small refractoring for new version

docs/core-concepts/Crews.md

@@ -123,7 +123,7 @@ result = my_crew.kickoff()
 print(result)
 ```
 
-### Kicking Off a Crew
+### Different wayt to Kicking Off a Crew
 
 Once your crew is assembled, initiate the workflow with the appropriate kickoff method. CrewAI provides several methods for better control over the kickoff process: `kickoff()`, `kickoff_for_each()`, `kickoff_async()`, and `kickoff_for_each_async()`.
 

docs/core-concepts/Training-Crew.md

@@ -0,0 +1,42 @@
+---
+title: crewAI Train
+description: Learn how to train your crewAI agents by giving them feedback early on and get consistent results.
+---
+
+## Introduction
+The training feature in CrewAI allows you to train your AI agents using the command-line interface (CLI). By running the command `crewai train -n <n_iterations>`, you can specify the number of iterations for the training process.
+
+During training, CrewAI utilizes techniques to optimize the performance of your agents along with human feedback. This helps the agents improve their understanding, decision-making, and problem-solving abilities.
+
+To use the training feature, follow these steps:
+
+1. Open your terminal or command prompt.
+2. Navigate to the directory where your CrewAI project is located.
+3. Run the following command:
+
+```shell
+crewai train -n <n_iterations>
+```
+
+Replace `<n_iterations>` with the desired number of training iterations. This determines how many times the agents will go through the training process.
+
+Remember to also replace the placeholder inputs with the actual values you want to use on the main.py file in the `train` function.
+
+```python
+def train():
+    """
+    Train the crew for a given number of iterations.
+    """
+    inputs = {"topic": "AI LLMs"}
+    try:
+        ProjectCreationCrew().crew().train(n_iterations=int(sys.argv[1]), inputs=inputs)
+    ...
+```
+
+It is important to note that the training process may take some time, depending on the complexity of your agents and will also require your feedback on each iteration.
+
+Once the training is complete, your agents will be equipped with enhanced capabilities and knowledge, ready to tackle complex tasks and provide more consistent and valuable insights.
+
+Remember to regularly update and retrain your agents to ensure they stay up-to-date with the latest information and advancements in the field.
+
+Happy training with CrewAI!

docs/how-to/Coding-Agents.md

@@ -0,0 +1,17 @@
+---
+title: Coding Agents
+description: Learn how to enable your crewAI Agents to write code and execute it.
+---
+
+## Introduction
+TLDR: strongly recommended to use bigger models like gpt-4 and such
+
+EXAMPLE:
+```python
+Agent(
+    role="Senior Python Developer",
+    goal="Craft well design and thought out code",
+    backstory="You are a senior python…”,
+    allow_code_execution=True,
+)
+```

docs/index.md

@@ -33,6 +33,11 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     Crews
                 </a>
             </li>
+            <li>
+                <a href="./core-concepts/Training-Crew">
+                    Training
+                </a>
+            </li>
             <li>
                 <a href="./core-concepts/Memory">
                     Memory
@@ -78,16 +83,36 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     Customizing Agents
                 </a>
             </li>
+            <li>
+                <a href="./how-to/Coding-Agents">
+                    Coding Agents
+                </a>
+            </li>
             <li>
                 <a href="./how-to/Human-Input-on-Execution">
                     Human Input on Execution
                 </a>
             </li>
+            <li>
+                <a href="./how-to/Kickoff-async">
+                    Kickoff a Crew Asynchronously
+                </a>
+            </li>
+            <li>
+                <a href="./how-to/Kickoff-for-each">
+                    Kickoff a Crew for a List
+                </a>
+            </li>
             <li>
                 <a href="./how-to/AgentOps-Observability">
                     Agent Monitoring with AgentOps
                 </a>
             </li>
+            <li>
+                <a href="./how-to/Langtrace-Observability">
+                    Agent Monitoring with LangTrace
+                </a>
+            </li>
         </ul>
     </div>
     <div style="width:30%">

mkdocs.yml

@@ -126,6 +126,7 @@ nav:
     - Processes: 'core-concepts/Processes.md'
     - Crews: 'core-concepts/Crews.md'
     - Collaboration: 'core-concepts/Collaboration.md'
+    - Training: 'core-concepts/Training-Crew.md'
     - Memory: 'core-concepts/Memory.md'
     - Using LangChain Tools: 'core-concepts/Using-LangChain-Tools.md'
     - Using LlamaIndex Tools: 'core-concepts/Using-LlamaIndex-Tools.md'
@@ -138,7 +139,10 @@ nav:
     - Create your own Manager Agent: 'how-to/Your-Own-Manager-Agent.md'
     - Connecting to any LLM: 'how-to/LLM-Connections.md'
     - Customizing Agents: 'how-to/Customizing-Agents.md'
+    - Coding Agents: 'how-to/Coding-Agents.md'
     - Human Input on Execution: 'how-to/Human-Input-on-Execution.md'
+    - Kickoff a Crew Asynchronously: 'how-to/Kickoff-async.md'
+    - Kickoff a Crew for a List: 'how-to/Kickoff-for-each.md'
     - Agent Monitoring with AgentOps: 'how-to/AgentOps-Observability.md'
     - Agent Monitoring with LangTrace: 'how-to/Langtrace-Observability.md'
   - Tools Docs:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "crewai"
-version = "0.35.0"
+version = "0.35.3"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"
@@ -14,17 +14,17 @@ Repository = "https://github.com/joaomdmoura/crewai"
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
 pydantic = "^2.4.2"
-langchain = "^0.1.10"
+langchain = ">=0.2,<=0.3"
 openai = "^1.13.3"
 opentelemetry-api = "^1.22.0"
 opentelemetry-sdk = "^1.22.0"
 opentelemetry-exporter-otlp-proto-http = "^1.22.0"
 instructor = "1.3.3"
 regex = "^2023.12.25"
-crewai-tools = { version = "^0.4.0", optional = true }
+crewai-tools = { version = "^0.4.1", optional = true }
 click = "^8.1.7"
 python-dotenv = "^1.0.0"
-embedchain = "0.1.109"
+embedchain = { git = "https://github.com/joaomdmoura/embedchain.git", branch = "main" }
 appdirs = "^1.4.4"
 jsonref = "^1.1.0"
 
@@ -43,7 +43,7 @@ mkdocs-material = { extras = ["imaging"], version = "^9.5.7" }
 mkdocs-material-extensions = "^1.3.1"
 pillow = "^10.2.0"
 cairosvg = "^2.7.1"
-crewai-tools = "^0.4.0"
+crewai-tools = "^0.4.1"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^8.0.0"

src/crewai/agent.py

@@ -255,6 +255,16 @@ class Agent(BaseAgent):
         tools = agent_tools.tools()
         return tools
 
+    def get_code_execution_tools(self):
+        try:
+            from crewai_tools import CodeInterpreterTool
+
+            return [CodeInterpreterTool()]
+        except ModuleNotFoundError:
+            self._logger.log(
+                "info", "Coding tools not available. Install crewai_tools. "
+            )
+
     def get_output_converter(self, llm, text, model, instructions):
         return Converter(llm=llm, text=text, model=model, instructions=instructions)
 
@@ -270,13 +280,8 @@ class Agent(BaseAgent):
                     tools_list.append(tool.to_langchain())
                 else:
                     tools_list.append(tool)
-
-            if self.allow_code_execution:
-                from crewai_tools.code_interpreter_tool import CodeInterpreterTool
-
-                tools_list.append(CodeInterpreterTool)
-
         except ModuleNotFoundError:
+            tools_list = []
             for tool in tools:
                 tools_list.append(tool)
         return tools_list

src/crewai/agents/agent_builder/base_agent.py

@@ -214,7 +214,7 @@ class BaseAgent(ABC, BaseModel):
         self.create_agent_executor()
 
     def increment_formatting_errors(self) -> None:
-        print("Formatting errors incremented")
+        self.formatting_errors += 1
 
     def copy(self):
         exclude = {

src/crewai/crew.py

@@ -299,6 +299,8 @@ class Crew(BaseModel):
                 and not agent.function_calling_llm
             ):
                 agent.function_calling_llm = self.function_calling_llm
+            if hasattr(agent, "allow_code_execution") and agent.allow_code_execution:
+                agent.tools += agent.get_code_execution_tools()
             if hasattr(agent, "step_callback") and not agent.step_callback:
                 agent.step_callback = self.step_callback
 

tests/crew_test.py

@@ -600,6 +600,30 @@ def test_task_with_no_arguments():
     assert result == "75"
 
 
+def test_code_execution_flag_adds_code_tool_upon_kickoff():
+    from crewai_tools import CodeInterpreterTool
+
+    programmer = Agent(
+        role="Programmer",
+        goal="Write code to solve problems.",
+        backstory="You're a programmer who loves to solve problems with code.",
+        allow_delegation=False,
+        allow_code_execution=True,
+    )
+
+    task = Task(
+        description="How much is 2 + 2?",
+        expected_output="The result of the sum as an integer.",
+        agent=programmer,
+    )
+
+    crew = Crew(agents=[programmer], tasks=[task])
+    crew.kickoff()
+    assert len(programmer.tools) == 1
+    assert programmer.tools[0].__class__ == CodeInterpreterTool
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_delegation_is_not_enabled_if_there_are_only_one_agent():
     from unittest.mock import patch
 
@@ -691,8 +715,8 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     assert result == '"Howdy!"'
 
     assert crew.usage_metrics == {
-        "total_tokens": 1640,
-        "prompt_tokens": 1357,
+        "total_tokens": 1616,
+        "prompt_tokens": 1333,
         "completion_tokens": 283,
         "successful_requests": 3,
     }