineKickoffResult", "PipelineOutput"]

src/crewai/pipeline/pipeline.py

@@ -1,405 +0,0 @@
-import asyncio
-import copy
-from typing import Any, Dict, List, Tuple, Union
-
-from pydantic import BaseModel, Field, model_validator
-
-from crewai.crew import Crew
-from crewai.crews.crew_output import CrewOutput
-from crewai.pipeline.pipeline_kickoff_result import PipelineKickoffResult
-from crewai.routers.router import Router
-from crewai.types.usage_metrics import UsageMetrics
-
-Trace = Union[Union[str, Dict[str, Any]], List[Union[str, Dict[str, Any]]]]
-PipelineStage = Union[Crew, List[Crew], Router]
-
-"""
-Developer Notes:
-
-This module defines a Pipeline class that represents a sequence of operations (stages)
-to process inputs. Each stage can be either sequential or parallel, and the pipeline
-can process multiple kickoffs concurrently.
-
-Core Loop Explanation:
-1. The `process_kickoffs` method processes multiple kickoffs in parallel, each going through
-   all pipeline stages.
-2. The `process_single_kickoff` method handles the processing of a single kickouff through
-   all stages, updating metrics and input data along the way.
-3. The `_process_stage` method determines whether a stage is sequential or parallel
-   and processes it accordingly.
-4. The `_process_single_crew` and `_process_parallel_crews` methods handle the
-   execution of single and parallel crew stages.
-5. The `_update_metrics_and_input` method updates usage metrics and the current input
-   with the outputs from a stage.
-6. The `_build_pipeline_kickoff_results` method constructs the final results of the
-   pipeline kickoff, including traces and outputs.
-
-Handling Traces and Crew Outputs:
-- During the processing of stages, we handle the results (traces and crew outputs)
-  for all stages except the last one differently from the final stage.
-- For intermediate stages, the primary focus is on passing the input data between stages.
-  This involves merging the output dictionaries from all crews in a stage into a single
-  dictionary and passing it to the next stage. This merged dictionary allows for smooth
-  data flow between stages.
-- For the final stage, in addition to passing the input data, we also need to prepare
-  the final outputs and traces to be returned as the overall result of the pipeline kickoff.
-  In this case, we do not merge the results, as each result needs to be included
-  separately in its own pipeline kickoff result.
-
-Pipeline Terminology:
-- Pipeline: The overall structure that defines a sequence of operations.
-- Stage: A distinct part of the pipeline, which can be either sequential or parallel.
-- Kickoff: A specific execution of the pipeline for a given set of inputs, representing a single instance of processing through the pipeline.
-- Branch: Parallel executions within a stage (e.g., concurrent crew operations).
-- Trace: The journey of an individual input through the entire pipeline.
-
-Example pipeline structure:
-crew1 >> crew2 >> crew3 
-
-This represents a pipeline with three sequential stages:
-1. crew1 is the first stage, which processes the input and passes its output to crew2.
-2. crew2 is the second stage, which takes the output from crew1 as its input, processes it, and passes its output to crew3.
-3. crew3 is the final stage, which takes the output from crew2 as its input and produces the final output of the pipeline.
-
-Each input creates its own kickoff, flowing through all stages of the pipeline.
-Multiple kickoffss can be processed concurrently, each following the defined pipeline structure.
-
-Another example pipeline structure:
-crew1 >> [crew2, crew3] >> crew4
-
-This represents a pipeline with three stages:
-1. A sequential stage (crew1)
-2. A parallel stage with two branches (crew2 and crew3 executing concurrently)
-3. Another sequential stage (crew4)
-
-Each input creates its own kickoff, flowing through all stages of the pipeline.
-Multiple kickoffs can be processed concurrently, each following the defined pipeline structure.
-"""
-
-
-class Pipeline(BaseModel):
-    stages: List[PipelineStage] = Field(
-        ..., description="List of crews representing stages to be executed in sequence"
-    )
-
-    @model_validator(mode="before")
-    @classmethod
-    def validate_stages(cls, values):
-        stages = values.get("stages", [])
-
-        def check_nesting_and_type(item, depth=0):
-            if depth > 1:
-                raise ValueError("Double nesting is not allowed in pipeline stages")
-            if isinstance(item, list):
-                for sub_item in item:
-                    check_nesting_and_type(sub_item, depth + 1)
-            elif not isinstance(item, (Crew, Router)):
-                raise ValueError(
-                    f"Expected Crew instance, Router instance, or list of Crews, got {type(item)}"
-                )
-
-        for stage in stages:
-            check_nesting_and_type(stage)
-        return values
-
-    async def kickoff(
-        self, inputs: List[Dict[str, Any]]
-    ) -> List[PipelineKickoffResult]:
-        """
-        Processes multiple runs in parallel, each going through all pipeline stages.
-
-        Args:
-            inputs (List[Dict[str, Any]]): List of inputs for each run.
-
-        Returns:
-            List[PipelineKickoffResult]: List of results from each run.
-        """
-        pipeline_results: List[PipelineKickoffResult] = []
-
-        # Process all runs in parallel
-        all_run_results = await asyncio.gather(
-            *(self.process_single_kickoff(input_data) for input_data in inputs)
-        )
-
-        # Flatten the list of lists into a single list of results
-        pipeline_results.extend(
-            result for run_result in all_run_results for result in run_result
-        )
-
-        return pipeline_results
-
-    async def process_single_kickoff(
-        self, kickoff_input: Dict[str, Any]
-    ) -> List[PipelineKickoffResult]:
-        """
-        Processes a single run through all pipeline stages.
-
-        Args:
-            input (Dict[str, Any]): The input for the run.
-
-        Returns:
-            List[PipelineKickoffResult]: The results of processing the run.
-        """
-        initial_input = copy.deepcopy(kickoff_input)
-        current_input = copy.deepcopy(kickoff_input)
-        stages = self._copy_stages()
-        pipeline_usage_metrics: Dict[str, UsageMetrics] = {}
-        all_stage_outputs: List[List[CrewOutput]] = []
-        traces: List[List[Union[str, Dict[str, Any]]]] = [[initial_input]]
-
-        stage_index = 0
-        while stage_index < len(stages):
-            stage = stages[stage_index]
-            stage_input = copy.deepcopy(current_input)
-
-            if isinstance(stage, Router):
-                next_pipeline, route_taken = stage.route(stage_input)
-                stages = (
-                    stages[: stage_index + 1]
-                    + list(next_pipeline.stages)
-                    + stages[stage_index + 1 :]
-                )
-                traces.append([{"route_taken": route_taken}])
-                stage_index += 1
-                continue
-
-            stage_outputs, stage_trace = await self._process_stage(stage, stage_input)
-
-            self._update_metrics_and_input(
-                pipeline_usage_metrics, current_input, stage, stage_outputs
-            )
-            traces.append(stage_trace)
-            all_stage_outputs.append(stage_outputs)
-            stage_index += 1
-
-        return self._build_pipeline_kickoff_results(
-            all_stage_outputs, traces, pipeline_usage_metrics
-        )
-
-    async def _process_stage(
-        self, stage: PipelineStage, current_input: Dict[str, Any]
-    ) -> Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]:
-        """
-        Processes a single stage of the pipeline, which can be either sequential or parallel.
-
-        Args:
-            stage (Union[Crew, List[Crew]]): The stage to process.
-            current_input (Dict[str, Any]): The input for the stage.
-
-        Returns:
-            Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]: The outputs and trace of the stage.
-        """
-        if isinstance(stage, Crew):
-            return await self._process_single_crew(stage, current_input)
-        elif isinstance(stage, list) and all(isinstance(crew, Crew) for crew in stage):
-            return await self._process_parallel_crews(stage, current_input)
-        else:
-            raise ValueError(f"Unsupported stage type: {type(stage)}")
-
-    async def _process_single_crew(
-        self, crew: Crew, current_input: Dict[str, Any]
-    ) -> Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]:
-        """
-        Processes a single crew.
-
-        Args:
-            crew (Crew): The crew to process.
-            current_input (Dict[str, Any]): The input for the crew.
-
-        Returns:
-            Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]: The output and trace of the crew.
-        """
-        output = await crew.kickoff_async(inputs=current_input)
-        return [output], [crew.name or str(crew.id)]
-
-    async def _process_parallel_crews(
-        self, crews: List[Crew], current_input: Dict[str, Any]
-    ) -> Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]:
-        """
-        Processes multiple crews in parallel.
-
-        Args:
-            crews (List[Crew]): The list of crews to process in parallel.
-            current_input (Dict[str, Any]): The input for the crews.
-
-        Returns:
-            Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]: The outputs and traces of the crews.
-        """
-        parallel_outputs = await asyncio.gather(
-            *[crew.kickoff_async(inputs=current_input) for crew in crews]
-        )
-        return parallel_outputs, [crew.name or str(crew.id) for crew in crews]
-
-    def _update_metrics_and_input(
-        self,
-        usage_metrics: Dict[str, UsageMetrics],
-        current_input: Dict[str, Any],
-        stage: PipelineStage,
-        outputs: List[CrewOutput],
-    ) -> None:
-        """
-        Updates metrics and current input with the outputs of a stage.
-
-        Args:
-            usage_metrics (Dict[str, Any]): The usage metrics to update.
-            current_input (Dict[str, Any]): The current input to update.
-            stage (Union[Crew, List[Crew]]): The stage that was processed.
-            outputs (List[CrewOutput]): The outputs of the stage.
-        """
-        if isinstance(stage, Crew):
-            usage_metrics[stage.name or str(stage.id)] = outputs[0].token_usage
-            current_input.update(outputs[0].to_dict())
-        elif isinstance(stage, list) and all(isinstance(crew, Crew) for crew in stage):
-            for crew, output in zip(stage, outputs):
-                usage_metrics[crew.name or str(crew.id)] = output.token_usage
-                current_input.update(output.to_dict())
-        else:
-            raise ValueError(f"Unsupported stage type: {type(stage)}")
-
-    def _build_pipeline_kickoff_results(
-        self,
-        all_stage_outputs: List[List[CrewOutput]],
-        traces: List[List[Union[str, Dict[str, Any]]]],
-        token_usage: Dict[str, UsageMetrics],
-    ) -> List[PipelineKickoffResult]:
-        """
-        Builds the results of a pipeline run.
-
-        Args:
-            all_stage_outputs (List[List[CrewOutput]]): All stage outputs.
-            traces (List[List[Union[str, Dict[str, Any]]]]): All traces.
-            token_usage (Dict[str, Any]): Token usage metrics.
-
-        Returns:
-            List[PipelineKickoffResult]: The results of the pipeline run.
-        """
-        formatted_traces = self._format_traces(traces)
-        formatted_crew_outputs = self._format_crew_outputs(all_stage_outputs)
-
-        return [
-            PipelineKickoffResult(
-                token_usage=token_usage,
-                trace=formatted_trace,
-                raw=crews_outputs[-1].raw,
-                pydantic=crews_outputs[-1].pydantic,
-                json_dict=crews_outputs[-1].json_dict,
-                crews_outputs=crews_outputs,
-            )
-            for crews_outputs, formatted_trace in zip(
-                formatted_crew_outputs, formatted_traces
-            )
-        ]
-
-    def _format_traces(
-        self, traces: List[List[Union[str, Dict[str, Any]]]]
-    ) -> List[List[Trace]]:
-        """
-        Formats the traces of a pipeline run.
-
-        Args:
-            traces (List[List[Union[str, Dict[str, Any]]]]): The traces to format.
-
-        Returns:
-            List[List[Trace]]: The formatted traces.
-        """
-        formatted_traces: List[Trace] = self._format_single_trace(traces[:-1])
-        return self._format_multiple_traces(formatted_traces, traces[-1])
-
-    def _format_single_trace(
-        self, traces: List[List[Union[str, Dict[str, Any]]]]
-    ) -> List[Trace]:
-        """
-        Formats single traces.
-
-        Args:
-            traces (List[List[Union[str, Dict[str, Any]]]]): The traces to format.
-
-        Returns:
-            List[Trace]: The formatted single traces.
-        """
-        formatted_traces: List[Trace] = []
-        for trace in traces:
-            formatted_traces.append(trace[0] if len(trace) == 1 else trace)
-        return formatted_traces
-
-    def _format_multiple_traces(
-        self,
-        formatted_traces: List[Trace],
-        final_trace: List[Union[str, Dict[str, Any]]],
-    ) -> List[List[Trace]]:
-        """
-        Formats multiple traces.
-
-        Args:
-            formatted_traces (List[Trace]): The formatted single traces.
-            final_trace (List[Union[str, Dict[str, Any]]]): The final trace to format.
-
-        Returns:
-            List[List[Trace]]: The formatted multiple traces.
-        """
-        traces_to_return: List[List[Trace]] = []
-        if len(final_trace) == 1:
-            formatted_traces.append(final_trace[0])
-            traces_to_return.append(formatted_traces)
-        else:
-            for trace in final_trace:
-                copied_traces = formatted_traces.copy()
-                copied_traces.append(trace)
-                traces_to_return.append(copied_traces)
-        return traces_to_return
-
-    def _format_crew_outputs(
-        self, all_stage_outputs: List[List[CrewOutput]]
-    ) -> List[List[CrewOutput]]:
-        """
-        Formats the outputs of all stages into a list of crew outputs.
-
-        Args:
-            all_stage_outputs (List[List[CrewOutput]]): All stage outputs.
-
-        Returns:
-            List[List[CrewOutput]]: Formatted crew outputs.
-        """
-        crew_outputs: List[CrewOutput] = [
-            output
-            for stage_outputs in all_stage_outputs[:-1]
-            for output in stage_outputs
-        ]
-        return [crew_outputs + [output] for output in all_stage_outputs[-1]]
-
-    def _copy_stages(self):
-        """Create a deep copy of the Pipeline's stages."""
-        new_stages = []
-        for stage in self.stages:
-            if isinstance(stage, list):
-                new_stages.append(
-                    [
-                        crew.copy() if hasattr(crew, "copy") else copy.deepcopy(crew)
-                        for crew in stage
-                    ]
-                )
-            elif hasattr(stage, "copy"):
-                new_stages.append(stage.copy())
-            else:
-                new_stages.append(copy.deepcopy(stage))
-
-        return new_stages
-
-    def __rshift__(self, other: PipelineStage) -> "Pipeline":
-        """
-        Implements the >> operator to add another Stage (Crew or List[Crew]) to an existing Pipeline.
-
-        Args:
-            other (Any): The stage to add.
-
-        Returns:
-            Pipeline: A new pipeline with the added stage.
-        """
-        if isinstance(other, (Crew, Router)) or (
-            isinstance(other, list) and all(isinstance(item, Crew) for item in other)
-        ):
-            return type(self)(stages=self.stages + [other])
-        else:
-            raise TypeError(
-                f"Unsupported operand type for >>: '{type(self).__name__}' and '{type(other).__name__}'"
-            )

src/crewai/pipeline/pipeline_kickoff_result.py

@@ -1,61 +0,0 @@
-import json
-import uuid
-from typing import Any, Dict, List, Optional, Union
-
-from pydantic import UUID4, BaseModel, Field
-
-from crewai.crews.crew_output import CrewOutput
-from crewai.types.usage_metrics import UsageMetrics
-
-
-class PipelineKickoffResult(BaseModel):
-    """Class that represents the result of a pipeline run."""
-
-    id: UUID4 = Field(
-        default_factory=uuid.uuid4,
-        frozen=True,
-        description="Unique identifier for the object, not set by user.",
-    )
-    raw: str = Field(description="Raw output of the pipeline run", default="")
-    pydantic: Any = Field(
-        description="Pydantic output of the pipeline run", default=None
-    )
-    json_dict: Union[Dict[str, Any], None] = Field(
-        description="JSON dict output of the pipeline run", default={}
-    )
-
-    token_usage: Dict[str, UsageMetrics] = Field(
-        description="Token usage for each crew in the run"
-    )
-    trace: List[Any] = Field(
-        description="Trace of the journey of inputs through the run"
-    )
-    crews_outputs: List[CrewOutput] = Field(
-        description="Output from each crew in the run",
-        default=[],
-    )
-
-    @property
-    def json(self) -> Optional[str]:
-        if self.crews_outputs[-1].tasks_output[-1].output_format != "json":
-            raise ValueError(
-                "No JSON output found in the final task of the final crew. Please make sure to set the output_json property in the final task in your crew."
-            )
-
-        return json.dumps(self.json_dict)
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert json_output and pydantic_output to a dictionary."""
-        output_dict = {}
-        if self.json_dict:
-            output_dict.update(self.json_dict)
-        elif self.pydantic:
-            output_dict.update(self.pydantic.model_dump())
-        return output_dict
-
-    def __str__(self):
-        if self.pydantic:
-            return str(self.pydantic)
-        if self.json_dict:
-            return str(self.json_dict)
-        return self.raw

src/crewai/pipeline/pipeline_output.py

@@ -1,20 +0,0 @@
-import uuid
-from typing import List
-
-from pydantic import UUID4, BaseModel, Field
-
-from crewai.pipeline.pipeline_kickoff_result import PipelineKickoffResult
-
-
-class PipelineOutput(BaseModel):
-    id: UUID4 = Field(
-        default_factory=uuid.uuid4,
-        frozen=True,
-        description="Unique identifier for the object, not set by user.",
-    )
-    run_results: List[PipelineKickoffResult] = Field(
-        description="List of results for each run through the pipeline", default=[]
-    )
-
-    def add_run_result(self, result: PipelineKickoffResult):
-        self.run_results.append(result)

src/crewai/project/__init__.py

@@ -8,12 +8,10 @@ from .annotations import (
     llm,
     output_json,
     output_pydantic,
-    pipeline,
     task,
     tool,
 )
 from .crew_base import CrewBase
-from .pipeline_base import PipelineBase
 
 __all__ = [
     "agent",
@@ -24,10 +22,8 @@ __all__ = [
     "tool",
     "callback",
     "CrewBase",
-    "PipelineBase",
     "llm",
     "cache_handler",
-    "pipeline",
     "before_kickoff",
     "after_kickoff",
 ]

src/crewai/project/annotations.py

@@ -65,22 +65,9 @@ def cache_handler(func):
     return memoize(func)
 
 
-def stage(func):
-    func.is_stage = True
-    return memoize(func)
-
-
-def router(func):
-    func.is_router = True
-    return memoize(func)
-
-
-def pipeline(func):
-    func.is_pipeline = True
-    return memoize(func)
-
-
 def crew(func) -> Callable[..., Crew]:
+
+    @wraps(func)
     def wrapper(self, *args, **kwargs) -> Crew:
         instantiated_tasks = []
         instantiated_agents = []

src/crewai/project/crew_base.py

@@ -213,4 +213,8 @@ def CrewBase(cls: T) -> T:
                     callback_functions[callback]() for callback in callbacks
                 ]
 
+    # 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)

src/crewai/project/pipeline_base.py

@@ -1,58 +0,0 @@
-from typing import Any, Callable, Dict, List, Type, Union
-
-from crewai.crew import Crew
-from crewai.pipeline.pipeline import Pipeline
-from crewai.routers.router import Router
-
-PipelineStage = Union[Crew, List[Crew], Router]
-
-
-# TODO: Could potentially remove. Need to check with @joao and @gui if this is needed for CrewAI+
-def PipelineBase(cls: Type[Any]) -> Type[Any]:
-    class WrappedClass(cls):
-        is_pipeline_class: bool = True  # type: ignore
-        stages: List[PipelineStage]
-
-        def __init__(self, *args: Any, **kwargs: Any) -> None:
-            super().__init__(*args, **kwargs)
-            self.stages = []
-            self._map_pipeline_components()
-
-        def _get_all_functions(self) -> Dict[str, Callable[..., Any]]:
-            return {
-                name: getattr(self, name)
-                for name in dir(self)
-                if callable(getattr(self, name))
-            }
-
-        def _filter_functions(
-            self, functions: Dict[str, Callable[..., Any]], attribute: str
-        ) -> Dict[str, Callable[..., Any]]:
-            return {
-                name: func
-                for name, func in functions.items()
-                if hasattr(func, attribute)
-            }
-
-        def _map_pipeline_components(self) -> None:
-            all_functions = self._get_all_functions()
-            crew_functions = self._filter_functions(all_functions, "is_crew")
-            router_functions = self._filter_functions(all_functions, "is_router")
-
-            for stage_attr in dir(self):
-                stage = getattr(self, stage_attr)
-                if isinstance(stage, (Crew, Router)):
-                    self.stages.append(stage)
-                elif callable(stage) and hasattr(stage, "is_crew"):
-                    self.stages.append(crew_functions[stage_attr]())
-                elif callable(stage) and hasattr(stage, "is_router"):
-                    self.stages.append(router_functions[stage_attr]())
-                elif isinstance(stage, list) and all(
-                    isinstance(item, Crew) for item in stage
-                ):
-                    self.stages.append(stage)
-
-        def build_pipeline(self) -> Pipeline:
-            return Pipeline(stages=self.stages)
-
-    return WrappedClass

src/crewai/project/utils.py

@@ -1,11 +1,13 @@
+from functools import wraps
+
 def memoize(func):
     cache = {}
 
+    @wraps(func)
     def memoized_func(*args, **kwargs):
         key = (args, tuple(kwargs.items()))
         if key not in cache:
             cache[key] = func(*args, **kwargs)
         return cache[key]
 
-    memoized_func.__dict__.update(func.__dict__)
     return memoized_func

src/crewai/routers/__init__.py

@@ -1,3 +0,0 @@
-from crewai.routers.router import Router
-
-__all__ = ["Router"]

src/crewai/routers/router.py

@@ -1,84 +0,0 @@
-from copy import deepcopy
-from typing import Any, Callable, Dict, Tuple
-
-from pydantic import BaseModel, Field, PrivateAttr
-
-
-class Route(BaseModel):
-    condition: Callable[[Dict[str, Any]], bool]
-    pipeline: Any
-
-
-class Router(BaseModel):
-    routes: Dict[str, Route] = Field(
-        default_factory=dict,
-        description="Dictionary of route names to (condition, pipeline) tuples",
-    )
-    default: Any = Field(..., description="Default pipeline if no conditions are met")
-    _route_types: Dict[str, type] = PrivateAttr(default_factory=dict)
-
-    class Config:
-        arbitrary_types_allowed = True
-
-    def __init__(self, routes: Dict[str, Route], default: Any, **data):
-        super().__init__(routes=routes, default=default, **data)
-        self._check_copyable(default)
-        for name, route in routes.items():
-            self._check_copyable(route.pipeline)
-            self._route_types[name] = type(route.pipeline)
-
-    @staticmethod
-    def _check_copyable(obj: Any) -> None:
-        if not hasattr(obj, "copy") or not callable(getattr(obj, "copy")):
-            raise ValueError(f"Object of type {type(obj)} must have a 'copy' method")
-
-    def add_route(
-        self,
-        name: str,
-        condition: Callable[[Dict[str, Any]], bool],
-        pipeline: Any,
-    ) -> "Router":
-        """
-        Add a named route with its condition and corresponding pipeline to the router.
-
-        Args:
-            name: A unique name for this route
-            condition: A function that takes a dictionary input and returns a boolean
-            pipeline: The Pipeline to execute if the condition is met
-
-        Returns:
-            The Router instance for method chaining
-        """
-        self._check_copyable(pipeline)
-        self.routes[name] = Route(condition=condition, pipeline=pipeline)
-        self._route_types[name] = type(pipeline)
-        return self
-
-    def route(self, input_data: Dict[str, Any]) -> Tuple[Any, str]:
-        """
-        Evaluate the input against the conditions and return the appropriate pipeline.
-
-        Args:
-            input_data: The input dictionary to be evaluated
-
-        Returns:
-            A tuple containing the next Pipeline to be executed and the name of the route taken
-        """
-        for name, route in self.routes.items():
-            if route.condition(input_data):
-                return route.pipeline, name
-
-        return self.default, "default"
-
-    def copy(self) -> "Router":
-        """Create a deep copy of the Router."""
-        new_routes = {
-            name: Route(
-                condition=deepcopy(route.condition),
-                pipeline=route.pipeline.copy(),
-            )
-            for name, route in self.routes.items()
-        }
-        new_default = self.default.copy()
-
-        return Router(routes=new_routes, default=new_default)

src/crewai/task.py

@@ -1,6 +1,6 @@
 import datetime
 import json
-import os
+from pathlib import Path
 import threading
 import uuid
 from concurrent.futures import Future
@@ -393,12 +393,13 @@ class Task(BaseModel):
         if self.output_file is None:
             raise ValueError("output_file is not set.")
 
-        directory = os.path.dirname(self.output_file)  # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
+        resolved_path = Path(self.output_file).expanduser().resolve()
+        directory = resolved_path.parent
 
-        if directory and not os.path.exists(directory):
-            os.makedirs(directory)
+        if not directory.exists():
+            directory.mkdir(parents=True, exist_ok=True)
 
-        with open(self.output_file, "w", encoding="utf-8") as file:
+        with resolved_path.open("w", encoding="utf-8") as file:
             if isinstance(result, dict):
                 import json
 

src/crewai/translations/en.json

@@ -19,10 +19,11 @@
     "human_feedback": "You got human feedback on your work, re-evaluate it and give a new Final Answer when ready.\n {human_feedback}",
     "getting_input": "This is the agent's final answer: {final_answer}\n\n",
     "summarizer_system_message": "You are a helpful assistant that summarizes text.",
-    "sumamrize_instruction": "Summarize the following text, make sure to include all the important information: {group}",
+    "summarize_instruction": "Summarize the following text, make sure to include all the important information: {group}",
     "summary": "This is a summary of our conversation so far:\n{merged_summary}",
     "manager_request": "Your best answer to your coworker asking you this, accounting for the context shared.",
-    "formatted_task_instructions": "Ensure your final answer contains only the content in the following format: {output_format}\n\nEnsure the final output does not include any code block markers like ```json or ```python."
+    "formatted_task_instructions": "Ensure your final answer contains only the content in the following format: {output_format}\n\nEnsure the final output does not include any code block markers like ```json or ```python.",
+    "human_feedback_classification": "Determine if the following feedback indicates that the user is satisfied or if further changes are needed. Respond with 'True' if further changes are needed, or 'False' if the user is satisfied. **Important** Do not include any additional commentary outside of your 'True' or 'False' response.\n\nFeedback: \"{feedback}\""
   },
   "errors": {
     "force_final_answer_error": "You can't keep going, this was the best you could do.\n {formatted_answer.text}",

src/crewai/utilities/constants.py

@@ -2,3 +2,5 @@ TRAINING_DATA_FILE = "training_data.pkl"
 TRAINED_AGENTS_DATA_FILE = "trained_agents_data.pkl"
 DEFAULT_SCORE_THRESHOLD = 0.35
 KNOWLEDGE_DIRECTORY = "knowledge"
+MAX_LLM_RETRY = 3
+MAX_FILE_NAME_LENGTH = 255

tests/agent_test.py

@@ -3,19 +3,20 @@
 import os
 from unittest import mock
 from unittest.mock import patch
+
 import pytest
 
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.agents.parser import AgentAction, CrewAgentParser, OutputParserException
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
 from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.tools.tool_usage_events import ToolUsageFinished
 from crewai.utilities import RPMController
-from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.utilities.events import Emitter
 
 
@@ -985,8 +986,7 @@ def test_agent_definition_based_on_dict():
 # test for human input
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_human_input():
-    from unittest.mock import patch
-
+    # Agent configuration
     config = {
         "role": "test role",
         "goal": "test goal",
@@ -995,6 +995,7 @@ def test_agent_human_input():
 
     agent = Agent(**config)
 
+    # Task configuration with human input enabled
     task = Task(
         agent=agent,
         description="Say the word: Hi",
@@ -1002,11 +1003,26 @@ def test_agent_human_input():
         human_input=True,
     )
 
-    with patch.object(CrewAgentExecutor, "_ask_human_input") as mock_human_input:
-        mock_human_input.return_value = "Don't say hi, say Hello instead!"
+    # Side effect function for _ask_human_input to simulate multiple feedback iterations
+    feedback_responses = iter(
+        [
+            "Don't say hi, say Hello instead!",  # First feedback
+            "looks good",  # Second feedback to exit loop
+        ]
+    )
+
+    def ask_human_input_side_effect(*args, **kwargs):
+        return next(feedback_responses)
+
+    with patch.object(
+        CrewAgentExecutor, "_ask_human_input", side_effect=ask_human_input_side_effect
+    ) as mock_human_input:
+        # Execute the task
         output = agent.execute_task(task)
-        mock_human_input.assert_called_once()
-        assert output == "Hello"
+
+        # Assertions to ensure the agent behaves correctly
+        assert mock_human_input.call_count == 2  # Should have asked for feedback twice
+        assert output.strip().lower() == "hello"  # Final output should be 'Hello'
 
 
 def test_interpolate_inputs():

tests/cassettes/test_agent_human_input.yaml

@@ -9,7 +9,8 @@ interactions:
       is the expect criteria for your final answer: The word: Hi\nyou MUST return
       the actual complete content as the final answer, not a summary.\n\nBegin! This
       is VERY important to you, use the tools available and give your best Final Answer,
-      your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
+      your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
     headers:
       accept:
       - application/json
@@ -18,16 +19,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '774'
+      - '824'
       content-type:
       - application/json
-      cookie:
-      - __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.47.0
+      - OpenAI/Python 1.52.1
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -37,29 +35,34 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.47.0
+      - 1.52.1
       x-stainless-raw-response:
       - 'true'
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.12.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-AB7WMYMmqACvaemh26N6a62wxlxvx\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727213882,\n  \"model\": \"gpt-4o-2024-05-13\",\n
+    content: "{\n  \"id\": \"chatcmpl-AaqIIsTxhvf75xvuu7gQScIlRSKbW\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1733344190,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
       \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
       Answer: Hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
       \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      158,\n    \"completion_tokens\": 14,\n    \"total_tokens\": 172,\n    \"completion_tokens_details\":
-      {\n      \"reasoning_tokens\": 0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
+      158,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 170,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0705bf87c0\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c85eb4f58751cf3-GRU
+      - 8ece8cfc3b1f4532-ATL
       Connection:
       - keep-alive
       Content-Encoding:
@@ -67,7 +70,118 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 24 Sep 2024 21:38:03 GMT
+      - Wed, 04 Dec 2024 20:29:50 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
+        path=/; expires=Wed, 04-Dec-24 20:59:50 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '313'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999816'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_9fd9a8ee688045dcf7ac5f6fdf689372
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "Determine if the following
+      feedback indicates that the user is satisfied or if further changes are needed.
+      Respond with ''True'' if further changes are needed, or ''False'' if the user
+      is satisfied. **Important** Do not include any additional commentary outside
+      of your ''True'' or ''False'' response.\n\nFeedback: \"Don''t say hi, say Hello
+      instead!\""}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream":
+      false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '461'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
+        _cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AaqIIaQlLyoyPmk909PvAIfA2TmJL\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1733344190,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"True\",\n        \"refusal\": null\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 78,\n    \"completion_tokens\":
+      1,\n    \"total_tokens\": 79,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0705bf87c0\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ece8d060b5e4532-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 04 Dec 2024 20:29:50 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -76,28 +190,30 @@ interactions:
       - nosniff
       access-control-expose-headers:
       - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '262'
+      - '375'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
-      - '10000'
+      - '30000'
       x-ratelimit-limit-tokens:
-      - '30000000'
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - '9999'
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - '29999817'
+      - '149999898'
       x-ratelimit-reset-requests:
-      - 6ms
+      - 2ms
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_69b1deae1cc3cbf488cee975cd3b04df
+      - req_be7cb475e0859a82c37ee3f2871ea5ea
     http_version: HTTP/1.1
     status_code: 200
 - request:
@@ -110,8 +226,10 @@ interactions:
       is the expect criteria for your final answer: The word: Hi\nyou MUST return
       the actual complete content as the final answer, not a summary.\n\nBegin! This
       is VERY important to you, use the tools available and give your best Final Answer,
-      your job depends on it!\n\nThought:"}, {"role": "user", "content": "Feedback:
-      Don''t say hi, say Hello instead!"}], "model": "gpt-4o"}'
+      your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I now
+      can give a great answer  \nFinal Answer: Hi"}, {"role": "user", "content": "Feedback:
+      Don''t say hi, say Hello instead!"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
+      "stream": false}'
     headers:
       accept:
       - application/json
@@ -120,16 +238,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '849'
+      - '986'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
-        _cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
+      - __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
+        _cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.47.0
+      - OpenAI/Python 1.52.1
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -139,29 +257,34 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.47.0
+      - 1.52.1
       x-stainless-raw-response:
       - 'true'
+      x-stainless-retry-count:
+      - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.12.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-AB7WNec1Ohw0pEU91kuCTuts2hXWM\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727213883,\n  \"model\": \"gpt-4o-2024-05-13\",\n
+    content: "{\n  \"id\": \"chatcmpl-AaqIJAAxpVfUOdrsgYKHwfRlHv4RS\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1733344191,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
       \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
-      Answer: Hello\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      172,\n    \"completion_tokens\": 14,\n    \"total_tokens\": 186,\n    \"completion_tokens_details\":
-      {\n      \"reasoning_tokens\": 0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
+      \"assistant\",\n        \"content\": \"Thought: I now can give a great answer
+      \ \\nFinal Answer: Hello\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      188,\n    \"completion_tokens\": 14,\n    \"total_tokens\": 202,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0705bf87c0\"\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8c85eb52cd7c1cf3-GRU
+      - 8ece8d090fc34532-ATL
       Connection:
       - keep-alive
       Content-Encoding:
@@ -169,7 +292,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 24 Sep 2024 21:38:03 GMT
+      - Wed, 04 Dec 2024 20:29:51 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -178,28 +301,134 @@ interactions:
       - nosniff
       access-control-expose-headers:
       - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '261'
+      - '484'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
       - max-age=31536000; includeSubDomains; preload
       x-ratelimit-limit-requests:
-      - '10000'
+      - '30000'
       x-ratelimit-limit-tokens:
-      - '30000000'
+      - '150000000'
       x-ratelimit-remaining-requests:
-      - '9999'
+      - '29999'
       x-ratelimit-remaining-tokens:
-      - '29999806'
+      - '149999793'
       x-ratelimit-reset-requests:
-      - 6ms
+      - 2ms
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_11a316792b5f54af94cce0c702aec290
+      - req_5bf4a565ad6c2567a1ed204ecac89134
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "Determine if the following
+      feedback indicates that the user is satisfied or if further changes are needed.
+      Respond with ''True'' if further changes are needed, or ''False'' if the user
+      is satisfied. **Important** Do not include any additional commentary outside
+      of your ''True'' or ''False'' response.\n\nFeedback: \"looks good\""}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '439'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
+        _cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AaqIJqyG8vl9mxj2qDPZgaxyNLLIq\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1733344191,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"False\",\n        \"refusal\": null\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 73,\n    \"completion_tokens\":
+      1,\n    \"total_tokens\": 74,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0705bf87c0\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ece8d0cfdeb4532-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 04 Dec 2024 20:29:51 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '341'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999902'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_5554bade8ceda00cf364b76a51b708ff
     http_version: HTTP/1.1
     status_code: 200
 version: 1