Update feature_request.md

Add both Bug and Feature templates

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,35 @@
+---
+name: Bug report
+about: Create a report to help us improve CrewAI
+title: "[BUG]"
+labels: bug
+assignees: ''
+
+---
+
+**Description**
+Provide a clear and concise description of what the bug is.
+
+**Steps to Reproduce**
+Provide a step-by-step process to reproduce the behavior:
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots/Code snippets**
+If applicable, add screenshots or code snippets to help explain your problem.
+
+**Environment Details:**
+- **Operating System**: [e.g., Ubuntu 20.04, macOS Catalina, Windows 10]
+- **Python Version**: [e.g., 3.8, 3.9, 3.10]
+- **crewAI Version**: [e.g., 0.30.11]
+- **crewAI Tools Version**: [e.g., 0.2.6]
+
+**Logs**
+Include relevant logs or error messages if applicable.
+
+**Possible Solution**
+Have a solution in mind? Please suggest it here, or write "None".
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,21 @@
+---
+name: Feature request
+about: Suggest a Feature to improve CrewAI
+title: "[FEAT]"
+labels: feature-request, improvement
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+If possible attach the Issue related to it
+
+**Describe the solution you'd like / Use-case**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

README.md

@@ -254,7 +254,7 @@ pip install dist/*.tar.gz
 
 CrewAI uses anonymous telemetry to collect usage data with the main purpose of helping us improve the library by focusing our efforts on the most used features, integrations and tools.
 
-There is NO data being collected on the prompts, tasks descriptions agents backstories or goals nor tools usage, no API calls, nor responses nor any data that is being processed by the agents, nor any secrets and env vars.
+It's pivotal to understand that **NO data is collected** concerning prompts, task descriptions, agents' backstories or goals, usage of tools, API calls, responses, any data processed by the agents, or secrets and environment variables, with the exception of the conditions mentioned. When the `share_crew` feature is enabled, detailed data including task descriptions, agents' backstories or goals, and other specific attributes are collected to provide deeper insights while respecting user privacy. We don't offer a way to disable it now, but we will in the future.
 
 Data collected includes:
 
@@ -279,7 +279,7 @@ Data collected includes:
 - Tools names available
   - Understand out of the publically available tools, which ones are being used the most so we can improve them
 
-Users can opt-in sharing the complete telemetry data by setting the `share_crew` attribute to `True` on their Crews.
+Users can opt-in to Further Telemetry, sharing the complete telemetry data by setting the `share_crew` attribute to `True` on their Crews. Enabling `share_crew` results in the collection of detailed crew and task execution data, including `goal`, `backstory`, `context`, and `output` of tasks. This enables a deeper insight into usage patterns while respecting the user's choice to share.
 
 ## License
 

docs/core-concepts/Agents.md

@@ -114,7 +114,7 @@ from langchain.agents import load_tools
 langchain_tools = load_tools(["google-serper"], llm=llm)
 
 agent1 = CustomAgent(
-    role="backstory agent",
+    role="agent role",
     goal="who is {input}?",
     backstory="agent backstory",
     verbose=True,
@@ -127,7 +127,7 @@ task1 = Task(
 )
 
 agent2 = Agent(
-    role="bio agent",
+    role="agent role",
     goal="summarize the short bio for {input} and if needed do more research",
     backstory="agent backstory",
     verbose=True,

docs/core-concepts/Crews.md

@@ -33,6 +33,7 @@ A crew in crewAI represents a collaborative group of agents working together to
 | **Manager Callbacks** _(optional)_    | `manager_callbacks`    | `manager_callbacks` takes a list of callback handlers to be executed by the manager agent when a hierarchical process is used.                                                                                                                            |
 | **Prompt File** _(optional)_          | `prompt_file`          | Path to the prompt JSON file to be used for the crew.                                                                                                                                                                                                     |
 | **Planning** *(optional)*             | `planning`             |  Adds planning ability to the Crew. When activated before each Crew iteration, all Crew data is sent to an AgentPlanner that will plan the tasks and this plan will be added to each task description.
+| **Planning LLM** *(optional)*         | `planning_llm`         | The language model used by the AgentPlanner in a planning process. |
 
 !!! note "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.
@@ -136,7 +137,7 @@ crew = Crew(
     verbose=2
 )
 
-result = crew.kickoff()
+crew_output = crew.kickoff()
 
 # Accessing the crew output
 print(f"Raw Output: {crew_output.raw}")

docs/core-concepts/Planning.md

@@ -23,6 +23,25 @@ my_crew = Crew(
 
 From this point on, your crew will have planning enabled, and the tasks will be planned before each iteration.
 
+#### Planning LLM
+
+Now you can define the LLM that will be used to plan the tasks. You can use any ChatOpenAI LLM model available.
+
+```python
+from crewai import Crew, Agent, Task, Process
+from langchain_openai import ChatOpenAI
+
+# Assemble your crew with planning capabilities and custom LLM
+my_crew = Crew(
+    agents=self.agents,
+    tasks=self.tasks,
+    process=Process.sequential,
+    planning=True,
+    planning_llm=ChatOpenAI(model="gpt-4o")
+)
+```
+
+
 ### Example
 
 When running the base case example, you will see something like the following output, which represents the output of the AgentPlanner responsible for creating the step-by-step logic to add to the Agents tasks.

docs/getting-started/Installing-CrewAI.md

@@ -18,4 +18,7 @@ pip install crewai
 # Install the main crewAI package and the tools package
 # that includes a series of helpful tools for your agents
 pip install 'crewai[tools]'
+
+# Alternatively, you can also use:
+pip install crewai crewai-tools
 ```

docs/getting-started/Start-a-New-CrewAI-Project-Template-Method.md

@@ -0,0 +1,255 @@
+---
+title: Starting a New CrewAI Project - Using Template
+description: A comprehensive guide to starting a new CrewAI project, including the latest updates and project setup methods.
+---
+
+# Starting Your CrewAI Project
+
+Welcome to the ultimate guide for starting a new CrewAI project. This document will walk you through the steps to create, customize, and run your CrewAI project, ensuring you have everything you need to get started.
+
+Beforre we start there are a couple of things to note:
+
+1. CrewAI is a Python package and requires Python >=3.10 and <=3.13 to run.
+2. The preferred way of setting up CrewAI is using the `crewai create` command.This will create a new project folder and install a skeleton template for you to work on.
+
+## Prerequisites
+
+Before getting started with CrewAI, make sure that you have installed it via pip:
+
+```shell
+$ pip install crewai crewai-tools
+```
+
+### Virtual Environments
+It is highly recommended that you use virtual environments to ensure that your CrewAI project is isolated from other projects and dependencies. Virtual environments provide a clean, separate workspace for each project, preventing conflicts between different versions of packages and libraries. This isolation is crucial for maintaining consistency and reproducibility in your development process. You have multiple options for setting up virtual environments depending on your operating system and Python version:
+
+1. Use venv (Python's built-in virtual environment tool):
+   venv is included with Python 3.3 and later, making it a convenient choice for many developers. It's lightweight and easy to use, perfect for simple project setups.
+
+   To set up virtual environments with venv, refer to the official [Python documentation](https://docs.python.org/3/tutorial/venv.html).
+
+2. Use Conda (A Python virtual environment manager):
+   Conda is an open-source package manager and environment management system for Python. It's widely used by data scientists, developers, and researchers to manage dependencies and environments in a reproducible way.
+
+   To set up virtual environments with Conda, refer to the official [Conda documentation](https://docs.conda.io/projects/conda/en/stable/user-guide/getting-started.html).
+
+3. Use Poetry (A Python package manager and dependency management tool):
+   Poetry is an open-source Python package manager that simplifies the installation of packages and their dependencies. Poetry offers a convenient way to manage virtual environments and dependencies.
+   Poetry is CrewAI's prefered tool for package / dependancy management in CrewAI.
+
+### Code IDEs
+
+Most users of CrewAI a Code Editor / Integrated Development Environment (IDE) for building there Crews. You can use any code IDE of your choice. Seee below for some popular options for Code Editors / Integrated Development Environments (IDE):
+
+- [Visual Studio Code](https://code.visualstudio.com/) - Most popular
+- [PyCharm](https://www.jetbrains.com/pycharm/)
+- [Cursor AI](https://cursor.com)
+
+Pick one that suits your style and needs.
+
+## Creating a New Project
+In this example we will be using Venv as our virtual environment manager.
+
+To setup a virtual environment, run the following CLI command:
+
+```shell
+$ python3 -m venv <venv-name>
+```
+
+Activate your virtual environment by running the following CLI command:
+
+```shell
+$ source <venv-name>/bin/activate
+```
+
+Now, to create a new CrewAI project, run the following CLI command:
+
+```shell
+$ crewai create <project_name>
+```
+
+This command will create a new project folder with the following structure:
+
+```shell
+my_project/
+├── .gitignore
+├── pyproject.toml
+├── README.md
+└── src/
+    └── my_project/
+        ├── __init__.py
+        ├── main.py
+        ├── crew.py
+        ├── tools/
+        │   ├── custom_tool.py
+        │   └── __init__.py
+        └── config/
+            ├── agents.yaml
+            └── tasks.yaml
+```
+
+You can now start developing your project by editing the files in the `src/my_project` folder. The `main.py` file is the entry point of your project, and the `crew.py` file is where you define your agents and tasks.
+
+## Customizing Your Project
+
+To customize your project, you can:
+- Modify `src/my_project/config/agents.yaml` to define your agents.
+- Modify `src/my_project/config/tasks.yaml` to define your tasks.
+- Modify `src/my_project/crew.py` to add your own logic, tools, and specific arguments.
+- Modify `src/my_project/main.py` to add custom inputs for your agents and tasks.
+- Add your environment variables into the `.env` file.
+
+### Example: Defining Agents and Tasks
+
+#### agents.yaml
+
+```yaml
+researcher:
+  role: >
+    Job Candidate Researcher
+  goal: >
+    Find potential candidates for the job
+  backstory: >
+    You are adept at finding the right candidates by exploring various online
+    resources. Your skill in identifying suitable candidates ensures the best
+    match for job positions.
+```
+
+#### tasks.yaml
+
+```yaml
+research_candidates_task:
+  description: >
+    Conduct thorough research to find potential candidates for the specified job.
+    Utilize various online resources and databases to gather a comprehensive list of potential candidates.
+    Ensure that the candidates meet the job requirements provided.
+
+    Job Requirements:
+    {job_requirements}
+  expected_output: >
+    A list of 10 potential candidates with their contact information and brief profiles highlighting their suitability.
+  agent: researcher # THIS NEEDS TO MATCH THE AGENT NAME IN THE AGENTS.YAML FILE AND THE AGENT DEFINED IN THE Crew.PY FILE
+  context: # THESE NEED TO MATCH THE TASK NAMES DEFINED ABOVE AND THE TASKS.YAML FILE AND THE TASK DEFINED IN THE Crew.PY FILE
+    - researcher
+```
+
+### Referencing Variables:
+Your defined functions with the same name will be used. For example, you can reference the agent for specific tasks from task.yaml file. Ensure your annotated agent and function name is the same otherwise your task wont recognize the reference properly.
+
+#### Example References
+agent.yaml
+```yaml
+email_summarizer:
+    role: >
+      Email Summarizer
+    goal: >
+      Summarize emails into a concise and clear summary
+    backstory: >
+      You will create a 5 bullet point summary of the report
+    llm: mixtal_llm
+```
+
+task.yaml
+```yaml
+email_summarizer_task:
+    description: >
+      Summarize the email into a 5 bullet point summary
+    expected_output: >
+      A 5 bullet point summary of the email
+    agent: email_summarizer
+    context:
+      - reporting_task
+      - research_task
+```
+
+Use the annotations are used to properly reference the agent and task in the crew.py file.
+
+### Annotations include:
+* @agent
+* @task
+* @crew
+* @llm
+* @tool
+* @callback
+* @output_json
+* @output_pydantic
+* @cache_handler
+
+
+crew.py
+```py
+...
+    @llm
+    def mixtal_llm(self):
+        return ChatGroq(temperature=0, model_name="mixtral-8x7b-32768")
+
+    @agent
+    def email_summarizer(self) -> Agent:
+        return Agent(
+            config=self.agents_config["email_summarizer"],
+        )
+    ## ...other tasks defined
+    @task
+    def email_summarizer_task(self) -> Task:
+        return Task(
+            config=self.tasks_config["email_summarizer_task"],
+        )
+...
+```
+
+
+
+## Installing Dependencies
+
+To install the dependencies for your project, you can use Poetry. First, navigate to your project directory:
+
+```shell
+$ cd my_project
+$ poetry lock
+$ poetry install
+```
+
+This will install the dependencies specified in the `pyproject.toml` file.
+
+## Interpolating Variables
+
+Any variable interpolated in your `agents.yaml` and `tasks.yaml` files like `{variable}` will be replaced by the value of the variable in the `main.py` file.
+
+#### agents.yaml
+
+```yaml
+research_task:
+  description: >
+    Conduct a thorough research about the customer and competitors in the context
+    of {customer_domain}.
+    Make sure you find any interesting and relevant information given the
+    current year is 2024.
+  expected_output: >
+    A complete report on the customer and their customers and competitors,
+    including their demographics, preferences, market positioning and audience engagement.
+```
+
+#### main.py
+
+```python
+# main.py
+def run():
+    inputs = {
+        "customer_domain": "crewai.com"
+    }
+    MyProjectCrew(inputs).crew().kickoff(inputs=inputs)
+```
+
+## Running Your Project
+
+To run your project, use the following command:
+
+```shell
+$ poetry run my_project
+```
+
+This will initialize your crew of AI agents and begin task execution as defined in your configuration in the `main.py` file.
+
+## Deploying Your Project
+
+The easiest way to deploy your crew is through [CrewAI+](https://www.crewai.com/crewaiplus), where you can deploy your crew in a few clicks.

docs/how-to/Create-Custom-Tools.md

@@ -7,6 +7,7 @@ description: Comprehensive guide on crafting, using, and managing custom tools w
 This guide provides detailed instructions on creating custom tools for the crewAI framework and how to efficiently manage and utilize these tools, incorporating the latest functionalities such as tool delegation, error handling, and dynamic tool calling. It also highlights the importance of collaboration tools, enabling agents to perform a wide range of actions.
 
 ### Prerequisites
+
 Before creating your own tools, ensure you have the crewAI extra tools package installed:
 
 ```bash
@@ -31,7 +32,7 @@ class MyCustomTool(BaseTool):
 
 ### Using the `tool` Decorator
 
-Alternatively, use the `tool` decorator for a direct approach to create tools. This requires specifying attributes and the tool's logic within a function.
+Alternatively, you can use the tool decorator `@tool`. This approach allows you to define the tool's attributes and functionality directly within a function, offering a concise and efficient way to create specialized tools tailored to your needs.
 
 ```python
 from crewai_tools import tool

docs/how-to/Creating-a-Crew-and-kick-it-off.md

@@ -1,84 +0,0 @@
----
-title: Assembling and Activating Your CrewAI Team
-description: A comprehensive guide to creating a dynamic CrewAI team for your projects, with updated functionalities including verbose mode, memory capabilities, asynchronous execution, output customization, language model configuration, code execution, integration with third-party agents, and improved task management.
----
-
-## Introduction
-Embark on your CrewAI journey by setting up your environment and initiating your AI crew with the latest features. This guide ensures a smooth start, incorporating all recent updates for an enhanced experience, including code execution capabilities, integration with third-party agents, and advanced task management.
-
-## Step 0: Installation
-Install CrewAI and any necessary packages for your project. CrewAI is compatible with Python >=3.10,<=3.13.
-
-```shell
-pip install crewai
-pip install 'crewai[tools]'
-```
-
-## Step 1: Assemble Your Agents
-Define your agents with distinct roles, backstories, and enhanced capabilities. The Agent class now supports a wide range of attributes for fine-tuned control over agent behavior and interactions, including code execution and integration with third-party agents.
-
-```python
-import os
-from langchain.llms import OpenAI
-from crewai import Agent
-from crewai_tools import SerperDevTool, BrowserbaseLoadTool, EXASearchTool
-
-os.environ["OPENAI_API_KEY"] = "Your OpenAI Key"
-os.environ["SERPER_API_KEY"] = "Your Serper Key"
-os.environ["BROWSERBASE_API_KEY"] = "Your BrowserBase Key"
-os.environ["BROWSERBASE_PROJECT_ID"] = "Your BrowserBase Project Id"
-
-search_tool = SerperDevTool()
-browser_tool = BrowserbaseLoadTool()
-exa_search_tool = EXASearchTool()
-
-# Creating a senior researcher agent with advanced configurations
-researcher = Agent(
-    role='Senior Researcher',
-    goal='Uncover groundbreaking technologies in {topic}',
-    backstory=("Driven by curiosity, you're at the forefront of innovation, "
-               "eager to explore and share knowledge that could change the world."),
-    memory=True,
-    verbose=True,
-    allow_delegation=False,
-    tools=[search_tool, browser_tool],
-    allow_code_execution=False,  # New attribute for enabling code execution
-    max_iter=15,  # Maximum number of iterations for task execution
-    max_rpm=100,  # Maximum requests per minute
-    max_execution_time=3600,  # Maximum execution time in seconds
-    system_template="Your custom system template here",  # Custom system template
-    prompt_template="Your custom prompt template here",  # Custom prompt template
-    response_template="Your custom response template here",  # Custom response template
-)
-
-# Creating a writer agent with custom tools and specific configurations
-writer = Agent(
-    role='Writer',
-    goal='Narrate compelling tech stories about {topic}',
-    backstory=("With a flair for simplifying complex topics, you craft engaging "
-               "narratives that captivate and educate, bringing new discoveries to light."),
-    verbose=True,
-    allow_delegation=False,
-    memory=True,
-    tools=[exa_search_tool],
-    function_calling_llm=OpenAI(model_name="gpt-3.5-turbo"),  # Separate LLM for function calling
-)
-
-# Setting a specific manager agent
-manager = Agent(
-  role='Manager',
-  goal='Ensure the smooth operation and coordination of the team',
-  verbose=True,
-  backstory=(
-    "As a seasoned project manager, you excel in organizing "
-    "tasks, managing timelines, and ensuring the team stays on track."
-  ),
-  allow_code_execution=True,  # Enable code execution for the manager
-)
-```
-
-### New Agent Attributes and Features
-
-1. `allow_code_execution`: Enable or disable code execution capabilities for the agent (default is False).
-2. `max_execution_time`: Set a maximum execution time (in seconds) for the agent to complete a task.
-3. `function_calling_llm`: Specify a separate language model for function calling.

docs/how-to/Force-Tool-Ouput-as-Result.md

@@ -7,7 +7,7 @@ description: Learn how to force tool output as the result in of an Agent's task
 In CrewAI, you can force the output of a tool as the result of an agent's task. This feature is useful when you want to ensure that the tool output is captured and returned as the task result, and avoid the agent modifying the output during the task execution.
 
 ## Forcing Tool Output as Result
-To force the tool output as the result of an agent's task, you can set the `force_tool_output` parameter to `True` when creating the task. This parameter ensures that the tool output is captured and returned as the task result, without any modifications by the agent.
+To force the tool output as the result of an agent's task, you can set the `result_as_answer` parameter to `True` when creating the agent. This parameter ensures that the tool output is captured and returned as the task result, without any modifications by the agent.
 
 Here's an example of how to force the tool output as the result of an agent's task:
 
@@ -16,7 +16,7 @@ Here's an example of how to force the tool output as the result of an agent's ta
 # Define a custom tool that returns the result as the answer
 coding_agent =Agent(
         role="Data Scientist",
-        goal="Product amazing resports on AI",
+        goal="Product amazing reports on AI",
         backstory="You work with data and AI",
         tools=[MyCustomTool(result_as_answer=True)],
     )

docs/how-to/LLM-Connections.md

@@ -6,33 +6,25 @@ description: Comprehensive guide on integrating CrewAI with various Large Langua
 ## Connect CrewAI to LLMs
 
 !!! note "Default LLM"
-    By default, CrewAI uses OpenAI's GPT-4 model (specifically, the model specified by the OPENAI_MODEL_NAME environment variable, defaulting to "gpt-4o") for language processing. You can configure your agents to use a different model or API as described in this guide.
+    By default, CrewAI uses OpenAI's GPT-4o model (specifically, the model specified by the OPENAI_MODEL_NAME environment variable, defaulting to "gpt-4o") for language processing. You can configure your agents to use a different model or API as described in this guide.
+    By default, CrewAI uses OpenAI's GPT-4 model (specifically, the model specified by the OPENAI_MODEL_NAME environment variable, defaulting to "gpt-4") for language processing. You can configure your agents to use a different model or API as described in this guide.
 
-CrewAI offers flexibility in connecting to various LLMs, including local models via [Ollama](https://ollama.ai) and different APIs like Azure. It's compatible with all [LangChain LLM](https://python.langchain.com/docs/integrations/llms/) components, enabling diverse integrations for tailored AI solutions.
+CrewAI provides extensive versatility in integrating with various Language Models (LLMs), including local options through Ollama such as  Llama and Mixtral to cloud-based solutions like Azure. Its compatibility extends to all [LangChain LLM components](https://python.langchain.com/v0.2/docs/integrations/llms/), offering a wide range of integration possibilities for customized AI applications.
 
-## CrewAI Agent Overview
+The platform supports connections to an array of Generative AI models, including:
 
-The `Agent` class is the cornerstone for implementing AI solutions in CrewAI. Here's a comprehensive overview of the Agent class attributes and methods:
+ - OpenAI's suite of advanced language models
+ - Anthropic's cutting-edge AI offerings
+ - Ollama's diverse range of locally-hosted generative model & embeddings
+ - LM Studio's diverse range of locally hosted generative models & embeddings
+ - Groq's Super Fast LLM offerings
+ - Azures' generative AI offerings
+ - HuggingFace's generative AI offerings
 
-- **Attributes**:
+This broad spectrum of LLM options enables users to select the most suitable model for their specific needs, whether prioritizing local deployment, specialized capabilities, or cloud-based scalability.
-    - `role`: Defines the agent's role within the solution.
-    - `goal`: Specifies the agent's objective.
-    - `backstory`: Provides a background story to the agent.
-    - `cache` *Optional*: Determines whether the agent should use a cache for tool usage. Default is `True`.
-    - `max_rpm` *Optional*: Maximum number of requests per minute the agent's execution should respect. Optional.
-    - `verbose` *Optional*: Enables detailed logging of the agent's execution. Default is `False`.
-    - `allow_delegation` *Optional*: Allows the agent to delegate tasks to other agents, default is `True`.
-    - `tools`: Specifies the tools available to the agent for task execution. Optional.
-    - `max_iter` *Optional*: Maximum number of iterations for an agent to execute a task, default is 25.
-    - `max_execution_time` *Optional*: Maximum execution time for an agent to execute a task. Optional.
-    - `step_callback` *Optional*: Provides a callback function to be executed after each step. Optional.
-    - `llm` *Optional*: Indicates the Large Language Model the agent uses. By default, it uses the GPT-4 model defined in the environment variable "OPENAI_MODEL_NAME".
-    - `function_calling_llm` *Optional* :  Will turn the ReAct CrewAI agent into a function-calling agent.
-    - `callbacks` *Optional*: A list of callback functions from the LangChain library that are triggered during the agent's execution process.
-    - `system_template` *Optional*: Optional string to define the system format for the agent.
-    - `prompt_template` *Optional*: Optional string to define the prompt format for the agent.
-    - `response_template` *Optional*: Optional string to define the response format for the agent.
 
+## Changing the default LLM
+The default LLM is provided through the `langchain openai` package, which is installed by default when you install CrewAI. You can change this default LLM to a different model or API by setting the `OPENAI_MODEL_NAME` environment variable. This straightforward process allows you to harness the power of different OpenAI models, enhancing the flexibility and capabilities of your CrewAI implementation.
 ```python
 # Required
 os.environ["OPENAI_MODEL_NAME"]="gpt-4-0125-preview"
@@ -45,30 +37,27 @@ example_agent = Agent(
   verbose=True
 )
 ```
+## Ollama Local Integration
+Ollama is preferred for local LLM integration, offering customization and privacy benefits. To integrate Ollama with CrewAI, you will need the `langchain-ollama` package. You can then set the following environment variables to connect to your Ollama instance running locally on port 11434.
 
-## Ollama Integration
-Ollama is preferred for local LLM integration, offering customization and privacy benefits. To integrate Ollama with CrewAI, set the appropriate environment variables as shown below.
-
-### Setting Up Ollama
-- **Environment Variables Configuration**: To integrate Ollama, set the following environment variables:
 ```sh
-OPENAI_API_BASE='http://localhost:11434'
+os.environ[OPENAI_API_BASE]='http://localhost:11434'
-OPENAI_MODEL_NAME='llama2'  # Adjust based on available model
+os.environ[OPENAI_MODEL_NAME]='llama2'  # Adjust based on available model
-OPENAI_API_KEY=''
+os.environ[OPENAI_API_KEY]='' # No API Key required for Ollama
 ```
 
-## Ollama Integration (ex. for using Llama 2 locally)
+## Ollama Integration Step by Step (ex. for using Llama 3.1 8B locally)
-1. [Download Ollama](https://ollama.com/download).   
+1. [Download and install Ollama](https://ollama.com/download).   
-2. After setting up the Ollama, Pull the Llama2 by typing following lines into the terminal ```ollama pull llama2```.   
+2. After setting up the Ollama, Pull the Llama3.1 8B model by typing following lines into your terminal ```ollama run llama3.1```.   
-3. Enjoy your free Llama2 model that powered up by excellent agents from crewai.   
+3. Llama3.1 should now be served locally on `http://localhost:11434`
 ```
 from crewai import Agent, Task, Crew
-from langchain.llms import Ollama
+from langchain_ollama import ChatOllama
 import os
 os.environ["OPENAI_API_KEY"] = "NA"
 
 llm = Ollama(
-    model = "llama2",
+    model = "llama3.1",
     base_url = "http://localhost:11434")
 
 general_agent = Agent(role = "Math Professor",
@@ -98,13 +87,14 @@ There are a couple of different ways you can use HuggingFace to host your LLM.
 
 ### Your own HuggingFace endpoint
 ```python
-from langchain_community.llms import HuggingFaceEndpoint
+from langchain_huggingface import HuggingFaceEndpoint,
 
 llm = HuggingFaceEndpoint(
-    endpoint_url="<YOUR_ENDPOINT_URL_HERE>",
+    repo_id="microsoft/Phi-3-mini-4k-instruct",
-    huggingfacehub_api_token="<HF_TOKEN_HERE>",
     task="text-generation",
-    max_new_tokens=512
+    max_new_tokens=512,
+    do_sample=False,
+    repetition_penalty=1.03,
 )
 
 agent = Agent(
@@ -115,66 +105,50 @@ agent = Agent(
 )
 ```
 
-### From HuggingFaceHub endpoint
-```python
-from langchain_community.llms import HuggingFaceHub
-
-llm = HuggingFaceHub(
-    repo_id="HuggingFaceH4/zephyr-7b-beta",
-    huggingfacehub_api_token="<HF_TOKEN_HERE>",
-    task="text-generation",
-)
-```
-
 ## OpenAI Compatible API Endpoints
 Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, Groq, and Mistral AI.
 
 ### Configuration Examples
 #### FastChat
 ```sh
-OPENAI_API_BASE="http://localhost:8001/v1"
+os.environ[OPENAI_API_BASE]="http://localhost:8001/v1"
-OPENAI_MODEL_NAME='oh-2.5m7b-q51'
+os.environ[OPENAI_MODEL_NAME]='oh-2.5m7b-q51'
-OPENAI_API_KEY=NA
+os.environ[OPENAI_API_KEY]=NA
 ```
 
 #### LM Studio
 Launch [LM Studio](https://lmstudio.ai) and go to the Server tab. Then select a model from the dropdown menu and wait for it to load. Once it's loaded, click the green Start Server button and use the URL, port, and API key that's shown (you can modify them). Below is an example of the default settings as of LM Studio 0.2.19:
 ```sh
-OPENAI_API_BASE="http://localhost:1234/v1"
+os.environ[OPENAI_API_BASE]="http://localhost:1234/v1"
-OPENAI_API_KEY="lm-studio"
+os.environ[OPENAI_API_KEY]="lm-studio"
 ```
 
 #### Groq API
 ```sh
-OPENAI_API_KEY=your-groq-api-key
+os.environ[OPENAI_API_KEY]=your-groq-api-key
-OPENAI_MODEL_NAME='llama3-8b-8192'
+os.environ[OPENAI_MODEL_NAME]='llama3-8b-8192'
-OPENAI_API_BASE=https://api.groq.com/openai/v1
+os.environ[OPENAI_API_BASE]=https://api.groq.com/openai/v1
 ```
 
 #### Mistral API
 ```sh
-OPENAI_API_KEY=your-mistral-api-key
+os.environ[OPENAI_API_KEY]=your-mistral-api-key
-OPENAI_API_BASE=https://api.mistral.ai/v1
+os.environ[OPENAI_API_BASE]=https://api.mistral.ai/v1
-OPENAI_MODEL_NAME="mistral-small"
+os.environ[OPENAI_MODEL_NAME]="mistral-small"
 ```
 
 ### Solar
-```python
+```sh
 from langchain_community.chat_models.solar import SolarChat
-# Initialize language model
+```
-os.environ["SOLAR_API_KEY"] = "your-solar-api-key"
+```sh
-llm = SolarChat(max_tokens=1024)
+os.environ[SOLAR_API_BASE]="https://api.upstage.ai/v1/solar"
+os.environ[SOLAR_API_KEY]="your-solar-api-key"
+```
 
 # Free developer API key available here: https://console.upstage.ai/services/solar
 # Langchain Example: https://github.com/langchain-ai/langchain/pull/18556
-```
 
-### text-gen-web-ui
-```sh
-OPENAI_API_BASE=http://localhost:5000/v1
-OPENAI_MODEL_NAME=NA
-OPENAI_API_KEY=NA
-```
 
 ### Cohere
 ```python
@@ -190,10 +164,11 @@ llm = ChatCohere()
 ### Azure Open AI Configuration
 For Azure OpenAI API integration, set the following environment variables:
 ```sh
-AZURE_OPENAI_VERSION="2022-12-01"
+
-AZURE_OPENAI_DEPLOYMENT=""
+os.environ[AZURE_OPENAI_DEPLOYMENT] = "You deployment"
-AZURE_OPENAI_ENDPOINT=""
+os.environ["OPENAI_API_VERSION"] = "2023-12-01-preview"
-AZURE_OPENAI_KEY=""
+os.environ["AZURE_OPENAI_ENDPOINT"] = "Your Endpoint"
+os.environ["AZURE_OPENAI_API_KEY"] = "<Your API Key>"
 ```
 
 ### Example Agent with Azure LLM
@@ -216,6 +191,5 @@ azure_agent = Agent(
   llm=azure_llm
 )
 ```
-
 ## Conclusion
 Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.

docs/how-to/Start-a-New-CrewAI-Project.md

@@ -1,137 +0,0 @@
----
-title: Starting a New CrewAI Project
-description: A comprehensive guide to starting a new CrewAI project, including the latest updates and project setup methods.
----
-
-# Starting Your CrewAI Project
-
-Welcome to the ultimate guide for starting a new CrewAI project. This document will walk you through the steps to create, customize, and run your CrewAI project, ensuring you have everything you need to get started.
-
-## Prerequisites
-
-We assume you have already installed CrewAI. If not, please refer to the [installation guide](https://docs.crewai.com/how-to/Installing-CrewAI/) to install CrewAI and its dependencies.
-
-## Creating a New Project
-
-To create a new project, run the following CLI command:
-
-```shell
-$ crewai create my_project
-```
-
-This command will create a new project folder with the following structure:
-
-```shell
-my_project/
-├── .gitignore
-├── pyproject.toml
-├── README.md
-└── src/
-    └── my_project/
-        ├── __init__.py
-        ├── main.py
-        ├── crew.py
-        ├── tools/
-        │   ├── custom_tool.py
-        │   └── __init__.py
-        └── config/
-            ├── agents.yaml
-            └── tasks.yaml
-```
-
-You can now start developing your project by editing the files in the `src/my_project` folder. The `main.py` file is the entry point of your project, and the `crew.py` file is where you define your agents and tasks.
-
-## Customizing Your Project
-
-To customize your project, you can:
-- Modify `src/my_project/config/agents.yaml` to define your agents.
-- Modify `src/my_project/config/tasks.yaml` to define your tasks.
-- Modify `src/my_project/crew.py` to add your own logic, tools, and specific arguments.
-- Modify `src/my_project/main.py` to add custom inputs for your agents and tasks.
-- Add your environment variables into the `.env` file.
-
-### Example: Defining Agents and Tasks
-
-#### agents.yaml
-
-```yaml
-researcher:
-  role: >
-    Job Candidate Researcher
-  goal: >
-    Find potential candidates for the job
-  backstory: >
-    You are adept at finding the right candidates by exploring various online
-    resources. Your skill in identifying suitable candidates ensures the best
-    match for job positions.
-```
-
-#### tasks.yaml
-
-```yaml
-research_candidates_task:
-  description: >
-    Conduct thorough research to find potential candidates for the specified job.
-    Utilize various online resources and databases to gather a comprehensive list of potential candidates.
-    Ensure that the candidates meet the job requirements provided.
-
-    Job Requirements:
-    {job_requirements}
-  expected_output: >
-    A list of 10 potential candidates with their contact information and brief profiles highlighting their suitability.
-```
-
-## Installing Dependencies
-
-To install the dependencies for your project, you can use Poetry. First, navigate to your project directory:
-
-```shell
-$ cd my_project
-$ poetry lock
-$ poetry install
-```
-
-This will install the dependencies specified in the `pyproject.toml` file.
-
-## Interpolating Variables
-
-Any variable interpolated in your `agents.yaml` and `tasks.yaml` files like `{variable}` will be replaced by the value of the variable in the `main.py` file.
-
-#### agents.yaml
-
-```yaml
-research_task:
-  description: >
-    Conduct a thorough research about the customer and competitors in the context
-    of {customer_domain}.
-    Make sure you find any interesting and relevant information given the
-    current year is 2024.
-  expected_output: >
-    A complete report on the customer and their customers and competitors,
-    including their demographics, preferences, market positioning and audience engagement.
-```
-
-#### main.py
-
-```python
-# main.py
-def run():
-    inputs = {
-        "customer_domain": "crewai.com"
-    }
-    MyProjectCrew(inputs).crew().kickoff(inputs=inputs)
-```
-
-## Running Your Project
-
-To run your project, use the following command:
-
-```shell
-$ poetry run my_project
-```
-
-This will initialize your crew of AI agents and begin task execution as defined in your configuration in the `main.py` file.
-
-## Deploying Your Project
-
-The easiest way to deploy your crew is through [CrewAI+](https://www.crewai.com/crewaiplus), where you can deploy your crew in a few clicks.

docs/index.md

@@ -5,6 +5,19 @@
 Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
 
 <div style="display:flex; margin:0 auto; justify-content: center;">
+    <div style="width:25%">
+        <h2>Getting Started</h2>
+        <ul>
+            <li><a href='./getting-started/Installing-CrewAI'>
+                   Installing CrewAI
+                 </a>
+            </li>
+            <li><a href='./getting-started/Start-a-New-CrewAI-Project-Template-Method'>
+                   Start a New CrewAI Project: Template Method
+                 </a>
+            </li>
+        </ul>
+    </div>
     <div style="width:25%">
         <h2>Core Concepts</h2>
         <ul>
@@ -53,21 +66,6 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
     <div style="width:30%">
         <h2>How-To Guides</h2>
         <ul>
-            <li>
-                <a href="./how-to/Start-a-New-CrewAI-Project">
-                    Starting Your crewAI Project
-                </a>
-            </li>
-            <li>
-                <a href="./how-to/Installing-CrewAI">
-                    Installing crewAI
-                </a>
-            </li>
-            <li>
-                <a href="./how-to/Creating-a-Crew-and-kick-it-off">
-                    Getting Started
-                </a>
-            </li>
             <li>
                 <a href="./how-to/Create-Custom-Tools">
                     Create Custom Tools

docs/telemetry/Telemetry.md

@@ -5,7 +5,7 @@ description: Understanding the telemetry data collected by CrewAI and how it con
 
 ## Telemetry
 
-CrewAI utilizes anonymous telemetry to gather usage statistics with the primary goal of enhancing the library. Our focus is on improving and developing the features, integrations, and tools most utilized by our users.
+CrewAI utilizes anonymous telemetry to gather usage statistics with the primary goal of enhancing the library. Our focus is on improving and developing the features, integrations, and tools most utilized by our users. We don't offer a way to disable it now, but we will in the future.
 
 It's pivotal to understand that **NO data is collected** concerning prompts, task descriptions, agents' backstories or goals, usage of tools, API calls, responses, any data processed by the agents, or secrets and environment variables, with the exception of the conditions mentioned. When the `share_crew` feature is enabled, detailed data including task descriptions, agents' backstories or goals, and other specific attributes are collected to provide deeper insights while respecting user privacy.
 
@@ -22,7 +22,7 @@ It's pivotal to understand that **NO data is collected** concerning prompts, tas
 - **Tool Usage**: Identifying which tools are most frequently used allows us to prioritize improvements in those areas.
 
 ### Opt-In Further Telemetry Sharing
-Users can choose to share their complete telemetry data by enabling the `share_crew` attribute to `True` in their crew configurations. This opt-in approach respects user privacy and aligns with data protection standards by ensuring users have control over their data sharing preferences. Enabling `share_crew` results in the collection of detailed crew and task execution data, including `goal`, `backstory`, `context`, and `output` of tasks. This enables a deeper insight into usage patterns while respecting the user's choice to share.
+Users can choose to share their complete telemetry data by enabling the `share_crew` attribute to `True` in their crew configurations. Enabling `share_crew` results in the collection of detailed crew and task execution data, including `goal`, `backstory`, `context`, and `output` of tasks. This enables a deeper insight into usage patterns while respecting the user's choice to share.
 
 ### Updates and Revisions
 We are committed to maintaining the accuracy and transparency of our documentation. Regular reviews and updates are performed to ensure our documentation accurately reflects the latest developments of our codebase and telemetry practices. Users are encouraged to review this section for the most current information on our data collection practices and how they contribute to the improvement of CrewAI.

docs/tools/CodeInterpreterTool.md

@@ -1,9 +1,9 @@
 # CodeInterpreterTool
 
 ## Description
-This tool is used to give the Agent the ability to run code (Python3) from the code generated by the Agent itself. The code is executed in a sandboxed environment, so it is safe to run any code.
+This tool enables the Agent to execute Python 3 code that it has generated autonomously. The code is run in a secure, isolated environment, ensuring safety regardless of the content. 
 
-It is incredible useful since it allows the Agent to generate code, run it in the same environment, get the result and use it to make decisions.
+This functionality is particularly valuable as it allows the Agent to create code, execute it within the same ecosystem, obtain the results, and utilize that information to inform subsequent decisions and actions.
 
 ## Requirements
 

docs/tools/ComposioTool.md

@@ -2,7 +2,7 @@
 
 ## Description
 
-This tools is a wrapper around the composio toolset and gives your agent access to a wide variety of tools from the composio SDK.
+This tools is a wrapper around the composio set of tools and gives your agent access to a wide variety of tools from the composio SDK.
 
 ## Installation
 
@@ -19,7 +19,7 @@ after the installation is complete, either run `composio login` or export your c
 
 The following example demonstrates how to initialize the tool and execute a github action:
 
-1. Initialize toolset
+1. Initialize Composio tools
 
 ```python
 from composio import App

docs/tools/SerperDevTool.md

@@ -29,5 +29,69 @@ To effectively use the `SerperDevTool`, follow these steps:
 2. **API Key Acquisition**: Acquire a `serper.dev` API key by registering for a free account at `serper.dev`.
 3. **Environment Configuration**: Store your obtained API key in an environment variable named `SERPER_API_KEY` to facilitate its use by the tool.
 
+## Parameters
+
+The `SerperDevTool` comes with several parameters that will be passed to the API :
+
+- **search_url**: The URL endpoint for the search API. (Default is `https://google.serper.dev/search`)
+
+- **country**: Optional. Specify the country for the search results.
+- **location**: Optional. Specify the location for the search results.
+- **locale**: Optional. Specify the locale for the search results.
+- **n_results**: Number of search results to return. Default is `10`.
+
+The values for `country`, `location`, `locale` and `search_url` can be found on the [Serper Playground](https://serper.dev/playground).
+
+## Example with Parameters
+Here is an example demonstrating how to use the tool with additional parameters:
+
+```python
+from crewai_tools import SerperDevTool
+
+tool = SerperDevTool(
+    search_url="https://google.serper.dev/scholar",
+    n_results=2,
+)
+
+print(tool.run(search_query="ChatGPT"))
+
+# Using Tool: Search the internet
+
+# Search results: Title: Role of chat gpt in public health
+# Link: https://link.springer.com/article/10.1007/s10439-023-03172-7
+# Snippet: … ChatGPT in public health. In this overview, we will examine the potential uses of ChatGPT in
+# ---
+# Title: Potential use of chat gpt in global warming
+# Link: https://link.springer.com/article/10.1007/s10439-023-03171-8
+# Snippet: … as ChatGPT, have the potential to play a critical role in advancing our understanding of climate
+# ---
+
+```
+
+```python
+from crewai_tools import SerperDevTool
+
+tool = SerperDevTool(
+    country="fr",
+    locale="fr",
+    location="Paris, Paris, Ile-de-France, France",
+    n_results=2,
+)
+
+print(tool.run(search_query="Jeux Olympiques"))
+
+# Using Tool: Search the internet
+
+# Search results: Title: Jeux Olympiques de Paris 2024 - Actualités, calendriers, résultats
+# Link: https://olympics.com/fr/paris-2024
+# Snippet: Quels sont les sports présents aux Jeux Olympiques de Paris 2024 ? · Athlétisme · Aviron · Badminton · Basketball · Basketball 3x3 · Boxe · Breaking · Canoë ...
+# ---
+# Title: Billetterie Officielle de Paris 2024 - Jeux Olympiques et Paralympiques
+# Link: https://tickets.paris2024.org/
+# Snippet: Achetez vos billets exclusivement sur le site officiel de la billetterie de Paris 2024 pour participer au plus grand événement sportif au monde.
+# ---
+
+```
+
 ## Conclusion
-By integrating the `SerperDevTool` into Python projects, users gain the ability to conduct real-time, relevant searches across the internet directly from their applications. By adhering to the setup and usage guidelines provided, incorporating this tool into projects is streamlined and straightforward.
+By integrating the `SerperDevTool` into Python projects, users gain the ability to conduct real-time, relevant searches across the internet directly from their applications. The updated parameters allow for more customized and localized search results. By adhering to the setup and usage guidelines provided, incorporating this tool into projects is streamlined and straightforward.

mkdocs.yml

@@ -119,6 +119,9 @@ theme:
 
 nav:
   - Home: '/'
+  - Getting Started:
+    - Installing CrewAI: 'getting-started/Installing-CrewAI.md'
+    - Starting a new CrewAI project: 'getting-started/Start-a-New-CrewAI-Project-Template-Method.md'
   - Core Concepts:
     - Agents: 'core-concepts/Agents.md'
     - Tasks: 'core-concepts/Tasks.md'

poetry.lock

@@ -1,14 +1,14 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "agentops"
-version = "0.3.0"
+version = "0.3.2"
 description = "Python SDK for developing AI agent evals and observability"
 optional = true
 python-versions = ">=3.7"
 files = [
-    {file = "agentops-0.3.0-py3-none-any.whl", hash = "sha256:22aeb3355e66b32a2b2a9f676048b81979b2488feddb088f9266034b3ed50539"},
+    {file = "agentops-0.3.2-py3-none-any.whl", hash = "sha256:b35988e04378624204572bb3d7a454094f879ea573f05b57d4e75ab0bfbb82af"},
-    {file = "agentops-0.3.0.tar.gz", hash = "sha256:6c0c08a57410fa5e826a7bafa1deeba9f7b3524709427d9e1abbd0964caaf76b"},
+    {file = "agentops-0.3.2.tar.gz", hash = "sha256:55559ac4a43634831dfa8937c2597c28e332809dc7c6bb3bc3c8b233442e224c"},
 ]
 
 [package.dependencies]
@@ -294,38 +294,38 @@ files = [
 
 [[package]]
 name = "bcrypt"
-version = "4.1.3"
+version = "4.2.0"
 description = "Modern password hashing for your software and your servers"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "bcrypt-4.1.3-cp37-abi3-macosx_10_12_universal2.whl", hash = "sha256:48429c83292b57bf4af6ab75809f8f4daf52aa5d480632e53707805cc1ce9b74"},
+    {file = "bcrypt-4.2.0-cp37-abi3-macosx_10_12_universal2.whl", hash = "sha256:096a15d26ed6ce37a14c1ac1e48119660f21b24cba457f160a4b830f3fe6b5cb"},
-    {file = "bcrypt-4.1.3-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4a8bea4c152b91fd8319fef4c6a790da5c07840421c2b785084989bf8bbb7455"},
+    {file = "bcrypt-4.2.0-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c02d944ca89d9b1922ceb8a46460dd17df1ba37ab66feac4870f6862a1533c00"},
-    {file = "bcrypt-4.1.3-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d3b317050a9a711a5c7214bf04e28333cf528e0ed0ec9a4e55ba628d0f07c1a"},
+    {file = "bcrypt-4.2.0-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1d84cf6d877918620b687b8fd1bf7781d11e8a0998f576c7aa939776b512b98d"},
-    {file = "bcrypt-4.1.3-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:094fd31e08c2b102a14880ee5b3d09913ecf334cd604af27e1013c76831f7b05"},
+    {file = "bcrypt-4.2.0-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:1bb429fedbe0249465cdd85a58e8376f31bb315e484f16e68ca4c786dcc04291"},
-    {file = "bcrypt-4.1.3-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:4fb253d65da30d9269e0a6f4b0de32bd657a0208a6f4e43d3e645774fb5457f3"},
+    {file = "bcrypt-4.2.0-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:655ea221910bcac76ea08aaa76df427ef8625f92e55a8ee44fbf7753dbabb328"},
-    {file = "bcrypt-4.1.3-cp37-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:193bb49eeeb9c1e2db9ba65d09dc6384edd5608d9d672b4125e9320af9153a15"},
+    {file = "bcrypt-4.2.0-cp37-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:1ee38e858bf5d0287c39b7a1fc59eec64bbf880c7d504d3a06a96c16e14058e7"},
-    {file = "bcrypt-4.1.3-cp37-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:8cbb119267068c2581ae38790e0d1fbae65d0725247a930fc9900c285d95725d"},
+    {file = "bcrypt-4.2.0-cp37-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:0da52759f7f30e83f1e30a888d9163a81353ef224d82dc58eb5bb52efcabc399"},
-    {file = "bcrypt-4.1.3-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:6cac78a8d42f9d120b3987f82252bdbeb7e6e900a5e1ba37f6be6fe4e3848286"},
+    {file = "bcrypt-4.2.0-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:3698393a1b1f1fd5714524193849d0c6d524d33523acca37cd28f02899285060"},
-    {file = "bcrypt-4.1.3-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:01746eb2c4299dd0ae1670234bf77704f581dd72cc180f444bfe74eb80495b64"},
+    {file = "bcrypt-4.2.0-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:762a2c5fb35f89606a9fde5e51392dad0cd1ab7ae64149a8b935fe8d79dd5ed7"},
-    {file = "bcrypt-4.1.3-cp37-abi3-win32.whl", hash = "sha256:037c5bf7c196a63dcce75545c8874610c600809d5d82c305dd327cd4969995bf"},
+    {file = "bcrypt-4.2.0-cp37-abi3-win32.whl", hash = "sha256:5a1e8aa9b28ae28020a3ac4b053117fb51c57a010b9f969603ed885f23841458"},
-    {file = "bcrypt-4.1.3-cp37-abi3-win_amd64.whl", hash = "sha256:8a893d192dfb7c8e883c4576813bf18bb9d59e2cfd88b68b725990f033f1b978"},
+    {file = "bcrypt-4.2.0-cp37-abi3-win_amd64.whl", hash = "sha256:8f6ede91359e5df88d1f5c1ef47428a4420136f3ce97763e31b86dd8280fbdf5"},
-    {file = "bcrypt-4.1.3-cp39-abi3-macosx_10_12_universal2.whl", hash = "sha256:0d4cf6ef1525f79255ef048b3489602868c47aea61f375377f0d00514fe4a78c"},
+    {file = "bcrypt-4.2.0-cp39-abi3-macosx_10_12_universal2.whl", hash = "sha256:c52aac18ea1f4a4f65963ea4f9530c306b56ccd0c6f8c8da0c06976e34a6e841"},
-    {file = "bcrypt-4.1.3-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f5698ce5292a4e4b9e5861f7e53b1d89242ad39d54c3da451a93cac17b61921a"},
+    {file = "bcrypt-4.2.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3bbbfb2734f0e4f37c5136130405332640a1e46e6b23e000eeff2ba8d005da68"},
-    {file = "bcrypt-4.1.3-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ec3c2e1ca3e5c4b9edb94290b356d082b721f3f50758bce7cce11d8a7c89ce84"},
+    {file = "bcrypt-4.2.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3413bd60460f76097ee2e0a493ccebe4a7601918219c02f503984f0a7ee0aebe"},
-    {file = "bcrypt-4.1.3-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:3a5be252fef513363fe281bafc596c31b552cf81d04c5085bc5dac29670faa08"},
+    {file = "bcrypt-4.2.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:8d7bb9c42801035e61c109c345a28ed7e84426ae4865511eb82e913df18f58c2"},
-    {file = "bcrypt-4.1.3-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:5f7cd3399fbc4ec290378b541b0cf3d4398e4737a65d0f938c7c0f9d5e686611"},
+    {file = "bcrypt-4.2.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3d3a6d28cb2305b43feac298774b997e372e56c7c7afd90a12b3dc49b189151c"},
-    {file = "bcrypt-4.1.3-cp39-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:c4c8d9b3e97209dd7111bf726e79f638ad9224b4691d1c7cfefa571a09b1b2d6"},
+    {file = "bcrypt-4.2.0-cp39-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:9c1c4ad86351339c5f320ca372dfba6cb6beb25e8efc659bedd918d921956bae"},
-    {file = "bcrypt-4.1.3-cp39-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:31adb9cbb8737a581a843e13df22ffb7c84638342de3708a98d5c986770f2834"},
+    {file = "bcrypt-4.2.0-cp39-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:27fe0f57bb5573104b5a6de5e4153c60814c711b29364c10a75a54bb6d7ff48d"},
-    {file = "bcrypt-4.1.3-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:551b320396e1d05e49cc18dd77d970accd52b322441628aca04801bbd1d52a73"},
+    {file = "bcrypt-4.2.0-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:8ac68872c82f1add6a20bd489870c71b00ebacd2e9134a8aa3f98a0052ab4b0e"},
-    {file = "bcrypt-4.1.3-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:6717543d2c110a155e6821ce5670c1f512f602eabb77dba95717ca76af79867d"},
+    {file = "bcrypt-4.2.0-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:cb2a8ec2bc07d3553ccebf0746bbf3d19426d1c6d1adbd4fa48925f66af7b9e8"},
-    {file = "bcrypt-4.1.3-cp39-abi3-win32.whl", hash = "sha256:6004f5229b50f8493c49232b8e75726b568535fd300e5039e255d919fc3a07f2"},
+    {file = "bcrypt-4.2.0-cp39-abi3-win32.whl", hash = "sha256:77800b7147c9dc905db1cba26abe31e504d8247ac73580b4aa179f98e6608f34"},
-    {file = "bcrypt-4.1.3-cp39-abi3-win_amd64.whl", hash = "sha256:2505b54afb074627111b5a8dc9b6ae69d0f01fea65c2fcaea403448c503d3991"},
+    {file = "bcrypt-4.2.0-cp39-abi3-win_amd64.whl", hash = "sha256:61ed14326ee023917ecd093ee6ef422a72f3aec6f07e21ea5f10622b735538a9"},
-    {file = "bcrypt-4.1.3-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:cb9c707c10bddaf9e5ba7cdb769f3e889e60b7d4fea22834b261f51ca2b89fed"},
+    {file = "bcrypt-4.2.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:39e1d30c7233cfc54f5c3f2c825156fe044efdd3e0b9d309512cc514a263ec2a"},
-    {file = "bcrypt-4.1.3-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:9f8ea645eb94fb6e7bea0cf4ba121c07a3a182ac52876493870033141aa687bc"},
+    {file = "bcrypt-4.2.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:f4f4acf526fcd1c34e7ce851147deedd4e26e6402369304220250598b26448db"},
-    {file = "bcrypt-4.1.3-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:f44a97780677e7ac0ca393bd7982b19dbbd8d7228c1afe10b128fd9550eef5f1"},
+    {file = "bcrypt-4.2.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:1ff39b78a52cf03fdf902635e4c81e544714861ba3f0efc56558979dd4f09170"},
-    {file = "bcrypt-4.1.3-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:d84702adb8f2798d813b17d8187d27076cca3cd52fe3686bb07a9083930ce650"},
+    {file = "bcrypt-4.2.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:373db9abe198e8e2c70d12b479464e0d5092cc122b20ec504097b5f2297ed184"},
-    {file = "bcrypt-4.1.3.tar.gz", hash = "sha256:2ee15dd749f5952fe3f0430d0ff6b74082e159c50332a1413d51b5689cf06623"},
+    {file = "bcrypt-4.2.0.tar.gz", hash = "sha256:cf69eaf5185fd58f268f805b505ce31f9b9fc2d64b376642164e9244540c1221"},
 ]
 
 [package.extras]
@@ -355,17 +355,17 @@ lxml = ["lxml"]
 
 [[package]]
 name = "boto3"
-version = "1.34.145"
+version = "1.34.146"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "boto3-1.34.145-py3-none-any.whl", hash = "sha256:69d5afb7a017d07dd6bdfb680d2912d5d369b3fafa0a45161207d9f393b14d7e"},
+    {file = "boto3-1.34.146-py3-none-any.whl", hash = "sha256:7ec568fb19bce82a70be51f08fddac1ef927ca3fb0896cbb34303a012ba228d8"},
-    {file = "boto3-1.34.145.tar.gz", hash = "sha256:ac770fb53dde1743aec56bd8e56b7ee2e2f5ad42a37825968ec4ff8428822640"},
+    {file = "boto3-1.34.146.tar.gz", hash = "sha256:5686fe2a6d1aa1de8a88e9589cdcc33361640d3d7a13da718a30717248886124"},
 ]
 
 [package.dependencies]
-botocore = ">=1.34.145,<1.35.0"
+botocore = ">=1.34.146,<1.35.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.10.0,<0.11.0"
 
@@ -374,13 +374,13 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
 
 [[package]]
 name = "botocore"
-version = "1.34.145"
+version = "1.34.146"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "botocore-1.34.145-py3-none-any.whl", hash = "sha256:2e72e262de02adcb0264ac2bac159a28f55dbba8d9e52aa0308773a42950dff5"},
+    {file = "botocore-1.34.146-py3-none-any.whl", hash = "sha256:3fd4782362bd29c192704ebf859c5c8c5189ad05719e391eefe23088434427ae"},
-    {file = "botocore-1.34.145.tar.gz", hash = "sha256:edf0fb4c02186ae29b76263ac5fda18b0a085d334a310551c9984407cf1079e6"},
+    {file = "botocore-1.34.146.tar.gz", hash = "sha256:849cb8e54e042443aeabcd7822b5f2b76cb5cfe33fe3a71f91c7c069748a869c"},
 ]
 
 [package.dependencies]
@@ -747,13 +747,13 @@ colorama = {version = "*", markers = "platform_system == \"Windows\""}
 
 [[package]]
 name = "cohere"
-version = "5.6.1"
+version = "5.6.2"
 description = ""
 optional = false
 python-versions = "<4.0,>=3.8"
 files = [
-    {file = "cohere-5.6.1-py3-none-any.whl", hash = "sha256:1c8bcd39a54622d64b83cafb865f102cd2565ce091b0856fd5ce11bf7169109a"},
+    {file = "cohere-5.6.2-py3-none-any.whl", hash = "sha256:cfecf1343bcaa4091266c5a231fbcb3ccbd80cad05ea093ef80024a117aa3a2f"},
-    {file = "cohere-5.6.1.tar.gz", hash = "sha256:5d7efda64f0e512d4cc35aa04b17a6f74b3d8c175a99f2797991a7f31dfac349"},
+    {file = "cohere-5.6.2.tar.gz", hash = "sha256:6bb901afdfb02f62ad8ed2d82f12d8ea87a6869710f5f880cb89190c4e994805"},
 ]
 
 [package.dependencies]
@@ -1517,13 +1517,13 @@ protobuf = ">=3.20.2,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4
 
 [[package]]
 name = "google-cloud-storage"
-version = "2.17.0"
+version = "2.18.0"
 description = "Google Cloud Storage API client library"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "google-cloud-storage-2.17.0.tar.gz", hash = "sha256:49378abff54ef656b52dca5ef0f2eba9aa83dc2b2c72c78714b03a1a95fe9388"},
+    {file = "google_cloud_storage-2.18.0-py2.py3-none-any.whl", hash = "sha256:e8e1a9577952143c3fca8163005ecfadd2d70ec080fa158a8b305000e2c22fbb"},
-    {file = "google_cloud_storage-2.17.0-py2.py3-none-any.whl", hash = "sha256:5b393bc766b7a3bc6f5407b9e665b2450d36282614b7945e570b3480a456d1e1"},
+    {file = "google_cloud_storage-2.18.0.tar.gz", hash = "sha256:0aa3f7c57f3632f81b455d91558d2b27ada96eee2de3aaa17f689db1470d9578"},
 ]
 
 [package.dependencies]
@@ -1535,7 +1535,8 @@ google-resumable-media = ">=2.6.0"
 requests = ">=2.18.0,<3.0.0dev"
 
 [package.extras]
-protobuf = ["protobuf (<5.0.0dev)"]
+protobuf = ["protobuf (<6.0.0dev)"]
+tracing = ["opentelemetry-api (>=1.1.0)"]
 
 [[package]]
 name = "google-crc32c"
@@ -2865,13 +2866,13 @@ pyyaml = ">=5.1"
 
 [[package]]
 name = "mkdocs-material"
-version = "9.5.29"
+version = "9.5.30"
 description = "Documentation that simply works"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "mkdocs_material-9.5.29-py3-none-any.whl", hash = "sha256:afc1f508e2662ded95f0a35a329e8a5acd73ee88ca07ba73836eb6fcdae5d8b4"},
+    {file = "mkdocs_material-9.5.30-py3-none-any.whl", hash = "sha256:fc070689c5250a180e9b9d79d8491ef9a3a7acb240db0728728d6c31eeb131d4"},
-    {file = "mkdocs_material-9.5.29.tar.gz", hash = "sha256:3e977598ec15a4ddad5c4dfc9e08edab6023edb51e88f0729bd27be77e3d322a"},
+    {file = "mkdocs_material-9.5.30.tar.gz", hash = "sha256:3fd417dd42d679e3ba08b9e2d72cd8b8af142cc4a3969676ad6b00993dd182ec"},
 ]
 
 [package.dependencies]
@@ -3337,13 +3338,13 @@ sympy = "*"
 
 [[package]]
 name = "openai"
-version = "1.36.0"
+version = "1.37.0"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-1.36.0-py3-none-any.whl", hash = "sha256:82b74ded1fe2ea94abb19a007178bc143675f1b6903cebd63e2968d654bb0a6f"},
+    {file = "openai-1.37.0-py3-none-any.whl", hash = "sha256:a903245c0ecf622f2830024acdaa78683c70abb8e9d37a497b851670864c9f73"},
-    {file = "openai-1.36.0.tar.gz", hash = "sha256:a124baf0e1657d6156e12248642f88489cd030be8655b69bc1c13eb50e71a93d"},
+    {file = "openai-1.37.0.tar.gz", hash = "sha256:dc8197fc40ab9d431777b6620d962cc49f4544ffc3011f03ce0a805e6eb54adb"},
 ]
 
 [package.dependencies]
@@ -4085,6 +4086,19 @@ files = [
     {file = "pyarrow-17.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:392bc9feabc647338e6c89267635e111d71edad5fcffba204425a7c8d13610d7"},
     {file = "pyarrow-17.0.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:af5ff82a04b2171415f1410cff7ebb79861afc5dae50be73ce06d6e870615204"},
     {file = "pyarrow-17.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:edca18eaca89cd6382dfbcff3dd2d87633433043650c07375d095cd3517561d8"},
+    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7c7916bff914ac5d4a8fe25b7a25e432ff921e72f6f2b7547d1e325c1ad9d155"},
+    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f553ca691b9e94b202ff741bdd40f6ccb70cdd5fbf65c187af132f1317de6145"},
+    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:0cdb0e627c86c373205a2f94a510ac4376fdc523f8bb36beab2e7f204416163c"},
+    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:d7d192305d9d8bc9082d10f361fc70a73590a4c65cf31c3e6926cd72b76bc35c"},
+    {file = "pyarrow-17.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:02dae06ce212d8b3244dd3e7d12d9c4d3046945a5933d28026598e9dbbda1fca"},
+    {file = "pyarrow-17.0.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:13d7a460b412f31e4c0efa1148e1d29bdf18ad1411eb6757d38f8fbdcc8645fb"},
+    {file = "pyarrow-17.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9b564a51fbccfab5a04a80453e5ac6c9954a9c5ef2890d1bcf63741909c3f8df"},
+    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:32503827abbc5aadedfa235f5ece8c4f8f8b0a3cf01066bc8d29de7539532687"},
+    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a155acc7f154b9ffcc85497509bcd0d43efb80d6f733b0dc3bb14e281f131c8b"},
+    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:dec8d129254d0188a49f8a1fc99e0560dc1b85f60af729f47de4046015f9b0a5"},
+    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:a48ddf5c3c6a6c505904545c25a4ae13646ae1f8ba703c4df4a1bfe4f4006bda"},
+    {file = "pyarrow-17.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:42bf93249a083aca230ba7e2786c5f673507fa97bbd9725a1e2754715151a204"},
+    {file = "pyarrow-17.0.0.tar.gz", hash = "sha256:4beca9521ed2c0921c1023e68d097d0299b62c362639ea315572a58f3f50fd28"},
 ]
 
 [package.dependencies]
@@ -4321,13 +4335,13 @@ extra = ["pygments (>=2.12)"]
 
 [[package]]
 name = "pypdf"
-version = "4.3.0"
+version = "4.3.1"
 description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files"
 optional = false
 python-versions = ">=3.6"
 files = [
-    {file = "pypdf-4.3.0-py3-none-any.whl", hash = "sha256:eeea4d019b57c099d02a0e1692eaaab23341ae3f255c1dafa3c8566b4636496d"},
+    {file = "pypdf-4.3.1-py3-none-any.whl", hash = "sha256:64b31da97eda0771ef22edb1bfecd5deee4b72c3d1736b7df2689805076d6418"},
-    {file = "pypdf-4.3.0.tar.gz", hash = "sha256:0d7a4c67fd03782f5a09d3f48c11c7a31e0bb9af78861a25229bb49259ed0504"},
+    {file = "pypdf-4.3.1.tar.gz", hash = "sha256:b2f37fe9a3030aa97ca86067a56ba3f9d3565f9a791b305c7355d8392c30d91b"},
 ]
 
 [package.dependencies]
@@ -4414,13 +4428,13 @@ files = [
 
 [[package]]
 name = "pytest"
-version = "8.2.2"
+version = "8.3.1"
 description = "pytest: simple powerful testing with Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pytest-8.2.2-py3-none-any.whl", hash = "sha256:c434598117762e2bd304e526244f67bf66bbd7b5d6cf22138be51ff661980343"},
+    {file = "pytest-8.3.1-py3-none-any.whl", hash = "sha256:e9600ccf4f563976e2c99fa02c7624ab938296551f280835ee6516df8bc4ae8c"},
-    {file = "pytest-8.2.2.tar.gz", hash = "sha256:de4bb8104e201939ccdc688b27a89a7be2079b22e2bd2b07f806b6ba71117977"},
+    {file = "pytest-8.3.1.tar.gz", hash = "sha256:7e8e5c5abd6e93cb1cc151f23e57adc31fcf8cfd2a3ff2da63e23f732de35db6"},
 ]
 
 [package.dependencies]
@@ -4428,7 +4442,7 @@ colorama = {version = "*", markers = "sys_platform == \"win32\""}
 exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
 iniconfig = "*"
 packaging = "*"
-pluggy = ">=1.5,<2.0"
+pluggy = ">=1.5,<2"
 tomli = {version = ">=1", markers = "python_version < \"3.11\""}
 
 [package.extras]
@@ -4899,19 +4913,19 @@ files = [
 
 [[package]]
 name = "setuptools"
-version = "71.0.4"
+version = "71.1.0"
 description = "Easily download, build, install, upgrade, and uninstall Python packages"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "setuptools-71.0.4-py3-none-any.whl", hash = "sha256:ed2feca703be3bdbd94e6bb17365d91c6935c6b2a8d0bb09b66a2c435ba0b1a5"},
+    {file = "setuptools-71.1.0-py3-none-any.whl", hash = "sha256:33874fdc59b3188304b2e7c80d9029097ea31627180896fb549c578ceb8a0855"},
-    {file = "setuptools-71.0.4.tar.gz", hash = "sha256:48297e5d393a62b7cb2a10b8f76c63a73af933bd809c9e0d0d6352a1a0135dd8"},
+    {file = "setuptools-71.1.0.tar.gz", hash = "sha256:032d42ee9fb536e33087fb66cac5f840eb9391ed05637b3f2a76a7c8fb477936"},
 ]
 
 [package.extras]
 core = ["importlib-metadata (>=6)", "importlib-resources (>=5.10.2)", "jaraco.text (>=3.7)", "more-itertools (>=8.8)", "ordered-set (>=3.1.1)", "packaging (>=24)", "platformdirs (>=2.6.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
 doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier"]
-test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.10.0)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf", "pytest-ruff (<0.4)", "pytest-ruff (>=0.2.1)", "pytest-ruff (>=0.3.2)", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
+test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "importlib-metadata", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test", "mypy (==1.11.*)", "packaging (>=23.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-home (>=0.5)", "pytest-mypy", "pytest-perf", "pytest-ruff (<0.4)", "pytest-ruff (>=0.2.1)", "pytest-ruff (>=0.3.2)", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
 
 [[package]]
 name = "shapely"
@@ -5256,13 +5270,13 @@ test = ["pytest", "ruff"]
 
 [[package]]
 name = "together"
-version = "1.2.2"
+version = "1.2.3"
 description = "Python client for Together's Cloud Platform!"
 optional = false
 python-versions = "<4.0,>=3.8"
 files = [
-    {file = "together-1.2.2-py3-none-any.whl", hash = "sha256:7ce89f902dbaca67e46e693d90182514494f510f3bc16cb89d816a5031ab0433"},
+    {file = "together-1.2.3-py3-none-any.whl", hash = "sha256:bbafb4b8340e0f7e0ddb11ad447eb3467c591090910d0291cfbf74b47af045c1"},
-    {file = "together-1.2.2.tar.gz", hash = "sha256:fd026f4a604e1fb3ee2fa5803f31e5e36ad31b3d182ef47f611326de66907d13"},
+    {file = "together-1.2.3.tar.gz", hash = "sha256:4ea7626a9581d16fbf293e3eaf91557c43dea044627cf6dbe458bbf43408a6b2"},
 ]
 
 [package.dependencies]

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "crewai"
-version = "0.41.1"
+version = "0.46.0"
 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."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"

src/crewai/agent.py

@@ -55,8 +55,6 @@ class Agent(BaseAgent):
             tools: Tools at agents disposal
             step_callback: Callback to be executed after each step of the agent execution.
             callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
-            allow_code_execution: Enable code execution for the agent.
-            max_retry_limit: Maximum number of retries for an agent to execute a task when an error occurs.
     """
 
     _times_executed: int = PrivateAttr(default=0)
@@ -262,6 +260,7 @@ class Agent(BaseAgent):
             "tools_handler": self.tools_handler,
             "function_calling_llm": self.function_calling_llm,
             "callbacks": self.callbacks,
+            "max_tokens": self.max_tokens,
         }
 
         if self._rpm_controller:

src/crewai/agents/agent_builder/base_agent.py

@@ -45,6 +45,7 @@ class BaseAgent(ABC, BaseModel):
         i18n (I18N): Internationalization settings.
         cache_handler (InstanceOf[CacheHandler]): An instance of the CacheHandler class.
         tools_handler (InstanceOf[ToolsHandler]): An instance of the ToolsHandler class.
+        max_tokens: Maximum number of tokens for the agent to generate in a response.
 
 
     Methods:
@@ -118,6 +119,9 @@ class BaseAgent(ABC, BaseModel):
     tools_handler: InstanceOf[ToolsHandler] = Field(
         default=None, description="An instance of the ToolsHandler class."
     )
+    max_tokens: Optional[int] = Field(
+        default=None, description="Maximum number of tokens for the agent's execution."
+    )
 
     _original_role: str | None = None
     _original_goal: str | None = None

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -3,7 +3,6 @@ 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.memory.short_term.short_term_memory_item import ShortTermMemoryItem
 from crewai.utilities.converter import ConverterError
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities import I18N
@@ -39,18 +38,17 @@ class CrewAgentExecutorMixin:
             and "Action: Delegate work to coworker" not in output.log
         ):
             try:
-                memory = ShortTermMemoryItem(
-                    data=output.log,
-                    agent=self.crew_agent.role,
-                    metadata={
-                        "observation": self.task.description,
-                    },
-                )
                 if (
                     hasattr(self.crew, "_short_term_memory")
                     and self.crew._short_term_memory
                 ):
-                    self.crew._short_term_memory.save(memory)
+                    self.crew._short_term_memory.save(
+                        value=output.log,
+                        metadata={
+                            "observation": self.task.description,
+                        },
+                        agent=self.crew_agent.role,
+                    )
             except Exception as e:
                 print(f"Failed to add to short term memory: {e}")
                 pass

src/crewai/agents/executor.py

@@ -1,6 +1,8 @@
 import threading
 import time
-from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
+from typing import Any, Dict, Iterator, List, Literal, Optional, Tuple, Union
+import click
+
 
 from langchain.agents import AgentExecutor
 from langchain.agents.agent import ExceptionTool
@@ -11,12 +13,21 @@ from langchain_core.tools import BaseTool
 from langchain_core.utils.input import get_color_mapping
 from pydantic import InstanceOf
 
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains.summarize import load_summarize_chain
+
 from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
 from crewai.agents.tools_handler import ToolsHandler
+
+
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N
 from crewai.utilities.constants import TRAINING_DATA_FILE
+from crewai.utilities.exceptions.context_window_exceeding_exception import (
+    LLMContextLengthExceededException,
+)
 from crewai.utilities.training_handler import CrewTrainingHandler
+from crewai.utilities.logger import Logger
 
 
 class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
@@ -40,6 +51,8 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
     system_template: Optional[str] = None
     prompt_template: Optional[str] = None
     response_template: Optional[str] = None
+    _logger: Logger = Logger(verbose_level=2)
+    _fit_context_window_strategy: Optional[Literal["summarize"]] = "summarize"
 
     def _call(
         self,
@@ -131,7 +144,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             intermediate_steps = self._prepare_intermediate_steps(intermediate_steps)
 
             # Call the LLM to see what to do.
-            output = self.agent.plan(  # type: ignore #  Incompatible types in assignment (expression has type "AgentAction | AgentFinish | list[AgentAction]", variable has type "AgentAction")
+            output = self.agent.plan(
                 intermediate_steps,
                 callbacks=run_manager.get_child() if run_manager else None,
                 **inputs,
@@ -185,6 +198,27 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             yield AgentStep(action=output, observation=observation)
             return
 
+        except Exception as e:
+            if LLMContextLengthExceededException(str(e))._is_context_limit_error(
+                str(e)
+            ):
+                output = self._handle_context_length_error(
+                    intermediate_steps, run_manager, inputs
+                )
+
+                if isinstance(output, AgentFinish):
+                    yield output
+                elif isinstance(output, list):
+                    for step in output:
+                        yield step
+                return
+
+            yield AgentStep(
+                action=AgentAction("_Exception", str(e), str(e)),
+                observation=str(e),
+            )
+            return
+
         # If the tool chosen is the finishing tool, then we end and return.
         if isinstance(output, AgentFinish):
             if self.should_ask_for_human_input:
@@ -235,6 +269,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
                 agent=self.crew_agent,
                 action=agent_action,
             )
+
             tool_calling = tool_usage.parse(agent_action.log)
 
             if isinstance(tool_calling, ToolUsageErrorException):
@@ -280,3 +315,91 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             CrewTrainingHandler(TRAINING_DATA_FILE).append(
                 self.crew._train_iteration, agent_id, training_data
             )
+
+    def _handle_context_length(
+        self, intermediate_steps: List[Tuple[AgentAction, str]]
+    ) -> List[Tuple[AgentAction, str]]:
+        text = intermediate_steps[0][1]
+        original_action = intermediate_steps[0][0]
+
+        text_splitter = RecursiveCharacterTextSplitter(
+            separators=["\n\n", "\n"],
+            chunk_size=8000,
+            chunk_overlap=500,
+        )
+
+        if self._fit_context_window_strategy == "summarize":
+            docs = text_splitter.create_documents([text])
+            self._logger.log(
+                "debug",
+                "Summarizing Content, it is recommended to use a RAG tool",
+                color="bold_blue",
+            )
+            summarize_chain = load_summarize_chain(
+                self.llm, chain_type="map_reduce", verbose=True
+            )
+            summarized_docs = []
+            for doc in docs:
+                summary = summarize_chain.invoke(
+                    {"input_documents": [doc]}, return_only_outputs=True
+                )
+
+                summarized_docs.append(summary["output_text"])
+
+            formatted_results = "\n\n".join(summarized_docs)
+            summary_step = AgentStep(
+                action=AgentAction(
+                    tool=original_action.tool,
+                    tool_input=original_action.tool_input,
+                    log=original_action.log,
+                ),
+                observation=formatted_results,
+            )
+            summary_tuple = (summary_step.action, summary_step.observation)
+            return [summary_tuple]
+
+        return intermediate_steps
+
+    def _handle_context_length_error(
+        self,
+        intermediate_steps: List[Tuple[AgentAction, str]],
+        run_manager: Optional[CallbackManagerForChainRun],
+        inputs: Dict[str, str],
+    ) -> Union[AgentFinish, List[AgentStep]]:
+        self._logger.log(
+            "debug",
+            "Context length exceeded. Asking user if they want to use summarize prompt to fit, this will reduce context length.",
+            color="yellow",
+        )
+        user_choice = click.confirm(
+            "Context length exceeded. Do you want to summarize the text to fit models context window?"
+        )
+        if user_choice:
+            self._logger.log(
+                "debug",
+                "Context length exceeded. Using summarize prompt to fit, this will reduce context length.",
+                color="bold_blue",
+            )
+            intermediate_steps = self._handle_context_length(intermediate_steps)
+
+            output = self.agent.plan(
+                intermediate_steps,
+                callbacks=run_manager.get_child() if run_manager else None,
+                **inputs,
+            )
+
+            if isinstance(output, AgentFinish):
+                return output
+            elif isinstance(output, AgentAction):
+                return [AgentStep(action=output, observation=None)]
+            else:
+                return [AgentStep(action=action, observation=None) for action in output]
+        else:
+            self._logger.log(
+                "debug",
+                "Context length exceeded. Consider using smaller text or RAG tools from crewai_tools.",
+                color="red",
+            )
+            raise SystemExit(
+                "Context length exceeded and user opted not to summarize. Consider using smaller text or RAG tools from crewai_tools."
+            )

src/crewai/cli/cli.py

@@ -6,9 +6,9 @@ from crewai.memory.storage.kickoff_task_outputs_storage import (
 )
 
 from .create_crew import create_crew
+from .evaluate_crew import evaluate_crew
 from .replay_from_task import replay_task_command
 from .reset_memories_command import reset_memories_command
-from .test_crew import test_crew
 from .train_crew import train_crew
 
 
@@ -144,7 +144,7 @@ def reset_memories(long, short, entities, kickoff_outputs, all):
 def test(n_iterations: int, model: str):
     """Test the crew and evaluate the results."""
     click.echo(f"Testing the crew for {n_iterations} iterations with model {model}")
-    test_crew(n_iterations, model)
+    evaluate_crew(n_iterations, model)
 
 
 if __name__ == "__main__":

src/crewai/cli/evaluate_crew.py

@@ -3,9 +3,9 @@ import subprocess
 import click
 
 
-def test_crew(n_iterations: int, model: str) -> None:
+def evaluate_crew(n_iterations: int, model: str) -> None:
     """
-    Test the crew by running a command in the Poetry environment.
+    Test and Evaluate the crew by running a command in the Poetry environment.
 
     Args:
         n_iterations (int): The number of iterations to test the crew.

src/crewai/cli/reset_memories_command.py

@@ -9,10 +9,14 @@ from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandle
 
 def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
     """
-    Replay the crew execution from a specific task.
+    Reset the crew memories.
 
     Args:
-      task_id (str): The ID of the task to replay from.
+      long (bool): Whether to reset the long-term memory.
+      short (bool): Whether to reset the short-term memory.
+      entity (bool): Whether to reset the entity memory.
+      kickoff_outputs (bool): Whether to reset the latest kickoff task outputs.
+      all (bool): Whether to reset all memories.
     """
 
     try:

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

@@ -5,6 +5,7 @@ research_task:
     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: >
@@ -13,3 +14,4 @@ reporting_task:
   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/crew.py

@@ -32,14 +32,12 @@ class {{crew_name}}Crew():
 	def research_task(self) -> Task:
 		return Task(
 			config=self.tasks_config['research_task'],
-			agent=self.researcher()
 		)
 
 	@task
 	def reporting_task(self) -> Task:
 		return Task(
 			config=self.tasks_config['reporting_task'],
-			agent=self.reporting_analyst(),
 			output_file='report.md'
 		)
 

src/crewai/cli/templates/pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = "^0.41.1" }
+crewai = { extras = ["tools"], version = "^0.46.0" }
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"

src/crewai/crew.py

@@ -155,6 +155,10 @@ class Crew(BaseModel):
         default=False,
         description="Plan the crew execution and add the plan to the crew.",
     )
+    planning_llm: Optional[Any] = Field(
+        default=None,
+        description="Language model that will run the AgentPlanner if planning is True.",
+    )
     task_execution_output_json_files: Optional[List[str]] = Field(
         default=None,
         description="List of file paths for task execution JSON files.",
@@ -267,20 +271,6 @@ class Crew(BaseModel):
 
         return self
 
-    @model_validator(mode="after")
-    def check_tasks_in_hierarchical_process_not_async(self):
-        """Validates that the tasks in hierarchical process are not flagged with async_execution."""
-        if self.process == Process.hierarchical:
-            for task in self.tasks:
-                if task.async_execution:
-                    raise PydanticCustomError(
-                        "async_execution_in_hierarchical_process",
-                        "Hierarchical process error: Tasks cannot be flagged with async_execution.",
-                        {},
-                    )
-
-        return self
-
     @model_validator(mode="after")
     def validate_end_with_at_most_one_async_task(self):
         """Validates that the crew ends with at most one asynchronous task."""
@@ -560,15 +550,12 @@ class Crew(BaseModel):
     def _handle_crew_planning(self):
         """Handles the Crew planning."""
         self._logger.log("info", "Planning the crew execution")
-        result = CrewPlanner(self.tasks)._handle_crew_planning()
+        result = CrewPlanner(
+            tasks=self.tasks, planning_agent_llm=self.planning_llm
+        )._handle_crew_planning()
 
-        if result is not None and hasattr(result, "list_of_plans_per_task"):
+        for task, step_plan in zip(self.tasks, result.list_of_plans_per_task):
-            for task, step_plan in zip(self.tasks, result.list_of_plans_per_task):
+            task.description += step_plan
-                task.description += step_plan
-        else:
-            self._logger.log(
-                "info", "Something went wrong with the planning process of the Crew"
-            )
 
     def _store_execution_log(
         self,
@@ -606,7 +593,7 @@ class Crew(BaseModel):
     def _run_hierarchical_process(self) -> CrewOutput:
         """Creates and assigns a manager agent to make sure the crew completes the tasks."""
         self._create_manager_agent()
-        return self._execute_tasks(self.tasks, self.manager_agent)
+        return self._execute_tasks(self.tasks)
 
     def _create_manager_agent(self):
         i18n = I18N(prompt_file=self.prompt_file)
@@ -630,7 +617,6 @@ class Crew(BaseModel):
     def _execute_tasks(
         self,
         tasks: List[Task],
-        manager: Optional[BaseAgent] = None,
         start_index: Optional[int] = 0,
         was_replayed: bool = False,
     ) -> CrewOutput:
@@ -658,13 +644,13 @@ class Crew(BaseModel):
                         last_sync_output = task.output
                 continue
 
-            agent_to_use = self._get_agent_to_use(task, manager)
+            agent_to_use = self._get_agent_to_use(task)
             if agent_to_use is None:
                 raise ValueError(
                     f"No agent available for task: {task.description}. Ensure that either the task has an assigned agent or a manager agent is provided."
                 )
 
-            self._prepare_agent_tools(task, manager)
+            self._prepare_agent_tools(task)
             self._log_task_start(task, agent_to_use.role)
 
             if isinstance(task, ConditionalTask):
@@ -730,20 +716,18 @@ class Crew(BaseModel):
             return skipped_task_output
         return None
 
-    def _prepare_agent_tools(self, task: Task, manager: Optional[BaseAgent]):
+    def _prepare_agent_tools(self, task: Task):
         if self.process == Process.hierarchical:
-            if manager:
+            if self.manager_agent:
-                self._update_manager_tools(task, manager)
+                self._update_manager_tools(task)
             else:
                 raise ValueError("Manager agent is required for hierarchical process.")
         elif task.agent and task.agent.allow_delegation:
             self._add_delegation_tools(task)
 
-    def _get_agent_to_use(
+    def _get_agent_to_use(self, task: Task) -> Optional[BaseAgent]:
-        self, task: Task, manager: Optional[BaseAgent]
-    ) -> Optional[BaseAgent]:
         if self.process == Process.hierarchical:
-            return manager
+            return self.manager_agent
         return task.agent
 
     def _add_delegation_tools(self, task: Task):
@@ -779,11 +763,14 @@ class Crew(BaseModel):
         if self.output_log_file:
             self._file_handler.log(agent=role, task=task.description, status="started")
 
-    def _update_manager_tools(self, task: Task, manager: BaseAgent):
+    def _update_manager_tools(self, task: Task):
-        if task.agent:
+        if self.manager_agent:
-            manager.tools = task.agent.get_delegation_tools([task.agent])
+            if task.agent:
-        else:
+                self.manager_agent.tools = task.agent.get_delegation_tools([task.agent])
-            manager.tools = manager.get_delegation_tools(self.agents)
+            else:
+                self.manager_agent.tools = self.manager_agent.get_delegation_tools(
+                    self.agents
+                )
 
     def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
         context = (
@@ -882,7 +869,7 @@ class Crew(BaseModel):
             self.tasks[i].output = task_output
 
         self._logging_color = "bold_blue"
-        result = self._execute_tasks(self.tasks, self.manager_agent, start_index, True)
+        result = self._execute_tasks(self.tasks, start_index, True)
         return result
 
     def copy(self):

src/crewai/memory/short_term/short_term_memory.py

@@ -1,3 +1,4 @@
+from typing import Any, Dict, Optional
 from crewai.memory.memory import Memory
 from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
 from crewai.memory.storage.rag_storage import RAGStorage
@@ -18,8 +19,15 @@ class ShortTermMemory(Memory):
         )
         super().__init__(storage)
 
-    def save(self, item: ShortTermMemoryItem) -> None:
+    def save(
-        super().save(item.data, item.metadata, item.agent)
+        self,
+        value: Any,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent: Optional[str] = None,
+    ) -> None:
+        item = ShortTermMemoryItem(data=value, metadata=metadata, agent=agent)
+
+        super().save(value=item.data, metadata=item.metadata, agent=item.agent)
 
     def search(self, query: str, score_threshold: float = 0.35):
         return self.storage.search(query=query, score_threshold=score_threshold)  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters

src/crewai/memory/short_term/short_term_memory_item.py

@@ -3,7 +3,10 @@ from typing import Any, Dict, Optional
 
 class ShortTermMemoryItem:
     def __init__(
-        self, data: Any, agent: str, metadata: Optional[Dict[str, Any]] = None
+        self,
+        data: Any,
+        agent: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ):
         self.data = data
         self.agent = agent

src/crewai/memory/storage/interface.py

@@ -4,7 +4,7 @@ from typing import Any, Dict
 class Storage:
     """Abstract base class defining the storage interface"""
 
-    def save(self, key: str, value: Any, metadata: Dict[str, Any]) -> None:
+    def save(self, value: Any, metadata: Dict[str, Any]) -> None:
         pass
 
     def search(self, key: str) -> Dict[str, Any]:  # type: ignore

src/crewai/project/__init__.py

@@ -1,2 +1,25 @@
-from .annotations import agent, crew, task
+from .annotations import (
+    agent,
+    crew,
+    task,
+    output_json,
+    output_pydantic,
+    tool,
+    callback,
+    llm,
+    cache_handler,
+)
 from .crew_base import CrewBase
+
+__all__ = [
+    "agent",
+    "crew",
+    "task",
+    "output_json",
+    "output_pydantic",
+    "tool",
+    "callback",
+    "CrewBase",
+    "llm",
+    "cache_handler",
+]

src/crewai/project/annotations.py

@@ -30,6 +30,37 @@ def agent(func):
     return func
 
 
+def llm(func):
+    func.is_llm = True
+    func = memoize(func)
+    return func
+
+
+def output_json(cls):
+    cls.is_output_json = True
+    return cls
+
+
+def output_pydantic(cls):
+    cls.is_output_pydantic = True
+    return cls
+
+
+def tool(func):
+    func.is_tool = True
+    return memoize(func)
+
+
+def callback(func):
+    func.is_callback = True
+    return memoize(func)
+
+
+def cache_handler(func):
+    func.is_cache_handler = True
+    return memoize(func)
+
+
 def crew(func):
     def wrapper(self, *args, **kwargs):
         instantiated_tasks = []

src/crewai/project/crew_base.py

@@ -1,6 +1,7 @@
 import inspect
 import os
 from pathlib import Path
+from typing import Any, Callable, Dict
 
 import yaml
 from dotenv import load_dotenv
@@ -20,11 +21,6 @@ def CrewBase(cls):
                 base_directory = Path(frame_info.filename).parent.resolve()
                 break
 
-        if base_directory is None:
-            raise Exception(
-                "Unable to dynamically determine the project's base directory, you must run it from the project's root directory."
-            )
-
         original_agents_config_path = getattr(
             cls, "agents_config", "config/agents.yaml"
         )
@@ -32,12 +28,20 @@ def CrewBase(cls):
 
         def __init__(self, *args, **kwargs):
             super().__init__(*args, **kwargs)
+
+            if self.base_directory is None:
+                raise Exception(
+                    "Unable to dynamically determine the project's base directory, you must run it from the project's root directory."
+                )
+
             self.agents_config = self.load_yaml(
                 os.path.join(self.base_directory, self.original_agents_config_path)
             )
             self.tasks_config = self.load_yaml(
                 os.path.join(self.base_directory, self.original_tasks_config_path)
             )
+            self.map_all_agent_variables()
+            self.map_all_task_variables()
 
         @staticmethod
         def load_yaml(config_path: str):
@@ -45,4 +49,138 @@ def CrewBase(cls):
                 # parsedContent = YamlParser.parse(file)  # type: ignore # Argument 1 to "parse" has incompatible type "TextIOWrapper"; expected "YamlParser"
                 return yaml.safe_load(file)
 
+        def _get_all_functions(self):
+            return {
+                name: getattr(self, name)
+                for name in dir(self)
+                if callable(getattr(self, name))
+            }
+
+        def _filter_functions(
+            self, functions: Dict[str, Callable], attribute: str
+        ) -> Dict[str, Callable]:
+            return {
+                name: func
+                for name, func in functions.items()
+                if hasattr(func, attribute)
+            }
+
+        def map_all_agent_variables(self) -> None:
+            all_functions = self._get_all_functions()
+            llms = self._filter_functions(all_functions, "is_llm")
+            tool_functions = self._filter_functions(all_functions, "is_tool")
+            cache_handler_functions = self._filter_functions(
+                all_functions, "is_cache_handler"
+            )
+            callbacks = self._filter_functions(all_functions, "is_callback")
+            agents = self._filter_functions(all_functions, "is_agent")
+
+            for agent_name, agent_info in self.agents_config.items():
+                self._map_agent_variables(
+                    agent_name,
+                    agent_info,
+                    agents,
+                    llms,
+                    tool_functions,
+                    cache_handler_functions,
+                    callbacks,
+                )
+
+        def _map_agent_variables(
+            self,
+            agent_name: str,
+            agent_info: Dict[str, Any],
+            agents: Dict[str, Callable],
+            llms: Dict[str, Callable],
+            tool_functions: Dict[str, Callable],
+            cache_handler_functions: Dict[str, Callable],
+            callbacks: Dict[str, Callable],
+        ) -> None:
+            if llm := agent_info.get("llm"):
+                self.agents_config[agent_name]["llm"] = llms[llm]()
+
+            if tools := agent_info.get("tools"):
+                self.agents_config[agent_name]["tools"] = [
+                    tool_functions[tool]() for tool in tools
+                ]
+
+            if function_calling_llm := agent_info.get("function_calling_llm"):
+                self.agents_config[agent_name]["function_calling_llm"] = agents[
+                    function_calling_llm
+                ]()
+
+            if step_callback := agent_info.get("step_callback"):
+                self.agents_config[agent_name]["step_callback"] = callbacks[
+                    step_callback
+                ]()
+
+            if cache_handler := agent_info.get("cache_handler"):
+                self.agents_config[agent_name]["cache_handler"] = (
+                    cache_handler_functions[cache_handler]()
+                )
+
+        def map_all_task_variables(self) -> None:
+            all_functions = self._get_all_functions()
+            agents = self._filter_functions(all_functions, "is_agent")
+            tasks = self._filter_functions(all_functions, "is_task")
+            output_json_functions = self._filter_functions(
+                all_functions, "is_output_json"
+            )
+            tool_functions = self._filter_functions(all_functions, "is_tool")
+            callback_functions = self._filter_functions(all_functions, "is_callback")
+            output_pydantic_functions = self._filter_functions(
+                all_functions, "is_output_pydantic"
+            )
+
+            for task_name, task_info in self.tasks_config.items():
+                self._map_task_variables(
+                    task_name,
+                    task_info,
+                    agents,
+                    tasks,
+                    output_json_functions,
+                    tool_functions,
+                    callback_functions,
+                    output_pydantic_functions,
+                )
+
+        def _map_task_variables(
+            self,
+            task_name: str,
+            task_info: Dict[str, Any],
+            agents: Dict[str, Callable],
+            tasks: Dict[str, Callable],
+            output_json_functions: Dict[str, Callable],
+            tool_functions: Dict[str, Callable],
+            callback_functions: Dict[str, Callable],
+            output_pydantic_functions: Dict[str, Callable],
+        ) -> None:
+            if context_list := task_info.get("context"):
+                self.tasks_config[task_name]["context"] = [
+                    tasks[context_task_name]() for context_task_name in context_list
+                ]
+
+            if tools := task_info.get("tools"):
+                self.tasks_config[task_name]["tools"] = [
+                    tool_functions[tool]() for tool in tools
+                ]
+
+            if agent_name := task_info.get("agent"):
+                self.tasks_config[task_name]["agent"] = agents[agent_name]()
+
+            if output_json := task_info.get("output_json"):
+                self.tasks_config[task_name]["output_json"] = output_json_functions[
+                    output_json
+                ]
+
+            if output_pydantic := task_info.get("output_pydantic"):
+                self.tasks_config[task_name]["output_pydantic"] = (
+                    output_pydantic_functions[output_pydantic]
+                )
+
+            if callbacks := task_info.get("callbacks"):
+                self.tasks_config[task_name]["callbacks"] = [
+                    callback_functions[callback]() for callback in callbacks
+                ]
+
     return WrappedClass

src/crewai/task.py

@@ -1,6 +1,6 @@
+import datetime
 import json
 import os
-import re
 import threading
 import uuid
 from concurrent.futures import Future
@@ -8,7 +8,6 @@ from copy import copy
 from hashlib import md5
 from typing import Any, Dict, List, Optional, Tuple, Type, Union
 
-from langchain_openai import ChatOpenAI
 from opentelemetry.trace import Span
 from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
 from pydantic_core import PydanticCustomError
@@ -17,10 +16,8 @@ from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry.telemetry import Telemetry
-from crewai.utilities.converter import Converter, ConverterError
+from crewai.utilities.converter import Converter, convert_to_model
 from crewai.utilities.i18n import I18N
-from crewai.utilities.printer import Printer
-from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
 
 class Task(BaseModel):
@@ -111,6 +108,7 @@ class Task(BaseModel):
     _original_description: str | None = None
     _original_expected_output: str | None = None
     _thread: threading.Thread | None = None
+    _execution_time: float | None = None
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
@@ -124,9 +122,15 @@ class Task(BaseModel):
                 "may_not_set_field", "This field is not to be set by the user.", {}
             )
 
+    def _set_start_execution_time(self) -> float:
+        return datetime.datetime.now().timestamp()
+
+    def _set_end_execution_time(self, start_time: float) -> None:
+        self._execution_time = datetime.datetime.now().timestamp() - start_time
+
     @field_validator("output_file")
     @classmethod
-    def output_file_validattion(cls, value: str) -> str:
+    def output_file_validation(cls, value: str) -> str:
         """Validate the output file path by removing the / from the beginning of the path."""
         if value.startswith("/"):
             return value[1:]
@@ -220,6 +224,7 @@ class Task(BaseModel):
                 f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
             )
 
+        start_time = self._set_start_execution_time()
         self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
 
         self.prompt_context = context
@@ -243,6 +248,7 @@ class Task(BaseModel):
         )
         self.output = task_output
 
+        self._set_end_execution_time(start_time)
         if self.callback:
             self.callback(self.output)
 
@@ -326,18 +332,6 @@ class Task(BaseModel):
 
         return copied_task
 
-    def _create_converter(self, *args, **kwargs) -> Converter:
-        """Create a converter instance."""
-        if self.agent and not self.converter_cls:
-            converter = self.agent.get_output_converter(*args, **kwargs)
-        elif self.converter_cls:
-            converter = self.converter_cls(*args, **kwargs)
-
-        if not converter:
-            raise Exception("No output converter found or set.")
-
-        return converter
-
     def _export_output(
         self, result: str
     ) -> Tuple[Optional[BaseModel], Optional[Dict[str, Any]]]:
@@ -345,75 +339,26 @@ class Task(BaseModel):
         json_output: Optional[Dict[str, Any]] = None
 
         if self.output_pydantic or self.output_json:
-            model_output = self._convert_to_model(result)
+            model_output = convert_to_model(
-            pydantic_output = (
+                result,
-                model_output if isinstance(model_output, BaseModel) else None
+                self.output_pydantic,
+                self.output_json,
+                self.agent,
+                self.converter_cls,
             )
-            if isinstance(model_output, str):
+
+            if isinstance(model_output, BaseModel):
+                pydantic_output = model_output
+            elif isinstance(model_output, dict):
+                json_output = model_output
+            elif isinstance(model_output, str):
                 try:
                     json_output = json.loads(model_output)
                 except json.JSONDecodeError:
                     json_output = None
-            else:
-                json_output = model_output if isinstance(model_output, dict) else None
 
         return pydantic_output, json_output
 
-    def _convert_to_model(self, result: str) -> Union[dict, BaseModel, str]:
-        model = self.output_pydantic or self.output_json
-        if model is None:
-            return result
-
-        try:
-            return self._validate_model(result, model)
-        except Exception:
-            return self._handle_partial_json(result, model)
-
-    def _validate_model(
-        self, result: str, model: Type[BaseModel]
-    ) -> Union[dict, BaseModel]:
-        exported_result = model.model_validate_json(result)
-        if self.output_json:
-            return exported_result.model_dump()
-        return exported_result
-
-    def _handle_partial_json(
-        self, result: str, model: Type[BaseModel]
-    ) -> Union[dict, BaseModel, str]:
-        match = re.search(r"({.*})", result, re.DOTALL)
-        if match:
-            try:
-                exported_result = model.model_validate_json(match.group(0))
-                if self.output_json:
-                    return exported_result.model_dump()
-                return exported_result
-            except Exception:
-                pass
-
-        return self._convert_with_instructions(result, model)
-
-    def _convert_with_instructions(
-        self, result: str, model: Type[BaseModel]
-    ) -> Union[dict, BaseModel, str]:
-        llm = self.agent.function_calling_llm or self.agent.llm  # type: ignore # Item "None" of "BaseAgent | None" has no attribute "function_calling_llm"
-        instructions = self._get_conversion_instructions(model, llm)
-
-        converter = self._create_converter(
-            llm=llm, text=result, model=model, instructions=instructions
-        )
-        exported_result = (
-            converter.to_pydantic() if self.output_pydantic else converter.to_json()
-        )
-
-        if isinstance(exported_result, ConverterError):
-            Printer().print(
-                content=f"{exported_result.message} Using raw output instead.",
-                color="red",
-            )
-            return result
-
-        return exported_result
-
     def _get_output_format(self) -> OutputFormat:
         if self.output_json:
             return OutputFormat.JSON
@@ -421,34 +366,22 @@ class Task(BaseModel):
             return OutputFormat.PYDANTIC
         return OutputFormat.RAW
 
-    def _get_conversion_instructions(self, model: Type[BaseModel], llm: Any) -> str:
-        instructions = "I'm gonna convert this raw text into valid JSON."
-        if not self._is_gpt(llm):
-            model_schema = PydanticSchemaParser(model=model).get_schema()
-            instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
-        return instructions
-
-    def _save_output(self, content: str) -> None:
-        if not self.output_file:
-            raise Exception("Output file path is not set.")
-
-        directory = os.path.dirname(self.output_file)
-        if directory and not os.path.exists(directory):
-            os.makedirs(directory)
-        with open(self.output_file, "w", encoding="utf-8") as file:
-            file.write(content)
-
-    def _is_gpt(self, llm) -> bool:
-        return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
-
     def _save_file(self, result: Any) -> None:
+        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"
 
         if directory and not os.path.exists(directory):
             os.makedirs(directory)
 
-        with open(self.output_file, "w", encoding="utf-8") as file:  # type: ignore # Argument 1 to "open" has incompatible type "str | None"; expected "int | str | bytes | PathLike[str] | PathLike[bytes]"
+        with open(self.output_file, "w", encoding="utf-8") as file:
-            file.write(result)
+            if isinstance(result, dict):
+                import json
+
+                json.dump(result, file, ensure_ascii=False, indent=2)
+            else:
+                file.write(str(result))
         return None
 
     def __repr__(self):

src/crewai/telemetry/telemetry.py

@@ -40,7 +40,7 @@ class Telemetry:
     - Roles of agents in a crew
     - Tools names available
 
-    Users can opt-in to sharing more complete data suing the `share_crew`
+    Users can opt-in to sharing more complete data using the `share_crew`
     attribute in the Crew class.
     """
 

src/crewai/tools/tool_usage.py

@@ -16,7 +16,7 @@ try:
 except ImportError:
     agentops = None
 
-OPENAI_BIGGER_MODELS = ["gpt-4"]
+OPENAI_BIGGER_MODELS = ["gpt-4o"]
 
 
 class ToolUsageErrorException(Exception):
@@ -86,7 +86,8 @@ class ToolUsage:
     ) -> str:
         if isinstance(calling, ToolUsageErrorException):
             error = calling.message
-            self._printer.print(content=f"\n\n{error}\n", color="red")
+            if self.agent.verbose:
+                self._printer.print(content=f"\n\n{error}\n", color="red")
             self.task.increment_tools_errors()
             return error
 
@@ -96,7 +97,8 @@ class ToolUsage:
         except Exception as e:
             error = getattr(e, "message", str(e))
             self.task.increment_tools_errors()
-            self._printer.print(content=f"\n\n{error}\n", color="red")
+            if self.agent.verbose:
+                self._printer.print(content=f"\n\n{error}\n", color="red")
             return error
         return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"  # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
 
@@ -112,7 +114,8 @@ class ToolUsage:
                 result = self._i18n.errors("task_repeated_usage").format(
                     tool_names=self.tools_names
                 )
-                self._printer.print(content=f"\n\n{result}\n", color="purple")
+                if self.agent.verbose:
+                    self._printer.print(content=f"\n\n{result}\n", color="purple")
                 self._telemetry.tool_repeated_usage(
                     llm=self.function_calling_llm,
                     tool_name=tool.name,
@@ -168,7 +171,10 @@ class ToolUsage:
                         f'\n{error_message}.\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
                     ).message
                     self.task.increment_tools_errors()
-                    self._printer.print(content=f"\n\n{error_message}\n", color="red")
+                    if self.agent.verbose:
+                        self._printer.print(
+                            content=f"\n\n{error_message}\n", color="red"
+                        )
                     return error  # type: ignore # No return value expected
 
                 self.task.increment_tools_errors()
@@ -192,7 +198,8 @@ class ToolUsage:
                     calling=calling, output=result, should_cache=should_cache
                 )
 
-        self._printer.print(content=f"\n\n{result}\n", color="purple")
+        if self.agent.verbose:
+            self._printer.print(content=f"\n\n{result}\n", color="purple")
         if agentops:
             agentops.record(tool_event)
         self._telemetry.tool_usage(
@@ -346,7 +353,8 @@ class ToolUsage:
             if self._run_attempts > self._max_parsing_attempts:
                 self._telemetry.tool_usage_error(llm=self.function_calling_llm)
                 self.task.increment_tools_errors()
-                self._printer.print(content=f"\n\n{e}\n", color="red")
+                if self.agent.verbose:
+                    self._printer.print(content=f"\n\n{e}\n", color="red")
                 return ToolUsageErrorException(  # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
                     f'{self._i18n.errors("tool_usage_error").format(error=e)}\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
                 )

src/crewai/utilities/__init__.py

@@ -7,6 +7,9 @@ from .parser import YamlParser
 from .printer import Printer
 from .prompts import Prompts
 from .rpm_controller import RPMController
+from .exceptions.context_window_exceeding_exception import (
+    LLMContextLengthExceededException,
+)
 
 __all__ = [
     "Converter",
@@ -19,4 +22,5 @@ __all__ = [
     "Prompts",
     "RPMController",
     "YamlParser",
+    "LLMContextLengthExceededException",
 ]

src/crewai/utilities/converter.py

@@ -1,9 +1,14 @@
 import json
+import re
+from typing import Any, Optional, Type, Union
 
 from langchain.schema import HumanMessage, SystemMessage
 from langchain_openai import ChatOpenAI
+from pydantic import BaseModel, ValidationError
 
 from crewai.agents.agent_builder.utilities.base_output_converter import OutputConverter
+from crewai.utilities.printer import Printer
+from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
 
 class ConverterError(Exception):
@@ -72,3 +77,153 @@ class Converter(OutputConverter):
     def is_gpt(self) -> bool:
         """Return if llm provided is of gpt from openai."""
         return isinstance(self.llm, ChatOpenAI) and self.llm.openai_api_base is None
+
+
+def convert_to_model(
+    result: str,
+    output_pydantic: Optional[Type[BaseModel]],
+    output_json: Optional[Type[BaseModel]],
+    agent: Any,
+    converter_cls: Optional[Type[Converter]] = None,
+) -> Union[dict, BaseModel, str]:
+    model = output_pydantic or output_json
+    if model is None:
+        return result
+
+    try:
+        escaped_result = json.dumps(json.loads(result, strict=False))
+        return validate_model(escaped_result, model, bool(output_json))
+    except json.JSONDecodeError as e:
+        Printer().print(
+            content=f"Error parsing JSON: {e}. Attempting to handle partial JSON.",
+            color="yellow",
+        )
+        return handle_partial_json(
+            result, model, bool(output_json), agent, converter_cls
+        )
+    except ValidationError as e:
+        Printer().print(
+            content=f"Pydantic validation error: {e}. Attempting to handle partial JSON.",
+            color="yellow",
+        )
+        return handle_partial_json(
+            result, model, bool(output_json), agent, converter_cls
+        )
+    except Exception as e:
+        Printer().print(
+            content=f"Unexpected error during model conversion: {type(e).__name__}: {e}. Returning original result.",
+            color="red",
+        )
+        return result
+
+
+def validate_model(
+    result: str, model: Type[BaseModel], is_json_output: bool
+) -> Union[dict, BaseModel]:
+    exported_result = model.model_validate_json(result)
+    if is_json_output:
+        return exported_result.model_dump()
+    return exported_result
+
+
+def handle_partial_json(
+    result: str,
+    model: Type[BaseModel],
+    is_json_output: bool,
+    agent: Any,
+    converter_cls: Optional[Type[Converter]] = None,
+) -> Union[dict, BaseModel, str]:
+    match = re.search(r"({.*})", result, re.DOTALL)
+    if match:
+        try:
+            exported_result = model.model_validate_json(match.group(0))
+            if is_json_output:
+                return exported_result.model_dump()
+            return exported_result
+        except json.JSONDecodeError as e:
+            Printer().print(
+                content=f"Error parsing JSON: {e}. The extracted JSON-like string is not valid JSON. Attempting alternative conversion method.",
+                color="yellow",
+            )
+        except ValidationError as e:
+            Printer().print(
+                content=f"Pydantic validation error: {e}. The JSON structure doesn't match the expected model. Attempting alternative conversion method.",
+                color="yellow",
+            )
+        except Exception as e:
+            Printer().print(
+                content=f"Unexpected error during partial JSON handling: {type(e).__name__}: {e}. Attempting alternative conversion method.",
+                color="red",
+            )
+
+    return convert_with_instructions(
+        result, model, is_json_output, agent, converter_cls
+    )
+
+
+def convert_with_instructions(
+    result: str,
+    model: Type[BaseModel],
+    is_json_output: bool,
+    agent: Any,
+    converter_cls: Optional[Type[Converter]] = None,
+) -> Union[dict, BaseModel, str]:
+    llm = agent.function_calling_llm or agent.llm
+    instructions = get_conversion_instructions(model, llm)
+
+    converter = create_converter(
+        agent=agent,
+        converter_cls=converter_cls,
+        llm=llm,
+        text=result,
+        model=model,
+        instructions=instructions,
+    )
+    exported_result = (
+        converter.to_pydantic() if not is_json_output else converter.to_json()
+    )
+
+    if isinstance(exported_result, ConverterError):
+        Printer().print(
+            content=f"{exported_result.message} Using raw output instead.",
+            color="red",
+        )
+        return result
+
+    return exported_result
+
+
+def get_conversion_instructions(model: Type[BaseModel], llm: Any) -> str:
+    instructions = "I'm gonna convert this raw text into valid JSON."
+    if not is_gpt(llm):
+        model_schema = PydanticSchemaParser(model=model).get_schema()
+        instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
+    return instructions
+
+
+def is_gpt(llm: Any) -> bool:
+    from langchain_openai import ChatOpenAI
+
+    return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
+
+
+def create_converter(
+    agent: Optional[Any] = None,
+    converter_cls: Optional[Type[Converter]] = None,
+    *args,
+    **kwargs,
+) -> Converter:
+    if agent and not converter_cls:
+        if hasattr(agent, "get_output_converter"):
+            converter = agent.get_output_converter(*args, **kwargs)
+        else:
+            raise AttributeError("Agent does not have a 'get_output_converter' method")
+    elif converter_cls:
+        converter = converter_cls(*args, **kwargs)
+    else:
+        raise ValueError("Either agent or converter_cls must be provided")
+
+    if not converter:
+        raise Exception("No output converter found or set.")
+
+    return converter

src/crewai/utilities/crew_pydantic_output_parser.py

@@ -1,5 +1,5 @@
 import json
-from typing import Any, List, Type, Union
+from typing import Any, List, Type
 
 import regex
 from langchain.output_parsers import PydanticOutputParser
@@ -7,29 +7,24 @@ from langchain_core.exceptions import OutputParserException
 from langchain_core.outputs import Generation
 from langchain_core.pydantic_v1 import ValidationError
 from pydantic import BaseModel
-from pydantic.v1 import BaseModel as V1BaseModel
 
 
 class CrewPydanticOutputParser(PydanticOutputParser):
     """Parses the text into pydantic models"""
 
-    pydantic_object: Union[Type[BaseModel], Type[V1BaseModel]]
+    pydantic_object: Type[BaseModel]
 
-    def parse_result(self, result: List[Generation], *, partial: bool = False) -> Any:
+    def parse_result(self, result: List[Generation]) -> Any:
         result[0].text = self._transform_in_valid_json(result[0].text)
 
         # Treating edge case of function calling llm returning the name instead of tool_name
         json_object = json.loads(result[0].text)
-        json_object["tool_name"] = (
+        if "tool_name" not in json_object:
-            json_object["name"]
+            json_object["tool_name"] = json_object.get("name", "")
-            if "tool_name" not in json_object
-            else json_object["tool_name"]
-        )
         result[0].text = json.dumps(json_object)
 
-        json_object = super().parse_result(result)
         try:
-            return self.pydantic_object.parse_obj(json_object)
+            return self.pydantic_object.model_validate(json_object)
         except ValidationError as e:
             name = self.pydantic_object.__name__
             msg = f"Failed to parse {name} from completion {json_object}. Got: {e}"

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -28,6 +28,7 @@ class CrewEvaluator:
     """
 
     tasks_scores: defaultdict = defaultdict(list)
+    run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
     def __init__(self, crew, openai_model_name: str):
@@ -40,9 +41,6 @@ class CrewEvaluator:
         for task in self.crew.tasks:
             task.callback = self.evaluate
 
-    def set_iteration(self, iteration: int) -> None:
-        self.iteration = iteration
-
     def _evaluator_agent(self):
         return Agent(
             role="Task Execution Evaluator",
@@ -71,6 +69,9 @@ class CrewEvaluator:
             output_pydantic=TaskEvaluationPydanticOutput,
         )
 
+    def set_iteration(self, iteration: int) -> None:
+        self.iteration = iteration
+
     def print_crew_evaluation_result(self) -> None:
         """
         Prints the evaluation result of the crew in a table.
@@ -119,6 +120,16 @@ class CrewEvaluator:
         ]
         table.add_row("Crew", *map(str, crew_scores), f"{crew_average:.1f}")
 
+        run_exec_times = [
+            int(sum(tasks_exec_times))
+            for _, tasks_exec_times in self.run_execution_times.items()
+        ]
+        execution_time_avg = int(sum(run_exec_times) / len(run_exec_times))
+        table.add_row(
+            "Execution Time (s)",
+            *map(str, run_exec_times),
+            f"{execution_time_avg}",
+        )
         # Display the table in the terminal
         console = Console()
         console.print(table)
@@ -145,5 +156,8 @@ class CrewEvaluator:
 
         if isinstance(evaluation_result.pydantic, TaskEvaluationPydanticOutput):
             self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
+            self.run_execution_times[self.iteration].append(
+                current_task._execution_time
+            )
         else:
             raise ValueError("Evaluation result is not in the expected format")

src/crewai/utilities/evaluators/task_evaluator.py

@@ -54,23 +54,23 @@ class TaskEvaluator:
     def __init__(self, original_agent):
         self.llm = original_agent.llm
 
-    def evaluate(self, task, ouput) -> TaskEvaluation:
+    def evaluate(self, task, output) -> TaskEvaluation:
         evaluation_query = (
             f"Assess the quality of the task completed based on the description, expected output, and actual results.\n\n"
             f"Task Description:\n{task.description}\n\n"
             f"Expected Output:\n{task.expected_output}\n\n"
-            f"Actual Output:\n{ouput}\n\n"
+            f"Actual Output:\n{output}\n\n"
             "Please provide:\n"
             "- Bullet points suggestions to improve future similar tasks\n"
             "- A score from 0 to 10 evaluating on completion, quality, and overall performance"
             "- Entities extracted from the task output, if any, their type, description, and relationships"
         )
 
-        instructions = "I'm gonna convert this raw text into valid JSON."
+        instructions = "Convert all responses into valid JSON output."
 
         if not self._is_gpt(self.llm):
             model_schema = PydanticSchemaParser(model=TaskEvaluation).get_schema()
-            instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
+            instructions = f"{instructions}\n\nReturn only valid JSON with the following schema:\n```json\n{model_schema}\n```"
 
         converter = Converter(
             llm=self.llm,

src/crewai/utilities/exceptions/context_window_exceeding_exception.py

@@ -0,0 +1,26 @@
+class LLMContextLengthExceededException(Exception):
+    CONTEXT_LIMIT_ERRORS = [
+        "maximum context length",
+        "context length exceeded",
+        "context_length_exceeded",
+        "context window full",
+        "too many tokens",
+        "input is too long",
+        "exceeds token limit",
+    ]
+
+    def __init__(self, error_message: str):
+        self.original_error_message = error_message
+        super().__init__(self._get_error_message(error_message))
+
+    def _is_context_limit_error(self, error_message: str) -> bool:
+        return any(
+            phrase.lower() in error_message.lower()
+            for phrase in self.CONTEXT_LIMIT_ERRORS
+        )
+
+    def _get_error_message(self, error_message: str):
+        return (
+            f"LLM context length exceeded. Original error: {error_message}\n"
+            "Consider using a smaller input or implementing a text splitting strategy."
+        )

src/crewai/utilities/parser.py

@@ -1,17 +1,28 @@
 import re
 
-
 class YamlParser:
+    @staticmethod
     def parse(file):
+        """
+        Parses a YAML file, modifies specific patterns, and checks for unsupported 'context' usage.
+        Args:
+            file (file object): The YAML file to parse.
+        Returns:
+            str: The modified content of the YAML file.
+        Raises:
+            ValueError: If 'context:' is used incorrectly.
+        """
         content = file.read()
+
         # Replace single { and } with doubled ones, while leaving already doubled ones intact and the other special characters {# and {%
         modified_content = re.sub(r"(?<!\{){(?!\{)(?!\#)(?!\%)", "{{", content)
-        modified_content = re.sub(
+        modified_content = re.sub(r"(?<!\})(?<!\%)(?<!\#)\}(?!})", "}}", modified_content)
-            r"(?<!\})(?<!\%)(?<!\#)\}(?!})", "}}", modified_content
+
-        )
         # Check for 'context:' not followed by '[' and raise an error
         if re.search(r"context:(?!\s*\[)", modified_content):
             raise ValueError(
-                "Context is currently only supported in code when creating a task. Please use the 'context' key in the task configuration."
+                "Context is currently only supported in code when creating a task. "
+                "Please use the 'context' key in the task configuration."
             )
+
         return modified_content

src/crewai/utilities/planning_handler.py

@@ -1,5 +1,6 @@
-from typing import List, Optional
+from typing import Any, List, Optional
 
+from langchain_openai import ChatOpenAI
 from pydantic import BaseModel
 
 from crewai.agent import Agent
@@ -11,17 +12,27 @@ class PlannerTaskPydanticOutput(BaseModel):
 
 
 class CrewPlanner:
-    def __init__(self, tasks: List[Task]):
+    def __init__(self, tasks: List[Task], planning_agent_llm: Optional[Any] = None):
         self.tasks = tasks
 
-    def _handle_crew_planning(self) -> Optional[BaseModel]:
+        if planning_agent_llm is None:
+            self.planning_agent_llm = ChatOpenAI(model="gpt-4o-mini")
+        else:
+            self.planning_agent_llm = planning_agent_llm
+
+    def _handle_crew_planning(self) -> PlannerTaskPydanticOutput:
         """Handles the Crew planning by creating detailed step-by-step plans for each task."""
         planning_agent = self._create_planning_agent()
         tasks_summary = self._create_tasks_summary()
 
         planner_task = self._create_planner_task(planning_agent, tasks_summary)
 
-        return planner_task.execute_sync().pydantic
+        result = planner_task.execute_sync()
+
+        if isinstance(result.pydantic, PlannerTaskPydanticOutput):
+            return result.pydantic
+
+        raise ValueError("Failed to get the Planning output")
 
     def _create_planning_agent(self) -> Agent:
         """Creates the planning agent for the crew planning."""
@@ -32,6 +43,7 @@ class CrewPlanner:
                 "available to each agent so that they can perform the tasks in an exemplary manner"
             ),
             backstory="Planner agent for crew planning",
+            llm=self.planning_agent_llm,
         )
 
     def _create_planner_task(self, planning_agent: Agent, tasks_summary: str) -> Task:

src/crewai/utilities/pydantic_schema_parser.py

@@ -16,11 +16,13 @@ class PydanticSchemaParser(BaseModel):
         return self._get_model_schema(self.model)
 
     def _get_model_schema(self, model, depth=0) -> str:
-        lines = []
+        indent = "    " * depth
+        lines = [f"{indent}{{"]
         for field_name, field in model.model_fields.items():
             field_type_str = self._get_field_type(field, depth + 1)
-            lines.append(f"{' ' * 4 * depth}- {field_name}: {field_type_str}")
+            lines.append(f"{indent}    {field_name}: {field_type_str},")
-
+        lines[-1] = lines[-1].rstrip(",")  # Remove trailing comma from last item
+        lines.append(f"{indent}}}")
         return "\n".join(lines)
 
     def _get_field_type(self, field, depth) -> str:
@@ -35,6 +37,6 @@ class PydanticSchemaParser(BaseModel):
             else:
                 return f"List[{list_item_type.__name__}]"
         elif issubclass(field_type, BaseModel):
-            return f"\n{self._get_model_schema(field_type, depth)}"
+            return self._get_model_schema(field_type, depth)
         else:
             return field_type.__name__

src/crewai/utilities/token_counter_callback.py

@@ -10,24 +10,24 @@ from crewai.agents.agent_builder.utilities.base_token_process import TokenProces
 class TokenCalcHandler(BaseCallbackHandler):
     model_name: str = ""
     token_cost_process: TokenProcess
+    encoding: tiktoken.Encoding
 
     def __init__(self, model_name, token_cost_process):
         self.model_name = model_name
         self.token_cost_process = token_cost_process
+        try:
+            self.encoding = tiktoken.encoding_for_model(self.model_name)
+        except KeyError:
+            self.encoding = tiktoken.get_encoding("cl100k_base")
 
     def on_llm_start(
         self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
     ) -> None:
-        try:
-            encoding = tiktoken.encoding_for_model(self.model_name)
-        except KeyError:
-            encoding = tiktoken.get_encoding("cl100k_base")
-
         if self.token_cost_process is None:
             return
 
         for prompt in prompts:
-            self.token_cost_process.sum_prompt_tokens(len(encoding.encode(prompt)))
+            self.token_cost_process.sum_prompt_tokens(len(self.encoding.encode(prompt)))
 
     async def on_llm_new_token(self, token: str, **kwargs) -> None:
         self.token_cost_process.sum_completion_tokens(1)

tests/agent_test.py

@@ -7,6 +7,7 @@ import pytest
 from langchain.tools import tool
 from langchain_core.exceptions import OutputParserException
 from langchain_openai import ChatOpenAI
+from langchain.schema import AgentAction
 
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
@@ -397,7 +398,7 @@ def test_agent_moved_on_after_max_iterations():
     )
 
     task = Task(
-        description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool over and over until you're told you can give yout final answer.",
+        description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool over and over until you're told you can give your final answer.",
         expected_output="The final answer",
     )
     output = agent.execute_task(
@@ -948,7 +949,7 @@ def test_agent_use_trained_data(crew_training_handler):
     crew_training_handler().load.return_value = {
         agent.role: {
             "suggestions": [
-                "The result of the math operatio must be right.",
+                "The result of the math operation must be right.",
                 "Result must be better than 1.",
             ]
         }
@@ -958,7 +959,7 @@ def test_agent_use_trained_data(crew_training_handler):
 
     assert (
         result == "What is 1 + 1?You MUST follow these feedbacks: \n "
-        "The result of the math operatio must be right.\n - Result must be better than 1."
+        "The result of the math operation must be right.\n - Result must be better than 1."
     )
     crew_training_handler.assert_has_calls(
         [mock.call(), mock.call("trained_agents_data.pkl"), mock.call().load()]
@@ -1014,3 +1015,75 @@ def test_agent_max_retry_limit():
                 ),
             ]
         )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_context_length_exceeds_limit():
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+    )
+    original_action = AgentAction(
+        tool="test_tool", tool_input="test_input", log="test_log"
+    )
+
+    with patch.object(
+        CrewAgentExecutor, "_iter_next_step", wraps=agent.agent_executor._iter_next_step
+    ) as private_mock:
+        task = Task(
+            description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            expected_output="The final answer",
+        )
+        agent.execute_task(
+            task=task,
+        )
+        private_mock.assert_called_once()
+        with patch("crewai.agents.executor.click") as mock_prompt:
+            mock_prompt.return_value = "y"
+            with patch.object(
+                CrewAgentExecutor, "_handle_context_length"
+            ) as mock_handle_context:
+                mock_handle_context.side_effect = ValueError(
+                    "Context length limit exceeded"
+                )
+
+                long_input = "This is a very long input. " * 10000
+
+                # Attempt to handle context length, expecting the mocked error
+                with pytest.raises(ValueError) as excinfo:
+                    agent.agent_executor._handle_context_length(
+                        [(original_action, long_input)]
+                    )
+
+                assert "Context length limit exceeded" in str(excinfo.value)
+                mock_handle_context.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_context_length_exceeds_limit_cli_no():
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+    )
+    task = Task(description="test task", agent=agent, expected_output="test output")
+
+    with patch.object(
+        CrewAgentExecutor, "_iter_next_step", wraps=agent.agent_executor._iter_next_step
+    ) as private_mock:
+        task = Task(
+            description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            expected_output="The final answer",
+        )
+        agent.execute_task(
+            task=task,
+        )
+        private_mock.assert_called_once()
+        with patch("crewai.agents.executor.click") as mock_prompt:
+            mock_prompt.return_value = "n"
+            pytest.raises(SystemExit)
+            with patch.object(
+                CrewAgentExecutor, "_handle_context_length"
+            ) as mock_handle_context:
+                mock_handle_context.assert_not_called()

tests/cassettes/test_handle_context_length_exceeds_limit.yaml

@@ -0,0 +1,181 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: The final answer is 42.
+      But don''t give it yet, instead keep using the `get_final_answer` tool.\n\nThis
+      is the expect criteria for your final answer: The final answer \n you 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:\n", "role": "user"}], "model": "gpt-4o",
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '938'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        The"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        is"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"42"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ac1a40879b87d1f-LAX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Thu, 01 Aug 2024 00:16:40 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=MHUl15YVi607cmuLtQ84ESiH30IyJiIW1a40fopQ81w-1722471400-1.0.1.1-OGpq5Ezj6iE0ToM1diQllGb70.J3O_K2De9NbwZPWmW2qN07U20adJ_0yd6PKUNqMdL.xEnLcNAOWVmsfrLUrQ;
+        path=/; expires=Thu, 01-Aug-24 00:46:40 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=G2ZVNvfNfFk4DeKyZ7jMYetG7wOasINAGHstrOnuAY8-1722471400129-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '131'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15552000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_b68b417b3fe1c67244279551e411b37a
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_handle_context_length_exceeds_limit_cli_no.yaml

@@ -0,0 +1,162 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: The final answer is 42.
+      But don''t give it yet, instead keep using the `get_final_answer` tool.\n\nThis
+      is the expect criteria for your final answer: The final answer \n you 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:\n", "role": "user"}], "model": "gpt-4o",
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '938'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"42"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ac331b9eaee2b7f-LAX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Thu, 01 Aug 2024 04:48:09 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=OXht5zC71vWYFW_z_933m3sZfFS2xBez0DHv93FvT5s-1722487689-1.0.1.1-wE8JTR7MnwUgiiTDppYg8A7zLEiidth.MB0zrwONeAtNWRjKC1tuGf8LZYDlYIHUhqG73syYExpZ.5pZhzJkcg;
+        path=/; expires=Thu, 01-Aug-24 05:18:09 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=PAR7y4xRe4VzRT.7GK34Tq5r8vevY6xq0E.i.R40xnU-1722487689562-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '84'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15552000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_105dcfc53c9672dea0437249c12c3319
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cli/cli_test.py

@@ -135,29 +135,29 @@ def test_version_command_with_tools(runner):
     )
 
 
-@mock.patch("crewai.cli.cli.test_crew")
+@mock.patch("crewai.cli.cli.evaluate_crew")
-def test_test_default_iterations(test_crew, runner):
+def test_test_default_iterations(evaluate_crew, runner):
     result = runner.invoke(test)
 
-    test_crew.assert_called_once_with(3, "gpt-4o-mini")
+    evaluate_crew.assert_called_once_with(3, "gpt-4o-mini")
     assert result.exit_code == 0
     assert "Testing the crew for 3 iterations with model gpt-4o-mini" in result.output
 
 
-@mock.patch("crewai.cli.cli.test_crew")
+@mock.patch("crewai.cli.cli.evaluate_crew")
-def test_test_custom_iterations(test_crew, runner):
+def test_test_custom_iterations(evaluate_crew, runner):
     result = runner.invoke(test, ["--n_iterations", "5", "--model", "gpt-4o"])
 
-    test_crew.assert_called_once_with(5, "gpt-4o")
+    evaluate_crew.assert_called_once_with(5, "gpt-4o")
     assert result.exit_code == 0
     assert "Testing the crew for 5 iterations with model gpt-4o" in result.output
 
 
-@mock.patch("crewai.cli.cli.test_crew")
+@mock.patch("crewai.cli.cli.evaluate_crew")
-def test_test_invalid_string_iterations(test_crew, runner):
+def test_test_invalid_string_iterations(evaluate_crew, runner):
     result = runner.invoke(test, ["--n_iterations", "invalid"])
 
-    test_crew.assert_not_called()
+    evaluate_crew.assert_not_called()
     assert result.exit_code == 2
     assert (
         "Usage: test [OPTIONS]\nTry 'test --help' for help.\n\nError: Invalid value for '-n' / '--n_iterations': 'invalid' is not a valid integer.\n"

tests/cli/test_crew_test.py

@@ -3,7 +3,7 @@ from unittest import mock
 
 import pytest
 
-from crewai.cli import test_crew
+from crewai.cli import evaluate_crew
 
 
 @pytest.mark.parametrize(
@@ -14,13 +14,13 @@ from crewai.cli import test_crew
         (10, "gpt-4"),
     ],
 )
-@mock.patch("crewai.cli.test_crew.subprocess.run")
+@mock.patch("crewai.cli.evaluate_crew.subprocess.run")
 def test_crew_success(mock_subprocess_run, n_iterations, model):
     """Test the crew function for successful execution."""
     mock_subprocess_run.return_value = subprocess.CompletedProcess(
         args=f"poetry run test {n_iterations} {model}", returncode=0
     )
-    result = test_crew.test_crew(n_iterations, model)
+    result = evaluate_crew.evaluate_crew(n_iterations, model)
 
     mock_subprocess_run.assert_called_once_with(
         ["poetry", "run", "test", str(n_iterations), model],
@@ -31,26 +31,26 @@ def test_crew_success(mock_subprocess_run, n_iterations, model):
     assert result is None
 
 
-@mock.patch("crewai.cli.test_crew.click")
+@mock.patch("crewai.cli.evaluate_crew.click")
 def test_test_crew_zero_iterations(click):
-    test_crew.test_crew(0, "gpt-4o")
+    evaluate_crew.evaluate_crew(0, "gpt-4o")
     click.echo.assert_called_once_with(
         "An unexpected error occurred: The number of iterations must be a positive integer.",
         err=True,
     )
 
 
-@mock.patch("crewai.cli.test_crew.click")
+@mock.patch("crewai.cli.evaluate_crew.click")
 def test_test_crew_negative_iterations(click):
-    test_crew.test_crew(-2, "gpt-4o")
+    evaluate_crew.evaluate_crew(-2, "gpt-4o")
     click.echo.assert_called_once_with(
         "An unexpected error occurred: The number of iterations must be a positive integer.",
         err=True,
     )
 
 
-@mock.patch("crewai.cli.test_crew.click")
+@mock.patch("crewai.cli.evaluate_crew.click")
-@mock.patch("crewai.cli.test_crew.subprocess.run")
+@mock.patch("crewai.cli.evaluate_crew.subprocess.run")
 def test_test_crew_called_process_error(mock_subprocess_run, click):
     n_iterations = 5
     mock_subprocess_run.side_effect = subprocess.CalledProcessError(
@@ -59,7 +59,7 @@ def test_test_crew_called_process_error(mock_subprocess_run, click):
         output="Error",
         stderr="Some error occurred",
     )
-    test_crew.test_crew(n_iterations, "gpt-4o")
+    evaluate_crew.evaluate_crew(n_iterations, "gpt-4o")
 
     mock_subprocess_run.assert_called_once_with(
         ["poetry", "run", "test", "5", "gpt-4o"],
@@ -78,13 +78,13 @@ def test_test_crew_called_process_error(mock_subprocess_run, click):
     )
 
 
-@mock.patch("crewai.cli.test_crew.click")
+@mock.patch("crewai.cli.evaluate_crew.click")
-@mock.patch("crewai.cli.test_crew.subprocess.run")
+@mock.patch("crewai.cli.evaluate_crew.subprocess.run")
 def test_test_crew_unexpected_exception(mock_subprocess_run, click):
     # Arrange
     n_iterations = 5
     mock_subprocess_run.side_effect = Exception("Unexpected error")
-    test_crew.test_crew(n_iterations, "gpt-4o")
+    evaluate_crew.evaluate_crew(n_iterations, "gpt-4o")
 
     mock_subprocess_run.assert_called_once_with(
         ["poetry", "run", "test", "5", "gpt-4o"],

tests/crew_test.py

@@ -8,7 +8,6 @@ from unittest.mock import MagicMock, patch
 
 import pydantic_core
 import pytest
-
 from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
@@ -69,7 +68,7 @@ def test_crew_config_conditional_requirement():
                     "agent": "Senior Researcher",
                 },
                 {
-                    "description": "Write a 1 amazing paragraph highlight for each idead that showcases how good an article about this topic could be, check references if necessary or search for more content but make sure it's unique, interesting and well written. Return the list of ideas with their paragraph and your notes.",
+                    "description": "Write a 1 amazing paragraph highlight for each idea that showcases how good an article about this topic could be, check references if necessary or search for more content but make sure it's unique, interesting and well written. Return the list of ideas with their paragraph and your notes.",
                     "expected_output": "A 4 paragraph article about AI.",
                     "agent": "Senior Writer",
                 },
@@ -657,7 +656,7 @@ def test_sequential_async_task_execution_completion():
 
     sequential_result = sequential_crew.kickoff()
     assert sequential_result.raw.startswith(
-        "**The Evolution of Artificial Intelligence: A Journey Through Milestones**"
+        "The history of artificial intelligence (AI) is marked by several pivotal events that have shaped its evolution and impact on various sectors."
     )
 
 
@@ -1189,7 +1188,7 @@ def test_task_with_no_arguments():
     )
 
     task = Task(
-        description="Look at the available data nd give me a sense on the total number of sales.",
+        description="Look at the available data and give me a sense on the total number of sales.",
         expected_output="The total number of sales as an integer",
         agent=researcher,
     )
@@ -1236,7 +1235,7 @@ def test_delegation_is_not_enabled_if_there_are_only_one_agent():
     )
 
     task = Task(
-        description="Look at the available data nd give me a sense on the total number of sales.",
+        description="Look at the available data and give me a sense on the total number of sales.",
         expected_output="The total number of sales as an integer",
         agent=researcher,
     )
@@ -1312,14 +1311,14 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     )
 
     result = crew.kickoff()
-    assert result.raw == '"Howdy!"'
+    assert result.raw == "Howdy!"
 
     print(crew.usage_metrics)
 
     assert crew.usage_metrics == {
-        "total_tokens": 311,
+        "total_tokens": 219,
-        "prompt_tokens": 224,
+        "prompt_tokens": 201,
-        "completion_tokens": 87,
+        "completion_tokens": 18,
         "successful_requests": 1,
     }
 
@@ -1356,28 +1355,66 @@ def test_hierarchical_crew_creation_tasks_with_agents():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_crew_creation_tasks_with_async_execution():
+    """
+    Agents are not required for tasks in a hierarchical process but sometimes they are still added
+    This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
+    """
     from langchain_openai import ChatOpenAI
 
     task = Task(
-        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        description="Write one amazing paragraph about AI.",
-        expected_output="5 bullet points with a paragraph for each idea.",
+        expected_output="A single paragraph with 4 sentences.",
-        async_execution=True,  # should throw an error
+        agent=writer,
+        async_execution=True,
     )
 
-    with pytest.raises(pydantic_core._pydantic_core.ValidationError) as exec_info:
+    crew = Crew(
-        Crew(
+        tasks=[task],
-            tasks=[task],
+        agents=[writer, researcher, ceo],
-            agents=[researcher],
+        process=Process.hierarchical,
-            process=Process.hierarchical,
+        manager_llm=ChatOpenAI(model="gpt-4o"),
-            manager_llm=ChatOpenAI(model="gpt-4o"),
-        )
-
-    assert (
-        exec_info.value.errors()[0]["type"] == "async_execution_in_hierarchical_process"
     )
-    assert (
+
-        "Hierarchical process error: Tasks cannot be flagged with async_execution."
+    crew.kickoff()
-        in exec_info.value.errors()[0]["msg"]
+    assert crew.manager_agent is not None
+    assert crew.manager_agent.tools is not None
+    assert crew.manager_agent.tools[0].description.startswith(
+        "Delegate a specific task to one of the following coworkers: Senior Writer\n"
+    )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_hierarchical_crew_creation_tasks_with_sync_last():
+    """
+    Agents are not required for tasks in a hierarchical process but sometimes they are still added
+    This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
+    """
+    from langchain_openai import ChatOpenAI
+
+    task = Task(
+        description="Write one amazing paragraph about AI.",
+        expected_output="A single paragraph with 4 sentences.",
+        agent=writer,
+        async_execution=True,
+    )
+    task2 = Task(
+        description="Write one amazing paragraph about AI.",
+        expected_output="A single paragraph with 4 sentences.",
+        async_execution=False,
+    )
+
+    crew = Crew(
+        tasks=[task, task2],
+        agents=[writer, researcher, ceo],
+        process=Process.hierarchical,
+        manager_llm=ChatOpenAI(model="gpt-4o"),
+    )
+
+    crew.kickoff()
+    assert crew.manager_agent is not None
+    assert crew.manager_agent.tools is not None
+    assert crew.manager_agent.tools[0].description.startswith(
+        "Delegate a specific task to one of the following coworkers: Senior Writer, Researcher, CEO\n"
     )
 
 
@@ -1561,16 +1598,16 @@ def test_tools_with_custom_caching():
 
     writer1 = Agent(
         role="Writer",
-        goal="You write lesssons of math for kids.",
+        goal="You write lessons of math for kids.",
-        backstory="You're an expert in writting and you love to teach kids but you know nothing of math.",
+        backstory="You're an expert in writing and you love to teach kids but you know nothing of math.",
         tools=[multiplcation_tool],
         allow_delegation=False,
     )
 
     writer2 = Agent(
         role="Writer",
-        goal="You write lesssons of math for kids.",
+        goal="You write lessons of math for kids.",
-        backstory="You're an expert in writting and you love to teach kids but you know nothing of math.",
+        backstory="You're an expert in writing and you love to teach kids but you know nothing of math.",
         tools=[multiplcation_tool],
         allow_delegation=False,
     )

tests/memory/short_term_memory_test.py

@@ -23,10 +23,7 @@ def short_term_memory():
         expected_output="A list of relevant URLs based on the search query.",
         agent=agent,
     )
-    return ShortTermMemory(crew=Crew(
+    return ShortTermMemory(crew=Crew(agents=[agent], tasks=[task]))
-        agents=[agent],
-        tasks=[task]
-    ))
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -38,7 +35,11 @@ def test_save_and_search(short_term_memory):
         agent="test_agent",
         metadata={"task": "test_task"},
     )
-    short_term_memory.save(memory)
+    short_term_memory.save(
+        value=memory.data,
+        metadata=memory.metadata,
+        agent=memory.agent,
+    )
 
     find = short_term_memory.search("test value", score_threshold=0.01)[0]
     assert find["context"] == memory.data, "Data value mismatch."

tests/task_test.py

@@ -5,13 +5,12 @@ import json
 from unittest.mock import MagicMock, patch
 
 import pytest
-from pydantic import BaseModel
-from pydantic_core import ValidationError
-
 from crewai import Agent, Crew, Process, Task
 from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.task_output import TaskOutput
 from crewai.utilities.converter import Converter
+from pydantic import BaseModel
+from pydantic_core import ValidationError
 
 
 def test_task_tool_reflect_agent_tools():
@@ -110,7 +109,7 @@ def test_task_callback():
         task_completed.assert_called_once_with(task.output)
 
 
-def test_task_callback_returns_task_ouput():
+def test_task_callback_returns_task_output():
     from crewai.tasks.output_format import OutputFormat
 
     researcher = Agent(

tests/utilities/evaluators/test_crew_evaluator_handler.py

@@ -84,6 +84,10 @@ class TestCrewEvaluator:
             1: [10, 9, 8],
             2: [9, 8, 7],
         }
+        crew_planner.run_execution_times = {
+            1: [24, 45, 66],
+            2: [55, 33, 67],
+        }
 
         crew_planner.print_crew_evaluation_result()
 
@@ -98,6 +102,7 @@ class TestCrewEvaluator:
                 mock.call().add_row("Task 2", "9", "8", "8.5"),
                 mock.call().add_row("Task 3", "8", "7", "7.5"),
                 mock.call().add_row("Crew", "9.0", "8.0", "8.5"),
+                mock.call().add_row("Execution Time (s)", "135", "155", "145"),
             ]
         )
         console.assert_has_calls([mock.call(), mock.call().print(table())])

tests/utilities/evaluators/test_task_evaluator.py

@@ -56,8 +56,7 @@ def test_evaluate_training_data(converter_mock):
                 "based on the human feedback\n",
                 model=TrainingTaskEvaluation,
                 instructions="I'm gonna convert this raw text into valid JSON.\n\nThe json should have the "
-                "following structure, with the following keys:\n- suggestions: List[str]\n- "
+                "following structure, with the following keys:\n{\n    suggestions: List[str],\n    quality: float,\n    final_summary: str\n}",
-                "quality: float\n- final_summary: str",
             ),
             mock.call().to_pydantic(),
         ]

tests/utilities/test_converter.py

@@ -0,0 +1,266 @@
+import json
+from unittest.mock import MagicMock, Mock, patch
+
+import pytest
+from crewai.utilities.converter import (
+    Converter,
+    ConverterError,
+    convert_to_model,
+    convert_with_instructions,
+    create_converter,
+    get_conversion_instructions,
+    handle_partial_json,
+    is_gpt,
+    validate_model,
+)
+from pydantic import BaseModel
+
+
+# Sample Pydantic models for testing
+class EmailResponse(BaseModel):
+    previous_message_content: str
+
+
+class EmailResponses(BaseModel):
+    responses: list[EmailResponse]
+
+
+class SimpleModel(BaseModel):
+    name: str
+    age: int
+
+
+class NestedModel(BaseModel):
+    id: int
+    data: SimpleModel
+
+
+# Fixtures
+@pytest.fixture
+def mock_agent():
+    agent = Mock()
+    agent.function_calling_llm = None
+    agent.llm = Mock()
+    return agent
+
+
+# Tests for convert_to_model
+def test_convert_to_model_with_valid_json():
+    result = '{"name": "John", "age": 30}'
+    output = convert_to_model(result, SimpleModel, None, None)
+    assert isinstance(output, SimpleModel)
+    assert output.name == "John"
+    assert output.age == 30
+
+
+def test_convert_to_model_with_invalid_json():
+    result = '{"name": "John", "age": "thirty"}'
+    with patch("crewai.utilities.converter.handle_partial_json") as mock_handle:
+        mock_handle.return_value = "Fallback result"
+        output = convert_to_model(result, SimpleModel, None, None)
+        assert output == "Fallback result"
+
+
+def test_convert_to_model_with_no_model():
+    result = "Plain text"
+    output = convert_to_model(result, None, None, None)
+    assert output == "Plain text"
+
+
+def test_convert_to_model_with_special_characters():
+    json_string_test = """
+    {
+        "responses": [
+            {
+                "previous_message_content": "Hi Tom,\r\n\r\nNiamh has chosen the Mika phonics on"
+            }
+        ]
+    }
+    """
+    output = convert_to_model(json_string_test, EmailResponses, None, None)
+    assert isinstance(output, EmailResponses)
+    assert len(output.responses) == 1
+    assert (
+        output.responses[0].previous_message_content
+        == "Hi Tom,\r\n\r\nNiamh has chosen the Mika phonics on"
+    )
+
+
+def test_convert_to_model_with_escaped_special_characters():
+    json_string_test = json.dumps(
+        {
+            "responses": [
+                {
+                    "previous_message_content": "Hi Tom,\r\n\r\nNiamh has chosen the Mika phonics on"
+                }
+            ]
+        }
+    )
+    output = convert_to_model(json_string_test, EmailResponses, None, None)
+    assert isinstance(output, EmailResponses)
+    assert len(output.responses) == 1
+    assert (
+        output.responses[0].previous_message_content
+        == "Hi Tom,\r\n\r\nNiamh has chosen the Mika phonics on"
+    )
+
+
+def test_convert_to_model_with_multiple_special_characters():
+    json_string_test = """
+    {
+        "responses": [
+            {
+                "previous_message_content": "Line 1\r\nLine 2\tTabbed\nLine 3\r\n\rEscaped newline"
+            }
+        ]
+    }
+    """
+    output = convert_to_model(json_string_test, EmailResponses, None, None)
+    assert isinstance(output, EmailResponses)
+    assert len(output.responses) == 1
+    assert (
+        output.responses[0].previous_message_content
+        == "Line 1\r\nLine 2\tTabbed\nLine 3\r\n\rEscaped newline"
+    )
+
+
+# Tests for validate_model
+def test_validate_model_pydantic_output():
+    result = '{"name": "Alice", "age": 25}'
+    output = validate_model(result, SimpleModel, False)
+    assert isinstance(output, SimpleModel)
+    assert output.name == "Alice"
+    assert output.age == 25
+
+
+def test_validate_model_json_output():
+    result = '{"name": "Bob", "age": 40}'
+    output = validate_model(result, SimpleModel, True)
+    assert isinstance(output, dict)
+    assert output == {"name": "Bob", "age": 40}
+
+
+# Tests for handle_partial_json
+def test_handle_partial_json_with_valid_partial():
+    result = 'Some text {"name": "Charlie", "age": 35} more text'
+    output = handle_partial_json(result, SimpleModel, False, None)
+    assert isinstance(output, SimpleModel)
+    assert output.name == "Charlie"
+    assert output.age == 35
+
+
+def test_handle_partial_json_with_invalid_partial(mock_agent):
+    result = "No valid JSON here"
+    with patch("crewai.utilities.converter.convert_with_instructions") as mock_convert:
+        mock_convert.return_value = "Converted result"
+        output = handle_partial_json(result, SimpleModel, False, mock_agent)
+        assert output == "Converted result"
+
+
+# Tests for convert_with_instructions
+@patch("crewai.utilities.converter.create_converter")
+@patch("crewai.utilities.converter.get_conversion_instructions")
+def test_convert_with_instructions_success(
+    mock_get_instructions, mock_create_converter, mock_agent
+):
+    mock_get_instructions.return_value = "Instructions"
+    mock_converter = Mock()
+    mock_converter.to_pydantic.return_value = SimpleModel(name="David", age=50)
+    mock_create_converter.return_value = mock_converter
+
+    result = "Some text to convert"
+    output = convert_with_instructions(result, SimpleModel, False, mock_agent)
+
+    assert isinstance(output, SimpleModel)
+    assert output.name == "David"
+    assert output.age == 50
+
+
+@patch("crewai.utilities.converter.create_converter")
+@patch("crewai.utilities.converter.get_conversion_instructions")
+def test_convert_with_instructions_failure(
+    mock_get_instructions, mock_create_converter, mock_agent
+):
+    mock_get_instructions.return_value = "Instructions"
+    mock_converter = Mock()
+    mock_converter.to_pydantic.return_value = ConverterError("Conversion failed")
+    mock_create_converter.return_value = mock_converter
+
+    result = "Some text to convert"
+    with patch("crewai.utilities.converter.Printer") as mock_printer:
+        output = convert_with_instructions(result, SimpleModel, False, mock_agent)
+        assert output == result
+        mock_printer.return_value.print.assert_called_once()
+
+
+# Tests for get_conversion_instructions
+def test_get_conversion_instructions_gpt():
+    mock_llm = Mock()
+    mock_llm.openai_api_base = None
+    with patch("crewai.utilities.converter.is_gpt", return_value=True):
+        instructions = get_conversion_instructions(SimpleModel, mock_llm)
+        assert instructions == "I'm gonna convert this raw text into valid JSON."
+
+
+def test_get_conversion_instructions_non_gpt():
+    mock_llm = Mock()
+    with patch("crewai.utilities.converter.is_gpt", return_value=False):
+        with patch("crewai.utilities.converter.PydanticSchemaParser") as mock_parser:
+            mock_parser.return_value.get_schema.return_value = "Sample schema"
+            instructions = get_conversion_instructions(SimpleModel, mock_llm)
+            assert "Sample schema" in instructions
+
+
+# Tests for is_gpt
+def test_is_gpt_true():
+    from langchain_openai import ChatOpenAI
+
+    mock_llm = Mock(spec=ChatOpenAI)
+    mock_llm.openai_api_base = None
+    assert is_gpt(mock_llm) is True
+
+
+def test_is_gpt_false():
+    mock_llm = Mock()
+    assert is_gpt(mock_llm) is False
+
+
+class CustomConverter(Converter):
+    pass
+
+
+def test_create_converter_with_mock_agent():
+    mock_agent = MagicMock()
+    mock_agent.get_output_converter.return_value = MagicMock(spec=Converter)
+
+    converter = create_converter(
+        agent=mock_agent,
+        llm=Mock(),
+        text="Sample",
+        model=SimpleModel,
+        instructions="Convert",
+    )
+
+    assert isinstance(converter, Converter)
+    mock_agent.get_output_converter.assert_called_once()
+
+
+def test_create_converter_with_custom_converter():
+    converter = create_converter(
+        converter_cls=CustomConverter,
+        llm=Mock(),
+        text="Sample",
+        model=SimpleModel,
+        instructions="Convert",
+    )
+
+    assert isinstance(converter, CustomConverter)
+
+
+def test_create_converter_fails_without_agent_or_converter_cls():
+    with pytest.raises(
+        ValueError, match="Either agent or converter_cls must be provided"
+    ):
+        create_converter(
+            llm=Mock(), text="Sample", model=SimpleModel, instructions="Convert"
+        )

tests/utilities/test_planning_handler.py

@@ -1,10 +1,11 @@
 from unittest.mock import patch
-from crewai.tasks.task_output import TaskOutput
 
 import pytest
+from langchain_openai import ChatOpenAI
 
 from crewai.agent import Agent
 from crewai.task import Task
+from crewai.tasks.task_output import TaskOutput
 from crewai.utilities.planning_handler import CrewPlanner, PlannerTaskPydanticOutput
 
 
@@ -28,7 +29,19 @@ class TestCrewPlanner:
                 agent=Agent(role="Agent 3", goal="Goal 3", backstory="Backstory 3"),
             ),
         ]
-        return CrewPlanner(tasks)
+        return CrewPlanner(tasks, None)
+
+    @pytest.fixture
+    def crew_planner_different_llm(self):
+        tasks = [
+            Task(
+                description="Task 1",
+                expected_output="Output 1",
+                agent=Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1"),
+            )
+        ]
+        planning_agent_llm = ChatOpenAI(model="gpt-3.5-turbo")
+        return CrewPlanner(tasks, planning_agent_llm)
 
     def test_handle_crew_planning(self, crew_planner):
         with patch.object(Task, "execute_sync") as execute:
@@ -40,7 +53,7 @@ class TestCrewPlanner:
                 ),
             )
             result = crew_planner._handle_crew_planning()
-
+            assert crew_planner.planning_agent_llm.model_name == "gpt-4o-mini"
             assert isinstance(result, PlannerTaskPydanticOutput)
             assert len(result.list_of_plans_per_task) == len(crew_planner.tasks)
             execute.assert_called_once()
@@ -72,3 +85,22 @@ class TestCrewPlanner:
         assert isinstance(tasks_summary, str)
         assert tasks_summary.startswith("\n                Task Number 1 - Task 1")
         assert tasks_summary.endswith('"agent_tools": []\n                ')
+
+    def test_handle_crew_planning_different_llm(self, crew_planner_different_llm):
+        with patch.object(Task, "execute_sync") as execute:
+            execute.return_value = TaskOutput(
+                description="Description",
+                agent="agent",
+                pydantic=PlannerTaskPydanticOutput(list_of_plans_per_task=["Plan 1"]),
+            )
+            result = crew_planner_different_llm._handle_crew_planning()
+
+            assert (
+                crew_planner_different_llm.planning_agent_llm.model_name
+                == "gpt-3.5-turbo"
+            )
+            assert isinstance(result, PlannerTaskPydanticOutput)
+            assert len(result.list_of_plans_per_task) == len(
+                crew_planner_different_llm.tasks
+            )
+            execute.assert_called_once()