Merge branch 'main' into bugfix/plot_cli

* 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/cli.mdx

@@ -6,7 +6,7 @@ icon: terminal
 
 # CrewAI CLI Documentation
 
-The CrewAI CLI provides a set of commands to interact with CrewAI, allowing you to create, train, run, and manage crews and pipelines.
+The CrewAI CLI provides a set of commands to interact with CrewAI, allowing you to create, train, run, and manage crews & flows.
 
 ## Installation
 
@@ -146,3 +146,34 @@ crewai run
 Make sure to run these commands from the directory where your CrewAI project is set up. 
 Some commands may require additional configuration or setup within your project structure.
 </Note>
+
+
+### 9. API Keys
+
+When running ```crewai create crew``` command, the CLI will first show you the top 5 most common LLM providers and ask you to select one.
+
+Once you've selected an LLM provider, you will be prompted for API keys.
+
+#### Initial API key providers
+
+The CLI will initially prompt for API keys for the following services:
+
+* OpenAI
+* Groq
+* Anthropic
+* Google Gemini
+
+When you select a provider, the CLI will prompt you to enter your API key.
+
+#### Other Options
+
+If you select option 6, you will be able to select from a list of LiteLLM supported providers.
+
+When you select a provider, the CLI will prompt you to enter the Key name and the API key.
+
+See the following link for each provider's key name:
+
+* [LiteLLM Providers](https://docs.litellm.ai/docs/providers)
+
+
+

docs/concepts/flows.mdx

@@ -23,9 +23,9 @@ Flows allow you to create structured, event-driven workflows. They provide a sea
 Let's create a simple Flow where you will use OpenAI to generate a random city in one task and then use that city to generate a fun fact in another task.
 
 ```python Code
-import asyncio
 
 from crewai.flow.flow import Flow, listen, start
+from dotenv import load_dotenv
 from litellm import completion
 
 
@@ -67,19 +67,19 @@ class ExampleFlow(Flow):
         return fun_fact
 
 
-async def main():
+
 flow = ExampleFlow()
-    result = await flow.kickoff()
+result = flow.kickoff()
 
 print(f"Generated fun fact: {result}")
-
-asyncio.run(main())
 ```
 
 In the above example, we have created a simple Flow that generates a random city using OpenAI and then generates a fun fact about that city. The Flow consists of two tasks: `generate_city` and `generate_fun_fact`. The `generate_city` task is the starting point of the Flow, and the `generate_fun_fact` task listens for the output of the `generate_city` task.
 
 When you run the Flow, it will generate a random city and then generate a fun fact about that city. The output will be printed to the console.
 
+**Note:** Ensure you have set up your `.env` file to store your `OPENAI_API_KEY`. This key is necessary for authenticating requests to the OpenAI API.
+
 ### @start()
 
 The `@start()` decorator is used to mark a method as the starting point of a Flow. When a Flow is started, all the methods decorated with `@start()` are executed in parallel. You can have multiple start methods in a Flow, and they will all be executed when the Flow is started.
@@ -119,7 +119,6 @@ Here's how you can access the final output:
 
 <CodeGroup>
 ```python Code
-import asyncio
 from crewai.flow.flow import Flow, listen, start
 
 class OutputExampleFlow(Flow):
@@ -131,26 +130,24 @@ class OutputExampleFlow(Flow):
     def second_method(self, first_output):
         return f"Second method received: {first_output}"
 
-async def main():
+
 flow = OutputExampleFlow()
-    final_output = await flow.kickoff()
+final_output = flow.kickoff()
+
 print("---- Final Output ----")
 print(final_output)
-
-asyncio.run(main())
-```
+````
 
 ``` text Output
 ---- Final Output ----
 Second method received: Output from first_method
-```
+````
 
 </CodeGroup>
 
 In this example, the `second_method` is the last method to complete, so its output will be the final output of the Flow.
 The `kickoff()` method will return the final output, which is then printed to the console.
 
-
 #### Accessing and Updating State
 
 In addition to retrieving the final output, you can also access and update the state within your Flow. The state can be used to store and share data between different methods in the Flow. After the Flow has run, you can access the state to retrieve any information that was added or updated during the execution.
@@ -160,7 +157,6 @@ Here's an example of how to update and access the state:
 <CodeGroup>
 
 ```python Code
-import asyncio
 from crewai.flow.flow import Flow, listen, start
 from pydantic import BaseModel
 
@@ -181,14 +177,11 @@ class StateExampleFlow(Flow[ExampleState]):
         self.state.counter += 1
         return self.state.message
 
-async def main():
 flow = StateExampleFlow()
-    final_output = await flow.kickoff()
+final_output = flow.kickoff()
 print(f"Final Output: {final_output}")
 print("Final State:")
 print(flow.state)
-
-asyncio.run(main())
 ```
 
 ```text Output
@@ -196,6 +189,7 @@ Final Output: Hello from first_method - updated by second_method
 Final State:
 counter=2 message='Hello from first_method - updated by second_method'
 ```
+
 </CodeGroup>
 
 In this example, the state is updated by both `first_method` and `second_method`.
@@ -215,8 +209,6 @@ In unstructured state management, all state is stored in the `state` attribute o
 This approach offers flexibility, enabling developers to add or modify state attributes on the fly without defining a strict schema.
 
 ```python Code
-import asyncio
-
 from crewai.flow.flow import Flow, listen, start
 
 class UntructuredExampleFlow(Flow):
@@ -239,12 +231,8 @@ class UntructuredExampleFlow(Flow):
         print(f"State after third_method: {self.state}")
 
 
-async def main():
 flow = UntructuredExampleFlow()
-    await flow.kickoff()
-
-
-asyncio.run(main())
+flow.kickoff()
 ```
 
 **Key Points:**
@@ -258,8 +246,6 @@ Structured state management leverages predefined schemas to ensure consistency a
 By using models like Pydantic's `BaseModel`, developers can define the exact shape of the state, enabling better validation and auto-completion in development environments.
 
 ```python Code
-import asyncio
-
 from crewai.flow.flow import Flow, listen, start
 from pydantic import BaseModel
 
@@ -288,12 +274,8 @@ class StructuredExampleFlow(Flow[ExampleState]):
         print(f"State after third_method: {self.state}")
 
 
-async def main():
 flow = StructuredExampleFlow()
-    await flow.kickoff()
-
-
-asyncio.run(main())
+flow.kickoff()
 ```
 
 **Key Points:**
@@ -326,7 +308,6 @@ The `or_` function in Flows allows you to listen to multiple methods and trigger
 <CodeGroup>
 
 ```python Code
-import asyncio
 from crewai.flow.flow import Flow, listen, or_, start
 
 class OrExampleFlow(Flow):
@@ -344,12 +325,9 @@ class OrExampleFlow(Flow):
         print(f"Logger: {result}")
 
 
-async def main():
+
 flow = OrExampleFlow()
-    await flow.kickoff()
-
-
-asyncio.run(main())
+flow.kickoff()
 ```
 
 ```text Output
@@ -369,7 +347,6 @@ The `and_` function in Flows allows you to listen to multiple methods and trigge
 <CodeGroup>
 
 ```python Code
-import asyncio
 from crewai.flow.flow import Flow, and_, listen, start
 
 class AndExampleFlow(Flow):
@@ -387,13 +364,8 @@ class AndExampleFlow(Flow):
         print("---- Logger ----")
         print(self.state)
 
-
-async def main():
 flow = AndExampleFlow()
-    await flow.kickoff()
-
-
-asyncio.run(main())
+flow.kickoff()
 ```
 
 ```text Output
@@ -414,7 +386,6 @@ You can specify different routes based on the output of the method, allowing you
 <CodeGroup>
 
 ```python Code
-import asyncio
 import random
 from crewai.flow.flow import Flow, listen, router, start
 from pydantic import BaseModel
@@ -446,12 +417,8 @@ class RouterFlow(Flow[ExampleState]):
         print("Fourth method running")
 
 
-async def main():
 flow = RouterFlow()
-    await flow.kickoff()
-
-
-asyncio.run(main())
+flow.kickoff()
 ```
 
 ```text Output
@@ -486,7 +453,7 @@ This command will generate a new CrewAI project with the necessary folder struct
 After running the `crewai create flow name_of_flow` command, you will see a folder structure similar to the following:
 
 | Directory/File         | Description                                                        |
-|:---------------------------------|:------------------------------------------------------------------|
+| :--------------------- | :----------------------------------------------------------------- |
 | `name_of_flow/`        | Root directory for the flow.                                       |
 | ├── `crews/`           | Contains directories for specific crews.                           |
 | │ └── `poem_crew/`     | Directory for the "poem_crew" with its configurations and scripts. |
@@ -501,7 +468,6 @@ After running the `crewai create flow name_of_flow` command, you will see a fold
 | ├── `pyproject.toml`   | Configuration file for project dependencies and settings.          |
 | └── `.gitignore`       | Specifies files and directories to ignore in version control.      |
 
-
 ### Building Your Crews
 
 In the `crews` folder, you can define multiple crews. Each crew will have its own folder containing configuration files and the crew definition file. For example, the `poem_crew` folder contains:
@@ -520,7 +486,6 @@ Here's an example of how you can connect the `poem_crew` in the `main.py` file:
 
 ```python Code
 #!/usr/bin/env python
-import asyncio
 from random import randint
 
 from pydantic import BaseModel
@@ -536,14 +501,12 @@ class PoemFlow(Flow[PoemState]):
     @start()
     def generate_sentence_count(self):
         print("Generating sentence count")
-        # Generate a number between 1 and 5
         self.state.sentence_count = randint(1, 5)
 
     @listen(generate_sentence_count)
     def generate_poem(self):
         print("Generating poem")
-        poem_crew = PoemCrew().crew()
-        result = poem_crew.kickoff(inputs={"sentence_count": self.state.sentence_count})
+        result = PoemCrew().crew().kickoff(inputs={"sentence_count": self.state.sentence_count})
 
         print("Poem generated", result.raw)
         self.state.poem = result.raw
@@ -554,18 +517,17 @@ class PoemFlow(Flow[PoemState]):
         with open("poem.txt", "w") as f:
             f.write(self.state.poem)
 
-async def run():
-    """
-    Run the flow.
-    """
+def kickoff():
     poem_flow = PoemFlow()
-    await poem_flow.kickoff()
+    poem_flow.kickoff()
 
-def main():
-    asyncio.run(run())
+
+def plot():
+    poem_flow = PoemFlow()
+    poem_flow.plot()
 
 if __name__ == "__main__":
-    main()
+    kickoff()
 ```
 
 In this example, the `PoemFlow` class defines a flow that generates a sentence count, uses the `PoemCrew` to generate a poem, and then saves the poem to a file. The flow is kicked off by calling the `kickoff()` method.
@@ -587,13 +549,13 @@ source .venv/bin/activate
 After activating the virtual environment, you can run the flow by executing one of the following commands:
 
 ```bash
-crewai flow run
+crewai flow kickoff
 ```
 
 or
 
 ```bash
-uv run run_flow
+uv run kickoff
 ```
 
 The flow will execute, and you should see the output in the console.

docs/concepts/llms.mdx

@@ -62,6 +62,8 @@ os.environ["OPENAI_API_BASE"] = "https://api.your-provider.com/v1"
 2. Using LLM class attributes:
 
 ```python Code
+from crewai import LLM
+
 llm = LLM(
     model="custom-model-name",
     api_key="your-api-key",
@@ -95,9 +97,11 @@ When configuring an LLM for your agent, you have access to a wide range of param
 | **api_key**          | `str`             | Your API key for authentication.                                                                 |
 
 
-Example:
+## OpenAI Example Configuration
 
 ```python Code
+from crewai import LLM
+
 llm = LLM(
     model="gpt-4",
     temperature=0.8,
@@ -112,15 +116,31 @@ llm = LLM(
 )
 agent = Agent(llm=llm, ...)
 ```
+
+## Cerebras Example Configuration
+
+```python Code
+from crewai import LLM
+
+llm = LLM(
+    model="cerebras/llama-3.1-70b",
+    base_url="https://api.cerebras.ai/v1",
+    api_key="your-api-key-here"
+)
+agent = Agent(llm=llm, ...) 
+```
+
 ## Using Ollama (Local LLMs)
 
-crewAI supports using Ollama for running open-source models locally:
+CrewAI supports using Ollama for running open-source models locally:
 
 1. Install Ollama: [ollama.ai](https://ollama.ai/)
 2. Run a model: `ollama run llama2`
 3. Configure agent:
 
 ```python Code
+from crewai import LLM
+
 agent = Agent(
     llm=LLM(model="ollama/llama3.1", base_url="http://localhost:11434"),
     ...
@@ -132,6 +152,8 @@ agent = Agent(
 You can change the base API URL for any LLM provider by setting the `base_url` parameter:
 
 ```python Code
+from crewai import LLM
+
 llm = LLM(
     model="custom-model-name",
     base_url="https://api.your-provider.com/v1",

docs/concepts/memory.mdx

@@ -105,9 +105,48 @@ my_crew = Crew(
     process=Process.sequential,
     memory=True,
     verbose=True,
-    embedder=embedding_functions.OpenAIEmbeddingFunction(
-            api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
+    embedder={
+        "provider": "openai",
+        "config": {
+            "model": 'text-embedding-3-small'
+        }
+    }
 )
+```
+Alternatively, you can directly pass the OpenAIEmbeddingFunction to the embedder parameter.
+
+Example:
+```python Code
+from crewai import Crew, Agent, Task, Process
+from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
+
+my_crew = Crew(
+    agents=[...],
+    tasks=[...],
+    process=Process.sequential,
+    memory=True,
+    verbose=True,
+    embedder=OpenAIEmbeddingFunction(api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"),
+)
+```
+
+### Using Ollama embeddings
+
+```python Code
+from crewai import Crew, Agent, Task, Process
+
+my_crew = Crew(
+    agents=[...],
+    tasks=[...],
+    process=Process.sequential,
+    memory=True,
+    verbose=True,
+    embedder={
+        "provider": "ollama",
+        "config": {
+            "model": "mxbai-embed-large"
+        }
+    }
 )
 ```
 
@@ -122,16 +161,20 @@ my_crew = Crew(
     process=Process.sequential,
     memory=True,
     verbose=True,
-    embedder=embedding_functions.OpenAIEmbeddingFunction(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            model_name="text-embedding-ada-002"
-    )
+    embedder={
+        "provider": "google",
+        "config": {
+            "api_key": "<YOUR_API_KEY>",
+            "model_name": "<model_name>"
+        }
+    }
 )
 ```
 
 ### Using Azure OpenAI embeddings
 
 ```python Code
+from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
 from crewai import Crew, Agent, Task, Process
 
 my_crew = Crew(
@@ -140,7 +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",
@@ -153,6 +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(
@@ -161,7 +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",
@@ -181,10 +225,32 @@ my_crew = Crew(
     process=Process.sequential,
     memory=True,
     verbose=True,
-    embedder=embedding_functions.CohereEmbeddingFunction(
-        api_key=YOUR_API_KEY,
-        model_name="<model_name>"
+    embedder={
+        "provider": "cohere",
+        "config": {
+            "api_key": "YOUR_API_KEY",
+            "model_name": "<model_name>"
+        }
+    }
 )
+```
+### Using HuggingFace embeddings
+
+```python Code
+from crewai import Crew, Agent, Task, Process
+
+my_crew = Crew(
+    agents=[...],
+    tasks=[...],
+    process=Process.sequential,
+    memory=True,
+    verbose=True,
+    embedder={
+        "provider": "huggingface",
+        "config": {
+            "api_url": "<api_url>",
+        }
+    }
 )
 ```
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.74.0"
+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"
@@ -16,7 +16,7 @@ dependencies = [
     "opentelemetry-exporter-otlp-proto-http>=1.22.0",
     "instructor>=1.3.3",
     "regex>=2024.9.11",
-    "crewai-tools>=0.13.1",
+    "crewai-tools>=0.13.2",
     "click>=8.1.7",
     "python-dotenv>=1.0.0",
     "appdirs>=1.4.4",
@@ -25,7 +25,7 @@ dependencies = [
     "auth0-python>=4.7.1",
     "litellm>=1.44.22",
     "pyvis>=0.3.2",
-    "uv>=0.4.18",
+    "uv>=0.4.25",
     "tomli-w>=1.1.0",
     "chromadb>=0.4.24",
 ]
@@ -36,7 +36,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools>=0.12.1"]
+tools = ["crewai-tools>=0.13.2"]
 agentops = ["agentops>=0.3.0"]
 
 [tool.uv]
@@ -51,7 +51,7 @@ dev-dependencies = [
     "mkdocs-material-extensions>=1.3.1",
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
-    "crewai-tools>=0.12.1",
+    "crewai-tools>=0.13.2",
     "pytest>=8.0.0",
     "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",

src/crewai/__init__.py

@@ -14,5 +14,5 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.74.0"
+__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. "
@@ -394,7 +405,7 @@ class Agent(BaseAgent):
         """
         tool_strings = []
         for tool in tools:
-            args_schema = str(tool.args)
+            args_schema = str(tool.model_fields)
             if hasattr(tool, "func") and tool.func:
                 sig = signature(tool.func)
                 description = (
@@ -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/agents/crew_agent_executor.py

@@ -2,6 +2,7 @@ import json
 import re
 from typing import Any, Dict, List, Union
 
+from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
 from crewai.agents.parser import (
     FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE,
@@ -19,7 +20,6 @@ from crewai.utilities.exceptions.context_window_exceeding_exception import (
 )
 from crewai.utilities.logger import Logger
 from crewai.utilities.training_handler import CrewTrainingHandler
-from crewai.agents.agent_builder.base_agent import BaseAgent
 
 
 class CrewAgentExecutor(CrewAgentExecutorMixin):
@@ -323,9 +323,9 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             if self.crew is not None and hasattr(self.crew, "_train_iteration"):
                 train_iteration = self.crew._train_iteration
                 if agent_id in training_data and isinstance(train_iteration, int):
-                    training_data[agent_id][train_iteration]["improved_output"] = (
-                        result.output
-                    )
+                    training_data[agent_id][train_iteration][
+                        "improved_output"
+                    ] = result.output
                     training_handler.save(training_data)
                 else:
                     self._logger.log(

src/crewai/cli/cli.py

@@ -14,11 +14,11 @@ from .authentication.main import AuthenticationCommand
 from .deploy.main import DeployCommand
 from .evaluate_crew import evaluate_crew
 from .install_crew import install_crew
+from .kickoff_flow import kickoff_flow
 from .plot_flow import plot_flow
 from .replay_from_task import replay_task_command
 from .reset_memories_command import reset_memories_command
 from .run_crew import run_crew
-from .run_flow import run_flow
 from .tools.main import ToolCommand
 from .train_crew import train_crew
 from .update_crew import update_crew
@@ -32,10 +32,12 @@ def crewai():
 @crewai.command()
 @click.argument("type", type=click.Choice(["crew", "pipeline", "flow"]))
 @click.argument("name")
-def create(type, name):
+@click.option("--provider", type=str, help="The provider to use for the crew")
+@click.option("--skip_provider", is_flag=True, help="Skip provider validation")
+def create(type, name, provider, skip_provider=False):
     """Create a new crew, pipeline, or flow."""
     if type == "crew":
-        create_crew(name)
+        create_crew(name, provider, skip_provider)
     elif type == "pipeline":
         create_pipeline(name)
     elif type == "flow":
@@ -304,11 +306,11 @@ def flow():
     pass
 
 
-@flow.command(name="run")
+@flow.command(name="kickoff")
 def flow_run():
-    """Run the Flow."""
+    """Kickoff the Flow."""
     click.echo("Running the Flow")
-    run_flow()
+    kickoff_flow()
 
 
 @flow.command(name="plot")

src/crewai/cli/create_crew.py

@@ -1,8 +1,16 @@
+import sys
 from pathlib import Path
+
 import click
-from crewai.cli.utils import copy_template, load_env_vars, write_env_file
-from crewai.cli.provider import get_provider_data, select_provider, PROVIDERS
+
 from crewai.cli.constants import ENV_VARS
+from crewai.cli.provider import (
+    PROVIDERS,
+    get_provider_data,
+    select_model,
+    select_provider,
+)
+from crewai.cli.utils import copy_template, load_env_vars, write_env_file
 
 
 def create_folder_structure(name, parent_folder=None):
@@ -14,6 +22,14 @@ def create_folder_structure(name, parent_folder=None):
     else:
         folder_path = Path(folder_name)
 
+    if folder_path.exists():
+        if not click.confirm(
+            f"Folder {folder_name} already exists. Do you want to override it?"
+        ):
+            click.secho("Operation cancelled.", fg="yellow")
+            sys.exit(0)
+        click.secho(f"Overriding folder {folder_name}...", fg="green", bold=True)
+    else:
         click.secho(
             f"Creating {'crew' if parent_folder else 'folder'} {folder_name}...",
             fg="green",
@@ -27,11 +43,6 @@ def create_folder_structure(name, parent_folder=None):
             (folder_path / "src" / folder_name).mkdir(parents=True)
             (folder_path / "src" / folder_name / "tools").mkdir(parents=True)
             (folder_path / "src" / folder_name / "config").mkdir(parents=True)
-    else:
-        click.secho(
-            f"\tFolder {folder_name} already exists.",
-            fg="yellow",
-        )
 
     return folder_path, folder_name, class_name
 
@@ -70,37 +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
+        for provider, env_keys in ENV_VARS.items():
+            if any(key in env_vars for key in env_keys):
+                existing_provider = provider
+                break
+
+        if existing_provider:
+            if not click.confirm(
+                f"Found existing environment variable configuration for {existing_provider.capitalize()}. Do you want to override it?"
+            ):
+                click.secho("Keeping existing provider configuration.", fg="yellow")
+                return
 
         provider_models = get_provider_data()
         if not provider_models:
             return
 
+        while True:
             selected_provider = select_provider(provider_models)
-    if not selected_provider:
-        return
-    provider = selected_provider
-
-    # selected_model = select_model(provider, provider_models)
-    # if not selected_model:
-    #     return
-    # model = selected_model
-
-    if provider in PROVIDERS:
-        api_key_var = ENV_VARS[provider][0]
-    else:
-        api_key_var = click.prompt(
-            f"Enter the environment variable name for your {provider.capitalize()} API key",
-            type=str,
+            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"
             )
 
-    env_vars = {api_key_var: "YOUR_API_KEY_HERE"}
-    write_env_file(folder_path, env_vars)
+        while True:
+            selected_model = select_model(selected_provider, provider_models)
+            if selected_model is None:  # User typed 'q'
+                click.secho("Exiting...", fg="yellow")
+                sys.exit(0)
+            if selected_model:  # Valid selection
+                break
+            click.secho(
+                "No model selected. Please try again or press 'q' to exit.", fg="red"
+            )
 
-    # env_vars['MODEL'] = model
-    # click.secho(f"Selected model: {model}", fg="green")
+        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 = ""
+
+        if api_key_value.strip():
+            env_vars = {api_key_var: api_key_value}
+            write_env_file(folder_path, env_vars)
+            click.secho("API key saved to .env file", fg="green")
+        else:
+            click.secho(
+                "No API key provided. Skipping .env file creation.", fg="yellow"
+            )
+
+        env_vars["MODEL"] = selected_model
+        click.secho(f"Selected model: {selected_model}", fg="green")
 
     package_dir = Path(__file__).parent
     templates_dir = package_dir / "templates" / "crew"

src/crewai/cli/kickoff_flow.py

@@ -3,11 +3,11 @@ import subprocess
 import click
 
 
-def run_flow() -> None:
+def kickoff_flow() -> None:
     """
-    Run the flow by running a command in the UV environment.
+    Kickoff the flow by running a command in the UV environment.
     """
-    command = ["uv", "run", "run_flow"]
+    command = ["uv", "run", "kickoff"]
 
     try:
         result = subprocess.run(command, capture_output=False, text=True, check=True)

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/provider.py

@@ -1,10 +1,13 @@
 import json
 import time
-import requests
 from collections import defaultdict
-import click
 from pathlib import Path
-from crewai.cli.constants import PROVIDERS, MODELS, JSON_URL
+
+import click
+import requests
+
+from crewai.cli.constants import JSON_URL, MODELS, PROVIDERS
+
 
 def select_choice(prompt_message, choices):
     """
@@ -15,20 +18,37 @@ def select_choice(prompt_message, choices):
     - choices (list): A list of options to present to the user.
 
     Returns:
-    - str: The selected choice from the list, or None if the operation is aborted or an invalid selection is made.
+    - str: The selected choice from the list, or None if the user chooses to quit.
     """
+
+    provider_models = get_provider_data()
+    if not provider_models:
+        return
     click.secho(prompt_message, fg="cyan")
     for idx, choice in enumerate(choices, start=1):
         click.secho(f"{idx}. {choice}", fg="cyan")
+    click.secho("q. Quit", fg="cyan")
+
+    while True:
+        choice = click.prompt(
+            "Enter the number of your choice or 'q' to quit", type=str
+        )
+
+        if choice.lower() == "q":
+            return None
+
         try:
-        selected_index = click.prompt("Enter the number of your choice", type=int) - 1
-    except click.exceptions.Abort:
-        click.secho("Operation aborted by the user.", fg="red")
-        return None
-    if not (0 <= selected_index < len(choices)):
-        click.secho("Invalid selection.", fg="red")
-        return None
+            selected_index = int(choice) - 1
+            if 0 <= selected_index < len(choices):
                 return choices[selected_index]
+        except ValueError:
+            pass
+
+        click.secho(
+            "Invalid selection. Please select a number between 1 and 6 or 'q' to quit.",
+            fg="red",
+        )
+
 
 def select_provider(provider_models):
     """
@@ -38,21 +58,25 @@ def select_provider(provider_models):
     - provider_models (dict): A dictionary of provider models.
 
     Returns:
-    - str: The selected provider, or None if the operation is aborted or an invalid selection is made.
+    - str: The selected provider
+    - None: If user explicitly quits
     """
     predefined_providers = [p.lower() for p in PROVIDERS]
     all_providers = sorted(set(predefined_providers + list(provider_models.keys())))
 
-    provider = select_choice("Select a provider to set up:", predefined_providers + ['other'])
-    if not provider:
+    provider = select_choice(
+        "Select a provider to set up:", predefined_providers + ["other"]
+    )
+    if provider is None:  # User typed 'q'
         return None
-    provider = provider.lower()
 
-    if provider == 'other':
+    if provider == "other":
         provider = select_choice("Select a provider from the full list:", all_providers)
-        if not provider:
+        if provider is None:  # User typed 'q'
             return None
-    return provider
+
+    return provider.lower() if provider else False
+
 
 def select_model(provider, provider_models):
     """
@@ -76,9 +100,12 @@ def select_model(provider, provider_models):
         click.secho(f"No models available for provider '{provider}'.", fg="red")
         return None
 
-    selected_model = select_choice(f"Select a model to use for {provider.capitalize()}:", available_models)
+    selected_model = select_choice(
+        f"Select a model to use for {provider.capitalize()}:", available_models
+    )
     return selected_model
 
+
 def load_provider_data(cache_file, cache_expiry):
     """
     Loads provider data from a cache file if it exists and is not expired. If the cache is expired or corrupted, it fetches the data from the web.
@@ -91,15 +118,24 @@ def load_provider_data(cache_file, cache_expiry):
     - dict or None: The loaded provider data or None if the operation fails.
     """
     current_time = time.time()
-    if cache_file.exists() and (current_time - cache_file.stat().st_mtime) < cache_expiry:
+    if (
+        cache_file.exists()
+        and (current_time - cache_file.stat().st_mtime) < cache_expiry
+    ):
         data = read_cache_file(cache_file)
         if data:
             return data
-        click.secho("Cache is corrupted. Fetching provider data from the web...", fg="yellow")
+        click.secho(
+            "Cache is corrupted. Fetching provider data from the web...", fg="yellow"
+        )
     else:
-        click.secho("Cache expired or not found. Fetching provider data from the web...", fg="cyan")
+        click.secho(
+            "Cache expired or not found. Fetching provider data from the web...",
+            fg="cyan",
+        )
     return fetch_provider_data(cache_file)
 
+
 def read_cache_file(cache_file):
     """
     Reads and returns the JSON content from a cache file. Returns None if the file contains invalid JSON.
@@ -116,6 +152,7 @@ def read_cache_file(cache_file):
     except json.JSONDecodeError:
         return None
 
+
 def fetch_provider_data(cache_file):
     """
     Fetches provider data from a specified URL and caches it to a file.
@@ -139,6 +176,7 @@ def fetch_provider_data(cache_file):
         click.secho("Error parsing provider data. Invalid JSON format.", fg="red")
     return None
 
+
 def download_data(response):
     """
     Downloads data from a given HTTP response and returns the JSON content.
@@ -149,16 +187,19 @@ def download_data(response):
     Returns:
     - dict: The JSON content of the response.
     """
-    total_size = int(response.headers.get('content-length', 0))
+    total_size = int(response.headers.get("content-length", 0))
     block_size = 8192
     data_chunks = []
-    with click.progressbar(length=total_size, label='Downloading', show_pos=True) as progress_bar:
+    with click.progressbar(
+        length=total_size, label="Downloading", show_pos=True
+    ) as progress_bar:
         for chunk in response.iter_content(block_size):
             if chunk:
                 data_chunks.append(chunk)
                 progress_bar.update(len(chunk))
-    data_content = b''.join(data_chunks)
-    return json.loads(data_content.decode('utf-8'))
+    data_content = b"".join(data_chunks)
+    return json.loads(data_content.decode("utf-8"))
+
 
 def get_provider_data():
     """
@@ -167,9 +208,9 @@ def get_provider_data():
     Returns:
     - dict or None: A dictionary of providers mapped to their models or None if the operation fails.
     """
-    cache_dir = Path.home() / '.crewai'
+    cache_dir = Path.home() / ".crewai"
     cache_dir.mkdir(exist_ok=True)
-    cache_file = cache_dir / 'provider_cache.json'
+    cache_file = cache_dir / "provider_cache.json"
     cache_expiry = 24 * 3600
 
     data = load_provider_data(cache_file, cache_expiry)
@@ -179,7 +220,7 @@ def get_provider_data():
     provider_models = defaultdict(list)
     for model_name, properties in data.items():
         provider = properties.get("litellm_provider", "").strip().lower()
-        if 'http' in provider or provider == 'other':
+        if "http" in provider or provider == "other":
             continue
         if provider:
             provider_models[provider].append(model_name)

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

@@ -3,7 +3,7 @@ import sys
 from {{folder_name}}.crew import {{crew_name}}Crew
 
 # This main file is intended to be a way for you to run your
-# crew locally, so refrain from adding necessary logic into this file.
+# crew locally, so refrain from adding unnecessary logic into this file.
 # Replace with inputs you want to test with, it will automatically
 # interpolate any tasks and agents information
 

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]>=0.74.0,<1.0.0"
+    "crewai[tools]>=0.76.2,<1.0.0"
 ]
 
 [project.scripts]

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

@@ -1,65 +1,53 @@
 #!/usr/bin/env python
-import asyncio
 from random import randint
 
 from pydantic import BaseModel
+
 from crewai.flow.flow import Flow, listen, start
+
 from .crews.poem_crew.poem_crew import PoemCrew
 
+
 class PoemState(BaseModel):
     sentence_count: int = 1
     poem: str = ""
 
+
 class PoemFlow(Flow[PoemState]):
 
     @start()
     def generate_sentence_count(self):
         print("Generating sentence count")
-        # Generate a number between 1 and 5
         self.state.sentence_count = randint(1, 5)
 
     @listen(generate_sentence_count)
     def generate_poem(self):
         print("Generating poem")
-        print(f"State before poem: {self.state}")
-        result = PoemCrew().crew().kickoff(inputs={"sentence_count": self.state.sentence_count})
+        result = (
+            PoemCrew()
+            .crew()
+            .kickoff(inputs={"sentence_count": self.state.sentence_count})
+        )
 
         print("Poem generated", result.raw)
         self.state.poem = result.raw
 
-        print(f"State after generate_poem: {self.state}")
-
     @listen(generate_poem)
     def save_poem(self):
         print("Saving poem")
-        print(f"State before save_poem: {self.state}")
         with open("poem.txt", "w") as f:
             f.write(self.state.poem)
-        print(f"State after save_poem: {self.state}")
 
-async def run_flow():
-    """
-    Run the flow.
-    """
+
+def kickoff():
     poem_flow = PoemFlow()
-    await poem_flow.kickoff()
+    poem_flow.kickoff()
 
-async def plot_flow():
-    """
-    Plot the flow.
-    """
+
+def plot():
     poem_flow = PoemFlow()
     poem_flow.plot()
 
 
-def main():
-    asyncio.run(run_flow())
-
-
-def plot():
-    asyncio.run(plot_flow())
-
-
-
 if __name__ == "__main__":
-    main()
+    kickoff()

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

@@ -5,14 +5,12 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<=3.13"
 dependencies = [
-    "crewai[tools]>=0.74.0,<1.0.0",
-    "asyncio"
+    "crewai[tools]>=0.76.2,<1.0.0",
 ]
 
 [project.scripts]
-{{folder_name}} = "{{folder_name}}.main:main"
-run_flow = "{{folder_name}}.main:main"
-plot_flow = "{{folder_name}}.main:plot"
+kickoff = "{{folder_name}}.main:kickoff"
+plot = "{{folder_name}}.main:plot"
 
 [build-system]
 requires = ["hatchling"]

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 = ">=0.74.0,<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]>=0.74.0,<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]>=0.74.0"
+    "crewai[tools]>=0.76.2"
 ]
 

src/crewai/cli/tools/main.py

@@ -28,8 +28,6 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
     A class to handle tool repository related operations for CrewAI projects.
     """
 
-    BASE_URL = "https://app.crewai.com/pypi/"
-
     def __init__(self):
         BaseCommand.__init__(self)
         PlusAPIMixin.__init__(self, telemetry=self._telemetry)
@@ -178,12 +176,14 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
     def _add_package(self, tool_details):
         tool_handle = tool_details["handle"]
         repository_handle = tool_details["repository"]["handle"]
+        repository_url = tool_details["repository"]["url"]
+        index = f"{repository_handle}={repository_url}"
 
         add_package_command = [
             "uv",
             "add",
-            "--extra-index-url",
-            self.BASE_URL + repository_handle,
+            "--index",
+            index,
             tool_handle,
         ]
         add_package_result = subprocess.run(

src/crewai/crew.py

@@ -435,15 +435,16 @@ class Crew(BaseModel):
         self, n_iterations: int, filename: str, inputs: Optional[Dict[str, Any]] = {}
     ) -> None:
         """Trains the crew for a given number of iterations."""
-        self._setup_for_training(filename)
+        train_crew = self.copy()
+        train_crew._setup_for_training(filename)
 
         for n_iteration in range(n_iterations):
-            self._train_iteration = n_iteration
-            self.kickoff(inputs=inputs)
+            train_crew._train_iteration = n_iteration
+            train_crew.kickoff(inputs=inputs)
 
         training_data = CrewTrainingHandler(TRAINING_DATA_FILE).load()
 
-        for agent in self.agents:
+        for agent in train_crew.agents:
             result = TaskEvaluator(agent).evaluate_training_data(
                 training_data=training_data, agent_id=str(agent.id)
             )
@@ -987,17 +988,19 @@ class Crew(BaseModel):
         inputs: Optional[Dict[str, Any]] = None,
     ) -> None:
         """Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
-        self._test_execution_span = self._telemetry.test_execution_span(
-            self,
+        test_crew = self.copy()
+
+        self._test_execution_span = test_crew._telemetry.test_execution_span(
+            test_crew,
             n_iterations,
             inputs,
             openai_model_name,  # type: ignore[arg-type]
         )  # type: ignore[arg-type]
-        evaluator = CrewEvaluator(self, openai_model_name)  # type: ignore[arg-type]
+        evaluator = CrewEvaluator(test_crew, openai_model_name)  # type: ignore[arg-type]
 
         for i in range(1, n_iterations + 1):
             evaluator.set_iteration(i)
-            self.kickoff(inputs=inputs)
+            test_crew.kickoff(inputs=inputs)
 
         evaluator.print_crew_evaluation_result()
 

src/crewai/flow/flow.py

@@ -190,7 +190,10 @@ class Flow(Generic[T], metaclass=FlowMeta):
         """Returns the list of all outputs from executed methods."""
         return self._method_outputs
 
-    async def kickoff(self) -> Any:
+    def kickoff(self) -> Any:
+        return asyncio.run(self.kickoff_async())
+
+    async def kickoff_async(self) -> Any:
         if not self._start_methods:
             raise ValueError("No start method defined")
 

src/crewai/memory/entity/entity_memory.py

@@ -16,7 +16,7 @@ class EntityMemory(Memory):
             if storage
             else RAGStorage(
                 type="entities",
-                allow_reset=False,
+                allow_reset=True,
                 embedder_config=embedder_config,
                 crew=crew,
             )

src/crewai/memory/storage/rag_storage.py

@@ -8,6 +8,9 @@ from typing import Any, Dict, List, Optional
 from crewai.memory.storage.base_rag_storage import BaseRAGStorage
 from crewai.utilities.paths import db_storage_path
 from chromadb.api import ClientAPI
+from chromadb.api.types import validate_embedding_function
+from chromadb import Documents, EmbeddingFunction, Embeddings
+from typing import cast
 
 
 @contextlib.contextmanager
@@ -41,16 +44,93 @@ class RAGStorage(BaseRAGStorage):
         self.agents = agents
 
         self.type = type
-        self.embedder_config = embedder_config or self._create_embedding_function()
+
         self.allow_reset = allow_reset
         self._initialize_app()
 
+    def _set_embedder_config(self):
+        import chromadb.utils.embedding_functions as embedding_functions
+
+        if self.embedder_config is None:
+            self.embedder_config = self._create_default_embedding_function()
+
+        if isinstance(self.embedder_config, dict):
+            provider = self.embedder_config.get("provider")
+            config = self.embedder_config.get("config", {})
+            model_name = config.get("model")
+            if provider == "openai":
+                self.embedder_config = embedding_functions.OpenAIEmbeddingFunction(
+                    api_key=config.get("api_key") or os.getenv("OPENAI_API_KEY"),
+                    model_name=model_name,
+                )
+            elif provider == "azure":
+                self.embedder_config = embedding_functions.OpenAIEmbeddingFunction(
+                    api_key=config.get("api_key"),
+                    api_base=config.get("api_base"),
+                    api_type=config.get("api_type", "azure"),
+                    api_version=config.get("api_version"),
+                    model_name=model_name,
+                )
+            elif provider == "ollama":
+                from openai import OpenAI
+
+                class OllamaEmbeddingFunction(EmbeddingFunction):
+                    def __call__(self, input: Documents) -> Embeddings:
+                        client = OpenAI(
+                            base_url="http://localhost:11434/v1",
+                            api_key=config.get("api_key", "ollama"),
+                        )
+                        try:
+                            response = client.embeddings.create(
+                                input=input, model=model_name
+                            )
+                            embeddings = [item.embedding for item in response.data]
+                            return cast(Embeddings, embeddings)
+                        except Exception as e:
+                            raise e
+
+                self.embedder_config = OllamaEmbeddingFunction()
+            elif provider == "vertexai":
+                self.embedder_config = (
+                    embedding_functions.GoogleVertexEmbeddingFunction(
+                        model_name=model_name,
+                        api_key=config.get("api_key"),
+                    )
+                )
+            elif provider == "google":
+                self.embedder_config = (
+                    embedding_functions.GoogleGenerativeAiEmbeddingFunction(
+                        model_name=model_name,
+                        api_key=config.get("api_key"),
+                    )
+                )
+            elif provider == "cohere":
+                self.embedder_config = embedding_functions.CohereEmbeddingFunction(
+                    model_name=model_name,
+                    api_key=config.get("api_key"),
+                )
+            elif provider == "huggingface":
+                self.embedder_config = embedding_functions.HuggingFaceEmbeddingServer(
+                    url=config.get("api_url"),
+                )
+            else:
+                raise Exception(
+                    f"Unsupported embedding provider: {provider}, supported providers: [openai, azure, ollama, vertexai, google, cohere, huggingface]"
+                )
+        else:
+            validate_embedding_function(self.embedder_config)  # type: ignore # used for validating embedder_config if defined a embedding function/class
+            self.embedder_config = self.embedder_config
+
     def _initialize_app(self):
         import chromadb
+        from chromadb.config import Settings
 
+        self._set_embedder_config()
         chroma_client = chromadb.PersistentClient(
-            path=f"{db_storage_path()}/{self.type}/{self.agents}"
+            path=f"{db_storage_path()}/{self.type}/{self.agents}",
+            settings=Settings(allow_reset=self.allow_reset),
         )
+
         self.app = chroma_client
 
         try:
@@ -122,11 +202,15 @@ class RAGStorage(BaseRAGStorage):
             if self.app:
                 self.app.reset()
         except Exception as e:
+            if "attempt to write a readonly database" in str(e):
+                # Ignore this specific error
+                pass
+            else:
                 raise Exception(
                     f"An error occurred while resetting the {self.type} memory: {e}"
                 )
 
-    def _create_embedding_function(self):
+    def _create_default_embedding_function(self):
         import chromadb.utils.embedding_functions as embedding_functions
 
         return embedding_functions.OpenAIEmbeddingFunction(

src/crewai/tools/tool_usage.py

@@ -6,14 +6,13 @@ from difflib import SequenceMatcher
 from textwrap import dedent
 from typing import Any, List, Union
 
+import crewai.utilities.events as events
 from crewai.agents.tools_handler import ToolsHandler
 from crewai.task import Task
 from crewai.telemetry import Telemetry
 from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
 from crewai.tools.tool_usage_events import ToolUsageError, ToolUsageFinished
 from crewai.utilities import I18N, Converter, ConverterError, Printer
-import crewai.utilities.events as events
-
 
 agentops = None
 if os.environ.get("AGENTOPS_API_KEY"):
@@ -300,8 +299,11 @@ class ToolUsage:
         descriptions = []
         for tool in self.tools:
             args = {
-                k: {k2: v2 for k2, v2 in v.items() if k2 in ["description", "type"]}
-                for k, v in tool.args.items()
+                name: {
+                    "description": field.description,
+                    "type": field.annotation.__name__,
+                }
+                for name, field in tool.args_schema.model_fields.items()
             }
             descriptions.append(
                 "\n".join(

tests/cli/tools/test_main.py

@@ -75,8 +75,8 @@ def test_install_success(mock_get, mock_subprocess_run):
         [
             "uv",
             "add",
-            "--extra-index-url",
-            "https://app.crewai.com/pypi/sample-repo",
+            "--index",
+            "sample-repo=https://example.com/repo",
             "sample-tool",
         ],
         capture_output=False,

tests/crew_test.py

@@ -9,6 +9,7 @@ from unittest.mock import MagicMock, patch
 import instructor
 import pydantic_core
 import pytest
+
 from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
@@ -497,6 +498,7 @@ def test_cache_hitting_between_agents():
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_api_calls_throttling(capsys):
     from unittest.mock import patch
+
     from crewai_tools import tool
 
     @tool
@@ -779,11 +781,14 @@ def test_async_task_execution_call_count():
     list_important_history.output = mock_task_output
     write_article.output = mock_task_output
 
-    with patch.object(
+    with (
+        patch.object(
             Task, "execute_sync", return_value=mock_task_output
-    ) as mock_execute_sync, patch.object(
+        ) as mock_execute_sync,
+        patch.object(
             Task, "execute_async", return_value=mock_future
-    ) as mock_execute_async:
+        ) as mock_execute_async,
+    ):
         crew.kickoff()
 
         assert mock_execute_async.call_count == 2
@@ -1105,6 +1110,7 @@ def test_dont_set_agents_step_callback_if_already_set():
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_function_calling_llm():
     from unittest.mock import patch
+
     from crewai_tools import tool
 
     llm = "gpt-4o"
@@ -1448,52 +1454,6 @@ def test_crew_does_not_interpolate_without_inputs():
             interpolate_task_inputs.assert_not_called()
 
 
-# def test_crew_partial_inputs():
-#     agent = Agent(
-#         role="{topic} Researcher",
-#         goal="Express hot takes on {topic}.",
-#         backstory="You have a lot of experience with {topic}.",
-#     )
-
-#     task = Task(
-#         description="Give me an analysis around {topic}.",
-#         expected_output="{points} bullet points about {topic}.",
-#     )
-
-#     crew = Crew(agents=[agent], tasks=[task], inputs={"topic": "AI"})
-#     inputs = {"topic": "AI"}
-#     crew._interpolate_inputs(inputs=inputs)  # Manual call for now
-
-#     assert crew.tasks[0].description == "Give me an analysis around AI."
-#     assert crew.tasks[0].expected_output == "{points} bullet points about AI."
-#     assert crew.agents[0].role == "AI Researcher"
-#     assert crew.agents[0].goal == "Express hot takes on AI."
-#     assert crew.agents[0].backstory == "You have a lot of experience with AI."
-
-
-# def test_crew_invalid_inputs():
-#     agent = Agent(
-#         role="{topic} Researcher",
-#         goal="Express hot takes on {topic}.",
-#         backstory="You have a lot of experience with {topic}.",
-#     )
-
-#     task = Task(
-#         description="Give me an analysis around {topic}.",
-#         expected_output="{points} bullet points about {topic}.",
-#     )
-
-#     crew = Crew(agents=[agent], tasks=[task], inputs={"subject": "AI"})
-#     inputs = {"subject": "AI"}
-#     crew._interpolate_inputs(inputs=inputs)  # Manual call for now
-
-#     assert crew.tasks[0].description == "Give me an analysis around {topic}."
-#     assert crew.tasks[0].expected_output == "{points} bullet points about {topic}."
-#     assert crew.agents[0].role == "{topic} Researcher"
-#     assert crew.agents[0].goal == "Express hot takes on {topic}."
-#     assert crew.agents[0].backstory == "You have a lot of experience with {topic}."
-
-
 def test_task_callback_on_crew():
     from unittest.mock import MagicMock, patch
 
@@ -1770,7 +1730,10 @@ def test_manager_agent_with_tools_raises_exception():
 @patch("crewai.crew.Crew.kickoff")
 @patch("crewai.crew.CrewTrainingHandler")
 @patch("crewai.crew.TaskEvaluator")
-def test_crew_train_success(task_evaluator, crew_training_handler, kickoff):
+@patch("crewai.crew.Crew.copy")
+def test_crew_train_success(
+    copy_mock, task_evaluator, crew_training_handler, kickoff_mock
+):
     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.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -1781,9 +1744,19 @@ def test_crew_train_success(task_evaluator, crew_training_handler, kickoff):
         agents=[researcher, writer],
         tasks=[task],
     )
+
+    # Create a mock for the copied crew
+    copy_mock.return_value = crew
+
     crew.train(
         n_iterations=2, inputs={"topic": "AI"}, filename="trained_agents_data.pkl"
     )
+
+    # Ensure kickoff is called on the copied crew
+    kickoff_mock.assert_has_calls(
+        [mock.call(inputs={"topic": "AI"}), mock.call(inputs={"topic": "AI"})]
+    )
+
     task_evaluator.assert_has_calls(
         [
             mock.call(researcher),
@@ -1822,10 +1795,6 @@ def test_crew_train_success(task_evaluator, crew_training_handler, kickoff):
         ]
     )
 
-    kickoff.assert_has_calls(
-        [mock.call(inputs={"topic": "AI"}), mock.call(inputs={"topic": "AI"})]
-    )
-
 
 def test_crew_train_error():
     task = Task(
@@ -1840,7 +1809,7 @@ def test_crew_train_error():
     )
 
     with pytest.raises(TypeError) as e:
-        crew.train()
+        crew.train()  # type: ignore purposefully throwing err
         assert "train() missing 1 required positional argument: 'n_iterations'" in str(
             e
         )
@@ -2536,8 +2505,9 @@ def test_conditional_should_execute():
 
 
 @mock.patch("crewai.crew.CrewEvaluator")
+@mock.patch("crewai.crew.Crew.copy")
 @mock.patch("crewai.crew.Crew.kickoff")
-def test_crew_testing_function(mock_kickoff, crew_evaluator):
+def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
     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.",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -2548,11 +2518,15 @@ def test_crew_testing_function(mock_kickoff, crew_evaluator):
         agents=[researcher],
         tasks=[task],
     )
+
+    # Create a mock for the copied crew
+    copy_mock.return_value = crew
+
     n_iterations = 2
     crew.test(n_iterations, openai_model_name="gpt-4o-mini", inputs={"topic": "AI"})
 
-    assert len(mock_kickoff.mock_calls) == n_iterations
-    mock_kickoff.assert_has_calls(
+    # Ensure kickoff is called on the copied crew
+    kickoff_mock.assert_has_calls(
         [mock.call(inputs={"topic": "AI"}), mock.call(inputs={"topic": "AI"})]
     )
 

tests/tools/test_tool_usage.py

@@ -0,0 +1,119 @@
+import json
+import random
+from unittest.mock import MagicMock
+
+import pytest
+from crewai_tools import BaseTool
+from pydantic import BaseModel, Field
+
+from crewai import Agent, Task
+from crewai.tools.tool_usage import ToolUsage
+
+
+class RandomNumberToolInput(BaseModel):
+    min_value: int = Field(
+        ..., description="The minimum value of the range (inclusive)"
+    )
+    max_value: int = Field(
+        ..., description="The maximum value of the range (inclusive)"
+    )
+
+
+class RandomNumberTool(BaseTool):
+    name: str = "Random Number Generator"
+    description: str = "Generates a random number within a specified range"
+    args_schema: type[BaseModel] = RandomNumberToolInput
+
+    def _run(self, min_value: int, max_value: int) -> int:
+        return random.randint(min_value, max_value)
+
+
+# Example agent and task
+example_agent = Agent(
+    role="Number Generator",
+    goal="Generate random numbers for various purposes",
+    backstory="You are an AI agent specialized in generating random numbers within specified ranges.",
+    tools=[RandomNumberTool()],
+    verbose=True,
+)
+
+example_task = Task(
+    description="Generate a random number between 1 and 100",
+    expected_output="A random number between 1 and 100",
+    agent=example_agent,
+)
+
+
+def test_random_number_tool_range():
+    tool = RandomNumberTool()
+    result = tool._run(1, 10)
+    assert 1 <= result <= 10
+
+
+def test_random_number_tool_invalid_range():
+    tool = RandomNumberTool()
+    with pytest.raises(ValueError):
+        tool._run(10, 1)  # min_value > max_value
+
+
+def test_random_number_tool_schema():
+    tool = RandomNumberTool()
+
+    # Get the schema using model_json_schema()
+    schema = tool.args_schema.model_json_schema()
+
+    # Convert the schema to a string
+    schema_str = json.dumps(schema)
+
+    # Check if the schema string contains the expected fields
+    assert "min_value" in schema_str
+    assert "max_value" in schema_str
+
+    # Parse the schema string back to a dictionary
+    schema_dict = json.loads(schema_str)
+
+    # Check if the schema contains the correct field types
+    assert schema_dict["properties"]["min_value"]["type"] == "integer"
+    assert schema_dict["properties"]["max_value"]["type"] == "integer"
+
+    # Check if the schema contains the field descriptions
+    assert (
+        "minimum value" in schema_dict["properties"]["min_value"]["description"].lower()
+    )
+    assert (
+        "maximum value" in schema_dict["properties"]["max_value"]["description"].lower()
+    )
+
+
+def test_tool_usage_render():
+    tool = RandomNumberTool()
+
+    tool_usage = ToolUsage(
+        tools_handler=MagicMock(),
+        tools=[tool],
+        original_tools=[tool],
+        tools_description="Sample tool for testing",
+        tools_names="random_number_generator",
+        task=MagicMock(),
+        function_calling_llm=MagicMock(),
+        agent=MagicMock(),
+        action=MagicMock(),
+    )
+
+    rendered = tool_usage._render()
+
+    # Updated checks to match the actual output
+    assert "Tool Name: random number generator" in rendered
+    assert (
+        "Random Number Generator(min_value: 'integer', max_value: 'integer') - Generates a random number within a specified range min_value: 'The minimum value of the range (inclusive)', max_value: 'The maximum value of the range (inclusive)'"
+        in rendered
+    )
+    assert "Tool Arguments:" in rendered
+    assert (
+        "'min_value': {'description': 'The minimum value of the range (inclusive)', 'type': 'int'}"
+        in rendered
+    )
+    assert (
+        "'max_value': {'description': 'The maximum value of the range (inclusive)', 'type': 'int'}"
+        in rendered
+    )