feat: add validation for poetry data

* support unsafe code execution. add in docker install and running checks.

* Update return type

README.md

@@ -351,7 +351,7 @@ pre-commit install
 ### Running Tests
 
 ```bash
-uvx pytest
+uv run pytest .
 ```
 
 ### Running static type checks

docs/concepts/agents.mdx

@@ -31,16 +31,17 @@ Think of an agent as a member of a team, with specific skills and a particular j
 | **Max RPM** *(optional)*   | `max_rpm`  | Max RPM is the maximum number of requests per minute the agent can perform to avoid rate limits. It's optional and can be left unspecified, with a default value of `None`.                                                                               |
 | **Max Execution Time** *(optional)*   | `max_execution_time`  | Max Execution Time is the maximum execution time for an agent to execute a task. It's optional and can be left unspecified, with a default value of `None`, meaning no max execution time.                                                                     |
 | **Verbose** *(optional)*   | `verbose`  | Setting this to `True` configures the internal logger to provide detailed execution logs, aiding in debugging and monitoring. Default is `False`.                                                                                              |
-| **Allow Delegation** *(optional)* | `allow_delegation`  | Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent. Default is `False`.
+| **Allow Delegation** *(optional)* | `allow_delegation`  | Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent. Default is `False`.                                                                                                      |
 | **Step Callback** *(optional)* | `step_callback`  | A function that is called after each step of the agent. This can be used to log the agent's actions or to perform other operations. It will overwrite the crew `step_callback`.                                                               |
 | **Cache** *(optional)*     | `cache`  | Indicates if the agent should use a cache for tool usage. Default is `True`.                                                                                                                                                                  |
 | **System Template** *(optional)*     | `system_template`  | Specifies the system format for the agent. Default is `None`.                                                                                                                                                                  |
 | **Prompt Template** *(optional)*     | `prompt_template`  | Specifies the prompt format for the agent. Default is `None`.                                                                                                                                                                  |
 | **Response Template** *(optional)*     | `response_template`  | Specifies the response format for the agent. Default is `None`.                                                                                                                                                                  |
 | **Allow Code Execution** *(optional)*     | `allow_code_execution`  | Enable code execution for the agent. Default is `False`.                                                                                                                                                                  |
-| **Max Retry Limit** *(optional)*     | `max_retry_limit`  | Maximum number of retries for an agent to execute a task when an error occurs. Default is `2`.
+| **Max Retry Limit** *(optional)*     | `max_retry_limit`  | Maximum number of retries for an agent to execute a task when an error occurs. Default is `2`.                                                                                                                                                                  |
 | **Use System Prompt** *(optional)*     | `use_system_prompt`  | Adds the ability to not use system prompt (to support o1 models). Default is `True`.                                                                                                                                                                  |
 | **Respect Context Window** *(optional)*     | `respect_context_window`  | Summary strategy to avoid overflowing the context window. Default is `True`.                                                                                                                                                                  |
+| **Code Execution Mode** *(optional)* | `code_execution_mode` | Determines the mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution on the host machine). Default is `safe`.                                                                                                          |
 
 ## Creating an agent
 
@@ -83,6 +84,7 @@ agent = Agent(
   max_retry_limit=2,  # Optional
   use_system_prompt=True,  # Optional
   respect_context_window=True,  # Optional
+  code_execution_mode='safe',  # Optional, defaults to 'safe'
 )
 ```
 
@@ -156,4 +158,4 @@ crew = my_crew.kickoff(inputs={"input": "Mark Twain"})
 ## Conclusion
 
 Agents are the building blocks of the CrewAI framework. By understanding how to define and interact with agents, 
-you can create sophisticated AI systems that leverage the power of collaborative intelligence.
+you can create sophisticated AI systems that leverage the power of collaborative intelligence. The `code_execution_mode` attribute provides flexibility in how agents execute code, allowing for both secure and direct execution options.

docs/concepts/memory.mdx

@@ -118,7 +118,7 @@ Alternatively, you can directly pass the OpenAIEmbeddingFunction to the embedder
 Example:
 ```python Code
 from crewai import Crew, Agent, Task, Process
-from chromadb.utils.embedding_functions.openai_embedding_function import OpenAIEmbeddingFunction
+from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
 
 my_crew = Crew(
     agents=[...],
@@ -174,6 +174,7 @@ my_crew = Crew(
 ### Using Azure OpenAI embeddings
 
 ```python Code
+from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
 from crewai import Crew, Agent, Task, Process
 
 my_crew = Crew(
@@ -182,7 +183,7 @@ my_crew = Crew(
     process=Process.sequential,
     memory=True,
     verbose=True,
-    embedder=embedding_functions.OpenAIEmbeddingFunction(
+    embedder=OpenAIEmbeddingFunction(
         api_key="YOUR_API_KEY",
         api_base="YOUR_API_BASE_PATH",
         api_type="azure",
@@ -195,6 +196,7 @@ my_crew = Crew(
 ### Using Vertex AI embeddings
 
 ```python Code
+from chromadb.utils.embedding_functions import GoogleVertexEmbeddingFunction
 from crewai import Crew, Agent, Task, Process
 
 my_crew = Crew(
@@ -203,7 +205,7 @@ my_crew = Crew(
     process=Process.sequential,
     memory=True,
     verbose=True,
-    embedder=embedding_functions.GoogleVertexEmbeddingFunction(
+    embedder=GoogleVertexEmbeddingFunction(
         project_id="YOUR_PROJECT_ID",
         region="YOUR_REGION",
         api_key="YOUR_API_KEY",

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.75.1"
+version = "0.76.2"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<=3.13"
@@ -28,6 +28,7 @@ dependencies = [
     "uv>=0.4.25",
     "tomli-w>=1.1.0",
     "chromadb>=0.4.24",
+    "tomli>=2.0.2",
 ]
 
 [project.urls]

src/crewai/__init__.py

@@ -14,5 +14,5 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.75.1"
+__version__ = "0.76.2"
 __all__ = ["Agent", "Crew", "Process", "Task", "Pipeline", "Router", "LLM", "Flow"]

src/crewai/agent.py

@@ -1,6 +1,8 @@
 import os
+import shutil
+import subprocess
 from inspect import signature
-from typing import Any, List, Optional, Union
+from typing import Any, List, Literal, Optional, Union
 
 from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 
@@ -112,6 +114,10 @@ class Agent(BaseAgent):
         default=2,
         description="Maximum number of retries for an agent to execute a task when an error occurs.",
     )
+    code_execution_mode: Literal["safe", "unsafe"] = Field(
+        default="safe",
+        description="Mode for code execution: 'safe' (using Docker) or 'unsafe' (direct execution).",
+    )
 
     @model_validator(mode="after")
     def post_init_setup(self):
@@ -173,6 +179,9 @@ class Agent(BaseAgent):
         if not self.agent_executor:
             self._setup_agent_executor()
 
+        if self.allow_code_execution:
+            self._validate_docker_installation()
+
         return self
 
     def _setup_agent_executor(self):
@@ -308,7 +317,9 @@ class Agent(BaseAgent):
         try:
             from crewai_tools import CodeInterpreterTool
 
-            return [CodeInterpreterTool()]
+            # Set the unsafe_mode based on the code_execution_mode attribute
+            unsafe_mode = self.code_execution_mode == "unsafe"
+            return [CodeInterpreterTool(unsafe_mode=unsafe_mode)]
         except ModuleNotFoundError:
             self._logger.log(
                 "info", "Coding tools not available. Install crewai_tools. "
@@ -408,6 +419,25 @@ class Agent(BaseAgent):
 
         return "\n".join(tool_strings)
 
+    def _validate_docker_installation(self) -> None:
+        """Check if Docker is installed and running."""
+        if not shutil.which("docker"):
+            raise RuntimeError(
+                f"Docker is not installed. Please install Docker to use code execution with agent: {self.role}"
+            )
+
+        try:
+            subprocess.run(
+                ["docker", "info"],
+                check=True,
+                stdout=subprocess.PIPE,
+                stderr=subprocess.PIPE,
+            )
+        except subprocess.CalledProcessError:
+            raise RuntimeError(
+                f"Docker is not running. Please start Docker to use code execution with agent: {self.role}"
+            )
+
     @staticmethod
     def __tools_names(tools) -> str:
         return ", ".join([t.name for t in tools])

src/crewai/cli/cli.py

@@ -33,10 +33,11 @@ def crewai():
 @click.argument("type", type=click.Choice(["crew", "pipeline", "flow"]))
 @click.argument("name")
 @click.option("--provider", type=str, help="The provider to use for the crew")
-def create(type, name, provider):
+@click.option("--skip_provider", is_flag=True, help="Skip provider validation")
+def create(type, name, provider, skip_provider=False):
     """Create a new crew, pipeline, or flow."""
     if type == "crew":
-        create_crew(name, provider)
+        create_crew(name, provider, skip_provider)
     elif type == "pipeline":
         create_pipeline(name)
     elif type == "flow":

src/crewai/cli/create_crew.py

@@ -81,77 +81,84 @@ def copy_template_files(folder_path, name, class_name, parent_folder):
             copy_template(src_file, dst_file, name, class_name, folder_path.name)
 
 
-def create_crew(name, parent_folder=None):
+def create_crew(name, provider=None, skip_provider=False, parent_folder=None):
     folder_path, folder_name, class_name = create_folder_structure(name, parent_folder)
     env_vars = load_env_vars(folder_path)
+    if not skip_provider:
+        if not provider:
+            provider_models = get_provider_data()
+            if not provider_models:
+                return
 
-    existing_provider = None
+        existing_provider = None
-    for provider, env_keys in ENV_VARS.items():
+        for provider, env_keys in ENV_VARS.items():
-        if any(key in env_vars for key in env_keys):
+            if any(key in env_vars for key in env_keys):
-            existing_provider = provider
+                existing_provider = provider
-            break
+                break
 
-    if existing_provider:
+        if existing_provider:
-        if not click.confirm(
+            if not click.confirm(
-            f"Found existing environment variable configuration for {existing_provider.capitalize()}. Do you want to override it?"
+                f"Found existing environment variable configuration for {existing_provider.capitalize()}. Do you want to override it?"
-        ):
+            ):
-            click.secho("Keeping existing provider configuration.", fg="yellow")
+                click.secho("Keeping existing provider configuration.", fg="yellow")
+                return
+
+        provider_models = get_provider_data()
+        if not provider_models:
             return
 
-    provider_models = get_provider_data()
+        while True:
-    if not provider_models:
+            selected_provider = select_provider(provider_models)
-        return
+            if selected_provider is None:  # User typed 'q'
+                click.secho("Exiting...", fg="yellow")
+                sys.exit(0)
+            if selected_provider:  # Valid selection
+                break
+            click.secho(
+                "No provider selected. Please try again or press 'q' to exit.", fg="red"
+            )
 
-    while True:
+        while True:
-        selected_provider = select_provider(provider_models)
+            selected_model = select_model(selected_provider, provider_models)
-        if selected_provider is None:  # User typed 'q'
+            if selected_model is None:  # User typed 'q'
-            click.secho("Exiting...", fg="yellow")
+                click.secho("Exiting...", fg="yellow")
-            sys.exit(0)
+                sys.exit(0)
-        if selected_provider:  # Valid selection
+            if selected_model:  # Valid selection
-            break
+                break
-        click.secho(
+            click.secho(
-            "No provider selected. Please try again or press 'q' to exit.", fg="red"
+                "No model selected. Please try again or press 'q' to exit.", fg="red"
-        )
+            )
 
-    while True:
+        if selected_provider in PROVIDERS:
-        selected_model = select_model(selected_provider, provider_models)
+            api_key_var = ENV_VARS[selected_provider][0]
-        if selected_model is None:  # User typed 'q'
+        else:
-            click.secho("Exiting...", fg="yellow")
+            api_key_var = click.prompt(
-            sys.exit(0)
+                f"Enter the environment variable name for your {selected_provider.capitalize()} API key",
-        if selected_model:  # Valid selection
+                type=str,
-            break
+                default="",
-        click.secho(
+            )
-            "No model selected. Please try again or press 'q' to exit.", fg="red"
-        )
 
-    if selected_provider in PROVIDERS:
-        api_key_var = ENV_VARS[selected_provider][0]
-    else:
-        api_key_var = click.prompt(
-            f"Enter the environment variable name for your {selected_provider.capitalize()} API key",
-            type=str,
-            default="",
-        )
-
-    api_key_value = ""
-    click.echo(
-        f"Enter your {selected_provider.capitalize()} API key (press Enter to skip): ",
-        nl=False,
-    )
-    try:
-        api_key_value = input()
-    except (KeyboardInterrupt, EOFError):
         api_key_value = ""
+        click.echo(
+            f"Enter your {selected_provider.capitalize()} API key (press Enter to skip): ",
+            nl=False,
+        )
+        try:
+            api_key_value = input()
+        except (KeyboardInterrupt, EOFError):
+            api_key_value = ""
 
-    if api_key_value.strip():
+        if api_key_value.strip():
-        env_vars = {api_key_var: api_key_value}
+            env_vars = {api_key_var: api_key_value}
-        write_env_file(folder_path, env_vars)
+            write_env_file(folder_path, env_vars)
-        click.secho("API key saved to .env file", fg="green")
+            click.secho("API key saved to .env file", fg="green")
-    else:
+        else:
-        click.secho("No API key provided. Skipping .env file creation.", fg="yellow")
+            click.secho(
+                "No API key provided. Skipping .env file creation.", fg="yellow"
+            )
 
-    env_vars["MODEL"] = selected_model
+        env_vars["MODEL"] = selected_model
-    click.secho(f"Selected model: {selected_model}", fg="green")
+        click.secho(f"Selected model: {selected_model}", fg="green")
 
     package_dir = Path(__file__).parent
     templates_dir = package_dir / "templates" / "crew"

src/crewai/cli/plot_flow.py

@@ -7,7 +7,7 @@ def plot_flow() -> None:
     """
     Plot the flow by running a command in the UV environment.
     """
-    command = ["uv", "run", "plot_flow"]
+    command = ["uv", "run", "plot"]
 
     try:
         result = subprocess.run(command, capture_output=False, text=True, check=True)

src/crewai/cli/run_crew.py

@@ -1,10 +1,9 @@
 import subprocess
 
 import click
-import tomllib
 from packaging import version
 
-from crewai.cli.utils import get_crewai_version
+from crewai.cli.utils import get_crewai_version, read_toml
 
 
 def run_crew() -> None:
@@ -15,10 +14,9 @@ def run_crew() -> None:
     crewai_version = get_crewai_version()
     min_required_version = "0.71.0"
 
-    with open("pyproject.toml", "rb") as f:
+    pyproject_data = read_toml()
-        data = tomllib.load(f)
 
-    if data.get("tool", {}).get("poetry") and (
+    if pyproject_data.get("tool", {}).get("poetry") and (
         version.parse(crewai_version) < version.parse(min_required_version)
     ):
         click.secho(
@@ -35,10 +33,7 @@ def run_crew() -> None:
         click.echo(f"An error occurred while running the crew: {e}", err=True)
         click.echo(e.output, err=True, nl=True)
 
-        with open("pyproject.toml", "rb") as f:
+        if pyproject_data.get("tool", {}).get("poetry"):
-            data = tomllib.load(f)
-
-        if data.get("tool", {}).get("poetry"):
             click.secho(
                 "It's possible that you are using an old version of crewAI that uses poetry, please run `crewai update` to update your pyproject.toml to use uv.",
                 fg="yellow",

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.75.1,<1.0.0"
+    "crewai[tools]>=0.76.2,<1.0.0"
 ]
 
 [project.scripts]

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.75.1,<1.0.0",
+    "crewai[tools]>=0.76.2,<1.0.0",
 ]
 
 [project.scripts]

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

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = ">=0.75.1,<1.0.0" }
+crewai = { extras = ["tools"], version = ">=0.76.2,<1.0.0" }
 asyncio = "*"
 
 [tool.poetry.scripts]

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

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = ["Your Name <you@example.com>"]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.75.1,<1.0.0"
+    "crewai[tools]>=0.76.2,<1.0.0"
 ]
 
 [project.scripts]

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

@@ -5,6 +5,6 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.75.1"
+    "crewai[tools]>=0.76.2"
 ]
 

src/crewai/cli/update_crew.py

@@ -2,7 +2,8 @@ import os
 import shutil
 
 import tomli_w
-import tomllib
+
+from crewai.cli.utils import read_toml
 
 
 def update_crew() -> None:
@@ -18,10 +19,9 @@ def migrate_pyproject(input_file, output_file):
     And it will be used to migrate the pyproject.toml to the new format when uv is used.
     When the time comes that uv supports the new format, this function will be deprecated.
     """
-
+    poetry_data = {}
     # Read the input pyproject.toml
-    with open(input_file, "rb") as f:
+    pyproject_data = read_toml()
-        pyproject = tomllib.load(f)
 
     # Initialize the new project structure
     new_pyproject = {
@@ -30,30 +30,30 @@ def migrate_pyproject(input_file, output_file):
     }
 
     # Migrate project metadata
-    if "tool" in pyproject and "poetry" in pyproject["tool"]:
+    if "tool" in pyproject_data and "poetry" in pyproject_data["tool"]:
-        poetry = pyproject["tool"]["poetry"]
+        poetry_data = pyproject_data["tool"]["poetry"]
-        new_pyproject["project"]["name"] = poetry.get("name")
+        new_pyproject["project"]["name"] = poetry_data.get("name")
-        new_pyproject["project"]["version"] = poetry.get("version")
+        new_pyproject["project"]["version"] = poetry_data.get("version")
-        new_pyproject["project"]["description"] = poetry.get("description")
+        new_pyproject["project"]["description"] = poetry_data.get("description")
         new_pyproject["project"]["authors"] = [
             {
                 "name": author.split("<")[0].strip(),
                 "email": author.split("<")[1].strip(">").strip(),
             }
-            for author in poetry.get("authors", [])
+            for author in poetry_data.get("authors", [])
         ]
-        new_pyproject["project"]["requires-python"] = poetry.get("python")
+        new_pyproject["project"]["requires-python"] = poetry_data.get("python")
     else:
         # If it's already in the new format, just copy the project section
-        new_pyproject["project"] = pyproject.get("project", {})
+        new_pyproject["project"] = pyproject_data.get("project", {})
 
     # Migrate or copy dependencies
     if "dependencies" in new_pyproject["project"]:
         # If dependencies are already in the new format, keep them as is
         pass
-    elif "dependencies" in poetry:
+    elif poetry_data and "dependencies" in poetry_data:
         new_pyproject["project"]["dependencies"] = []
-        for dep, version in poetry["dependencies"].items():
+        for dep, version in poetry_data["dependencies"].items():
             if isinstance(version, dict):  # Handle extras
                 extras = ",".join(version.get("extras", []))
                 new_dep = f"{dep}[{extras}]"
@@ -67,10 +67,10 @@ def migrate_pyproject(input_file, output_file):
             new_pyproject["project"]["dependencies"].append(new_dep)
 
     # Migrate or copy scripts
-    if "scripts" in poetry:
+    if poetry_data and "scripts" in poetry_data:
-        new_pyproject["project"]["scripts"] = poetry["scripts"]
+        new_pyproject["project"]["scripts"] = poetry_data["scripts"]
-    elif "scripts" in pyproject.get("project", {}):
+    elif pyproject_data.get("project", {}) and "scripts" in pyproject_data["project"]:
-        new_pyproject["project"]["scripts"] = pyproject["project"]["scripts"]
+        new_pyproject["project"]["scripts"] = pyproject_data["project"]["scripts"]
     else:
         new_pyproject["project"]["scripts"] = {}
 
@@ -87,8 +87,8 @@ def migrate_pyproject(input_file, output_file):
         new_pyproject["project"]["scripts"]["run_crew"] = f"{module_name}.main:run"
 
     # Migrate optional dependencies
-    if "extras" in poetry:
+    if poetry_data and "extras" in poetry_data:
-        new_pyproject["project"]["optional-dependencies"] = poetry["extras"]
+        new_pyproject["project"]["optional-dependencies"] = poetry_data["extras"]
 
     # Backup the old pyproject.toml
     backup_file = "pyproject-old.toml"

src/crewai/cli/utils.py

@@ -6,6 +6,7 @@ from functools import reduce
 from typing import Any, Dict, List
 
 import click
+import tomli
 from rich.console import Console
 
 from crewai.cli.authentication.utils import TokenManager
@@ -54,6 +55,13 @@ def simple_toml_parser(content):
     return result
 
 
+def read_toml(file_path: str = "pyproject.toml"):
+    """Read the content of a TOML file and return it as a dictionary."""
+    with open(file_path, "rb") as f:
+        toml_dict = tomli.load(f)
+    return toml_dict
+
+
 def parse_toml(content):
     if sys.version_info >= (3, 11):
         return tomllib.loads(content)