Merge branch 'main' of github.com:crewAIInc/crewAI into knowledge

Make it green!

.github/workflows/security-checker.yml

@@ -19,5 +19,5 @@ jobs:
         run: pip install bandit
 
       - name: Run Bandit
-        run: bandit -c pyproject.toml -r src/ -lll
+        run: bandit -c pyproject.toml -r src/ -ll
 

.github/workflows/tests.yml

@@ -26,7 +26,7 @@ jobs:
         run: uv python install 3.11.9
 
       - name: Install the project
-        run: uv sync --dev
+        run: uv sync --dev --all-extras
 
       - name: Run tests
-        run: uv run pytest tests
+        run: uv run pytest tests -vv

.gitignore

@@ -17,3 +17,7 @@ rc-tests/*
 temp/*
 .vscode/*
 crew_tasks_output.json
+.codesight
+.mypy_cache
+.ruff_cache
+.venv

docs/concepts/crews.mdx

@@ -22,7 +22,8 @@ A crew in crewAI represents a collaborative group of agents working together to
 | **Max RPM** _(optional)_              | `max_rpm`              | Maximum requests per minute the crew adheres to during execution. Defaults to `None`.                                                                                                                                                                     |
 | **Language** _(optional)_             | `language`             | Language used for the crew, defaults to English.                                                                                                                                                                                                          |
 | **Language File** _(optional)_        | `language_file`        | Path to the language file to be used for the crew.                                                                                                                                                                                                        |
-| **Memory** _(optional)_               | `memory`               | Utilized for storing execution memories (short-term, long-term, entity memory). Defaults to `False`.                                                                                                                                                       |
+| **Memory** _(optional)_               | `memory`               | Utilized for storing execution memories (short-term, long-term, entity memory).                                                                                                                                                                           |
+| **Memory Config** _(optional)_        | `memory_config`        | Configuration for the memory provider to be used by the crew.                                                                                                                                                                                          |
 | **Cache** _(optional)_                | `cache`                | Specifies whether to use a cache for storing the results of tools' execution. Defaults to `True`.                                                                                                                                                          |
 | **Embedder** _(optional)_             | `embedder`             | Configuration for the embedder to be used by the crew. Mostly used by memory for now. Default is `{"provider": "openai"}`.                                                                                                                                                                     |
 | **Full Output** _(optional)_          | `full_output`          | Whether the crew should return the full output with all tasks outputs or just the final output. Defaults to `False`.                                                                                                                                       |

docs/concepts/flows.mdx

@@ -18,60 +18,63 @@ Flows allow you to create structured, event-driven workflows. They provide a sea
 
 4. **Flexible Control Flow**: Implement conditional logic, loops, and branching within your workflows.
 
+5. **Input Flexibility**: Flows can accept inputs to initialize or update their state, with different handling for structured and unstructured state management.
+
 ## Getting Started
 
 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
+### Passing Inputs to Flows
 
+Flows can accept inputs to initialize or update their state before execution. The way inputs are handled depends on whether the flow uses structured or unstructured state management.
+
+#### Structured State Management
+
+In structured state management, the flow's state is defined using a Pydantic `BaseModel`. Inputs must match the model's schema, and any updates will overwrite the default values.
+
+```python
 from crewai.flow.flow import Flow, listen, start
-from dotenv import load_dotenv
-from litellm import completion
+from pydantic import BaseModel
 
+class ExampleState(BaseModel):
+    counter: int = 0
+    message: str = ""
 
-class ExampleFlow(Flow):
-    model = "gpt-4o-mini"
-
+class StructuredExampleFlow(Flow[ExampleState]):
     @start()
-    def generate_city(self):
-        print("Starting flow")
+    def first_method(self):
+        # Implementation
 
-        response = completion(
-            model=self.model,
-            messages=[
-                {
-                    "role": "user",
-                    "content": "Return the name of a random city in the world.",
-                },
-            ],
-        )
+flow = StructuredExampleFlow()
+flow.kickoff(inputs={"counter": 10})
+```
 
-        random_city = response["choices"][0]["message"]["content"]
-        print(f"Random City: {random_city}")
+In this example, the `counter` is initialized to `10`, while `message` retains its default value.
 
-        return random_city
+#### Unstructured State Management
 
-    @listen(generate_city)
-    def generate_fun_fact(self, random_city):
-        response = completion(
-            model=self.model,
-            messages=[
-                {
-                    "role": "user",
-                    "content": f"Tell me a fun fact about {random_city}",
-                },
-            ],
-        )
+In unstructured state management, the flow's state is a dictionary. You can pass any dictionary to update the state.
 
-        fun_fact = response["choices"][0]["message"]["content"]
-        return fun_fact
+```python
+from crewai.flow.flow import Flow, listen, start
 
+class UnstructuredExampleFlow(Flow):
+    @start()
+    def first_method(self):
+        # Implementation
 
+flow = UnstructuredExampleFlow()
+flow.kickoff(inputs={"counter": 5, "message": "Initial message"})
+```
 
-flow = ExampleFlow()
-result = flow.kickoff()
+Here, both `counter` and `message` are updated based on the provided inputs.
 
-print(f"Generated fun fact: {result}")
+**Note:** Ensure that inputs for structured state management adhere to the defined schema to avoid validation errors.
+
+### Example Flow
+
+```python
+# Existing example code
 ```
 
 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.
@@ -94,14 +97,14 @@ The `@listen()` decorator can be used in several ways:
 
 1. **Listening to a Method by Name**: You can pass the name of the method you want to listen to as a string. When that method completes, the listener method will be triggered.
 
-   ```python Code
+   ```python
    @listen("generate_city")
    def generate_fun_fact(self, random_city):
        # Implementation
    ```
 
 2. **Listening to a Method Directly**: You can pass the method itself. When that method completes, the listener method will be triggered.
-   ```python Code
+   ```python
    @listen(generate_city)
    def generate_fun_fact(self, random_city):
        # Implementation
@@ -118,7 +121,7 @@ When you run a Flow, the final output is determined by the last method that comp
 Here's how you can access the final output:
 
 <CodeGroup>
-```python Code
+```python
 from crewai.flow.flow import Flow, listen, start
 
 class OutputExampleFlow(Flow):
@@ -130,18 +133,17 @@ class OutputExampleFlow(Flow):
     def second_method(self, first_output):
         return f"Second method received: {first_output}"
 
-
 flow = OutputExampleFlow()
 final_output = flow.kickoff()
 
 print("---- Final Output ----")
 print(final_output)
-````
+```
 
-``` text Output
+```text
 ---- Final Output ----
 Second method received: Output from first_method
-````
+```
 
 </CodeGroup>
 
@@ -156,7 +158,7 @@ Here's an example of how to update and access the state:
 
 <CodeGroup>
 
-```python Code
+```python
 from crewai.flow.flow import Flow, listen, start
 from pydantic import BaseModel
 
@@ -184,7 +186,7 @@ print("Final State:")
 print(flow.state)
 ```
 
-```text Output
+```text
 Final Output: Hello from first_method - updated by second_method
 Final State:
 counter=2 message='Hello from first_method - updated by second_method'
@@ -208,10 +210,10 @@ allowing developers to choose the approach that best fits their application's ne
 In unstructured state management, all state is stored in the `state` attribute of the `Flow` class.
 This approach offers flexibility, enabling developers to add or modify state attributes on the fly without defining a strict schema.
 
-```python Code
+```python
 from crewai.flow.flow import Flow, listen, start
 
-class UntructuredExampleFlow(Flow):
+class UnstructuredExampleFlow(Flow):
 
     @start()
     def first_method(self):
@@ -230,8 +232,7 @@ class UntructuredExampleFlow(Flow):
 
         print(f"State after third_method: {self.state}")
 
-
-flow = UntructuredExampleFlow()
+flow = UnstructuredExampleFlow()
 flow.kickoff()
 ```
 
@@ -245,16 +246,14 @@ flow.kickoff()
 Structured state management leverages predefined schemas to ensure consistency and type safety across the workflow.
 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
+```python
 from crewai.flow.flow import Flow, listen, start
 from pydantic import BaseModel
 
-
 class ExampleState(BaseModel):
     counter: int = 0
     message: str = ""
 
-
 class StructuredExampleFlow(Flow[ExampleState]):
 
     @start()
@@ -273,7 +272,6 @@ class StructuredExampleFlow(Flow[ExampleState]):
 
         print(f"State after third_method: {self.state}")
 
-
 flow = StructuredExampleFlow()
 flow.kickoff()
 ```
@@ -307,7 +305,7 @@ The `or_` function in Flows allows you to listen to multiple methods and trigger
 
 <CodeGroup>
 
-```python Code
+```python
 from crewai.flow.flow import Flow, listen, or_, start
 
 class OrExampleFlow(Flow):
@@ -324,13 +322,11 @@ class OrExampleFlow(Flow):
     def logger(self, result):
         print(f"Logger: {result}")
 
-
-
 flow = OrExampleFlow()
 flow.kickoff()
 ```
 
-```text Output
+```text
 Logger: Hello from the start method
 Logger: Hello from the second method
 ```
@@ -346,7 +342,7 @@ The `and_` function in Flows allows you to listen to multiple methods and trigge
 
 <CodeGroup>
 
-```python Code
+```python
 from crewai.flow.flow import Flow, and_, listen, start
 
 class AndExampleFlow(Flow):
@@ -368,7 +364,7 @@ flow = AndExampleFlow()
 flow.kickoff()
 ```
 
-```text Output
+```text
 ---- Logger ----
 {'greeting': 'Hello from the start method', 'joke': 'What do computers eat? Microchips.'}
 ```
@@ -385,7 +381,7 @@ You can specify different routes based on the output of the method, allowing you
 
 <CodeGroup>
 
-```python Code
+```python
 import random
 from crewai.flow.flow import Flow, listen, router, start
 from pydantic import BaseModel
@@ -416,12 +412,11 @@ class RouterFlow(Flow[ExampleState]):
     def fourth_method(self):
         print("Fourth method running")
 
-
 flow = RouterFlow()
 flow.kickoff()
 ```
 
-```text Output
+```text
 Starting the structured flow
 Third method running
 Fourth method running
@@ -484,7 +479,7 @@ The `main.py` file is where you create your flow and connect the crews together.
 
 Here's an example of how you can connect the `poem_crew` in the `main.py` file:
 
-```python Code
+```python
 #!/usr/bin/env python
 from random import randint
 
@@ -577,18 +572,20 @@ This command will create a new directory for your crew within the `crews` folder
 
 After adding a new crew, your folder structure will look like this:
 
-name_of_flow/
-├── crews/
-│   ├── poem_crew/
-│   │   ├── config/
-│   │   │   ├── agents.yaml
-│   │   │   └── tasks.yaml
-│   │   └── poem_crew.py
-│   └── name_of_crew/
-│       ├── config/
-│       │   ├── agents.yaml
-│       │   └── tasks.yaml
-│       └── name_of_crew.py
+| 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. |
+| │   │   ├── `config/`  | Configuration files directory for the "poem_crew".                 |
+| │   │   │  ├── `agents.yaml` | YAML file defining the agents for "poem_crew".                     |
+| │   │   │  └── `tasks.yaml`  | YAML file defining the tasks for "poem_crew".                      |
+| │   │   └── `poem_crew.py`    | Script for "poem_crew" functionality.                              |
+| └── `name_of_crew/`       | Directory for the new crew.                                          |
+|     ├── `config/`         | Configuration files directory for the new crew.                     |
+|     │   ├── `agents.yaml` | YAML file defining the agents for the new crew.                     |
+|     │   └── `tasks.yaml`  | YAML file defining the tasks for the new crew.                      |
+|     └── `name_of_crew.py` | Script for the new crew functionality.                              |
 
 You can then customize the `agents.yaml` and `tasks.yaml` files to define the agents and tasks for your new crew. The `name_of_crew.py` file will contain the crew's logic, which you can modify to suit your needs.
 
@@ -610,7 +607,7 @@ CrewAI provides two convenient methods to generate plots of your flows:
 
 If you are working directly with a flow instance, you can generate a plot by calling the `plot()` method on your flow object. This method will create an HTML file containing the interactive plot of your flow.
 
-```python Code
+```python
 # Assuming you have a flow instance
 flow.plot("my_flow_plot")
 ```

docs/concepts/knowledge.mdx

@@ -0,0 +1,75 @@
+---
+title: Knowledge
+description: What is knowledge in CrewAI and how to use it.
+icon: book
+---
+
+# Using Knowledge in CrewAI
+
+## Introduction
+
+The Knowledge class in CrewAI provides a powerful way to manage and query knowledge sources for your AI agents. This guide will show you how to implement knowledge management in your CrewAI projects.
+Additionally, we have specific tools for generate knowledge sources for strings, text files, PDF's, and Spreadsheets. You can expand on any source type by extending the `KnowledgeSource` class.
+
+## Basic Implementation
+
+Here's a simple example of how to use the Knowledge class:
+
+```python
+from crewai import Agent, Task, Crew, Process, LLM
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+
+# Create a knowledge source
+content = "Users name is John. He is 30 years old and lives in San Francisco."
+string_source = StringKnowledgeSource(
+    content=content, metadata={"preference": "personal"}
+)
+
+
+llm = LLM(model="gpt-4o-mini", temperature=0)
+  # Create an agent with the knowledge store
+agent = Agent(
+    role="About User",
+    goal="You know everything about the user.",
+    backstory="""You are a master at understanding people and their preferences.""",
+    verbose=True,
+    allow_delegation=False,
+    llm=llm,
+)
+task = Task(
+    description="Answer the following questions about the user: {question}",
+    expected_output="An answer to the question.",
+    agent=agent,
+)
+
+crew = Crew(
+    agents=[agent],
+    tasks=[task],
+    verbose=True,
+    process=Process.sequential,
+    knowledge={"sources": [string_source], "metadata": {"preference": "personal"}}, # Enable knowledge by adding the sources here. You can also add more sources to the sources list.
+)
+
+result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"})
+```
+
+
+## Embedder Configuration
+
+You can also configure the embedder for the knowledge store. This is useful if you want to use a different embedder for the knowledge store than the one used for the agents.
+
+```python
+...
+string_source = StringKnowledgeSource(
+    content="Users name is John. He is 30 years old and lives in San Francisco.",
+    metadata={"preference": "personal"}
+)
+crew = Crew(
+    ...
+    knowledge={
+        "sources": [string_source],
+        "metadata": {"preference": "personal"},
+        "embedder_config": {"provider": "openai", "config": {"model": "text-embedding-3-small"}},
+    },
+)
+```

docs/concepts/llms.mdx

@@ -25,7 +25,102 @@ By default, CrewAI uses the `gpt-4o-mini` model. It uses environment variables i
 - `OPENAI_API_BASE`
 - `OPENAI_API_KEY`
 
-### 2. Custom LLM Objects
+### 2. Updating YAML files
+
+You can update the `agents.yml` file to refer to the LLM you want to use:
+
+```yaml Code
+researcher:
+    role: Research Specialist
+    goal: Conduct comprehensive research and analysis to gather relevant information,
+        synthesize findings, and produce well-documented insights.
+    backstory: A dedicated research professional with years of experience in academic
+        investigation, literature review, and data analysis, known for thorough and
+        methodical approaches to complex research questions.
+    verbose: true
+    llm: openai/gpt-4o
+    # llm: azure/gpt-4o-mini
+    # llm: gemini/gemini-pro
+    # llm: anthropic/claude-3-5-sonnet-20240620
+    # llm: bedrock/anthropic.claude-3-sonnet-20240229-v1:0
+    # llm: mistral/mistral-large-latest
+    # llm: ollama/llama3:70b
+    # llm: groq/llama-3.2-90b-vision-preview
+    # llm: watsonx/meta-llama/llama-3-1-70b-instruct
+    # llm: nvidia_nim/meta/llama3-70b-instruct
+    # llm: sambanova/Meta-Llama-3.1-8B-Instruct
+    # ...
+```
+
+Keep in mind that you will need to set certain ENV vars depending on the model you are
+using to account for the credentials or set a custom LLM object like described below.
+Here are some of the required ENV vars for some of the LLM integrations:
+
+<AccordionGroup>
+    <Accordion title="OpenAI">
+    ```python Code
+    OPENAI_API_KEY=<your-api-key>
+    OPENAI_API_BASE=<optional-custom-base-url>
+    OPENAI_MODEL_NAME=<openai-model-name>
+    OPENAI_ORGANIZATION=<your-org-id>       # OPTIONAL
+    OPENAI_API_BASE=<openaiai-api-base>     # OPTIONAL
+    ```
+    </Accordion>
+
+    <Accordion title="Anthropic">
+    ```python Code
+    ANTHROPIC_API_KEY=<your-api-key>
+    ```
+    </Accordion>
+
+    <Accordion title="Google">
+    ```python Code
+    GEMINI_API_KEY=<your-api-key>
+    ```
+    </Accordion>
+
+    <Accordion title="Azure">
+    ```python Code
+    AZURE_API_KEY=<your-api-key>                    # "my-azure-api-key"
+    AZURE_API_BASE=<your-resource-url>              # "https://example-endpoint.openai.azure.com"
+    AZURE_API_VERSION=<api-version>                 # "2023-05-15"
+    AZURE_AD_TOKEN=<your-azure-ad-token>            # Optional
+    AZURE_API_TYPE=<your-azure-api-type>            # Optional
+    ```
+    </Accordion>
+
+    <Accordion title="AWS Bedrock">
+    ```python Code
+    AWS_ACCESS_KEY_ID=<your-access-key>
+    AWS_SECRET_ACCESS_KEY=<your-secret-key>
+    AWS_DEFAULT_REGION=<your-region>
+    ```
+    </Accordion>
+
+    <Accordion title="Mistral">
+    ```python Code
+    MISTRAL_API_KEY=<your-api-key>
+    ```
+    </Accordion>
+
+    <Accordion title="Groq">
+    ```python Code
+    GROQ_API_KEY=<your-api-key>
+    ```
+    </Accordion>
+
+    <Accordion title="IBM watsonx.ai">
+    ```python Code
+    WATSONX_URL=<your-url>                          # (required) Base URL of your WatsonX instance
+    WATSONX_APIKEY=<your-apikey>                    # (required) IBM cloud API key
+    WATSONX_TOKEN=<your-token>                      # (required) IAM auth token (alternative to APIKEY)
+    WATSONX_PROJECT_ID=<your-project-id>            # (optional) Project ID of your WatsonX instance
+    WATSONX_DEPLOYMENT_SPACE_ID=<your-space-id>     # (optional) ID of deployment space for deployed models
+    ```
+    </Accordion>
+</AccordionGroup>
+
+### 3. Custom LLM Objects
 
 Pass a custom LLM implementation or object from another library.
 
@@ -102,7 +197,7 @@ When configuring an LLM for your agent, you have access to a wide range of param
 
 These are examples of how to configure LLMs for your agent.
 
-<AccordionGroup>    
+<AccordionGroup>
     <Accordion title="OpenAI">
 
     ```python Code
@@ -131,13 +226,12 @@ These are examples of how to configure LLMs for your agent.
 
     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, ...) 
+    agent = Agent(llm=llm, ...)
     ```
     </Accordion>
- 
+
     <Accordion title="Ollama (Local LLMs)">
 
     CrewAI supports using Ollama for running open-source models locally:
@@ -151,7 +245,7 @@ These are examples of how to configure LLMs for your agent.
 
     agent = Agent(
         llm=LLM(
-            model="ollama/llama3.1", 
+            model="ollama/llama3.1",
             base_url="http://localhost:11434"
         ),
         ...
@@ -165,8 +259,7 @@ These are examples of how to configure LLMs for your agent.
     from crewai import LLM
 
     llm = LLM(
-        model="groq/llama3-8b-8192", 
-        base_url="https://api.groq.com/openai/v1", 
+        model="groq/llama3-8b-8192",
         api_key="your-api-key-here"
     )
     agent = Agent(llm=llm, ...)
@@ -180,21 +273,18 @@ These are examples of how to configure LLMs for your agent.
 
     llm = LLM(
         model="anthropic/claude-3-5-sonnet-20241022",
-        base_url="https://api.anthropic.com/v1",
         api_key="your-api-key-here"
     )
     agent = Agent(llm=llm, ...)
     ```
     </Accordion>
 
-    <Accordion title="Fireworks">
-
+    <Accordion title="Fireworks AI">
     ```python Code
     from crewai import LLM
 
     llm = LLM(
-        model="fireworks/meta-llama-3.1-8b-instruct",
-        base_url="https://api.fireworks.ai/inference/v1",
+        model="fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct",
         api_key="your-api-key-here"
     )
     agent = Agent(llm=llm, ...)
@@ -207,8 +297,7 @@ These are examples of how to configure LLMs for your agent.
     from crewai import LLM
 
     llm = LLM(
-        model="gemini/gemini-1.5-flash",
-        base_url="https://api.gemini.google.com/v1",
+        model="gemini/gemini-1.5-pro-002",
         api_key="your-api-key-here"
     )
     agent = Agent(llm=llm, ...)
@@ -230,6 +319,29 @@ These are examples of how to configure LLMs for your agent.
     </Accordion>
 
     <Accordion title="IBM watsonx.ai">
+    You can use IBM Watson by seeting the following ENV vars:
+
+    ```python Code
+    WATSONX_URL=<your-url>
+    WATSONX_APIKEY=<your-apikey>
+    WATSONX_PROJECT_ID=<your-project-id>
+    ```
+
+    You can then define your agents llms by updating the `agents.yml`
+
+    ```yaml Code
+    researcher:
+        role: Research Specialist
+        goal: Conduct comprehensive research and analysis to gather relevant information,
+            synthesize findings, and produce well-documented insights.
+        backstory: A dedicated research professional with years of experience in academic
+            investigation, literature review, and data analysis, known for thorough and
+            methodical approaches to complex research questions.
+        verbose: true
+        llm: watsonx/meta-llama/llama-3-1-70b-instruct
+    ```
+
+    You can also set up agents more dynamically as a base level LLM instance, like bellow:
 
     ```python Code
     from crewai import LLM
@@ -242,6 +354,20 @@ These are examples of how to configure LLMs for your agent.
     agent = Agent(llm=llm, ...)
     ```
     </Accordion>
+
+    <Accordion title="Hugging Face">
+
+    ```python Code
+    from crewai import LLM
+
+    llm = LLM(
+        model="huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct",
+        api_key="your-api-key-here",
+        base_url="your_api_endpoint"
+    )
+    agent = Agent(llm=llm, ...)
+    ```
+    </Accordion>
 </AccordionGroup>
 
 ## Changing the Base API URL

docs/concepts/memory.mdx

@@ -18,6 +18,7 @@ reason, and learn from past interactions.
 | **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. |
 | **Entity Memory**    | Captures and organizes information about entities (people, places, concepts) encountered during tasks, facilitating deeper understanding and relationship mapping. Uses `RAG` for storing entity information. |
 | **Contextual Memory**| Maintains the context of interactions by combining `ShortTermMemory`, `LongTermMemory`, and `EntityMemory`, aiding in the coherence and relevance of agent responses over a sequence of tasks or a conversation. |
+| **User Memory**      | Stores user-specific information and preferences, enhancing personalization and user experience. |
 
 ## How Memory Systems Empower Agents
 
@@ -92,6 +93,47 @@ my_crew = Crew(
 )
 ```
 
+## Integrating Mem0 for Enhanced User Memory
+
+[Mem0](https://mem0.ai/) is a self-improving memory layer for LLM applications, enabling personalized AI experiences. 
+
+To include user-specific memory you can get your API key [here](https://app.mem0.ai/dashboard/api-keys) and refer the [docs](https://docs.mem0.ai/platform/quickstart#4-1-create-memories) for adding user preferences.
+
+
+```python Code
+import os
+from crewai import Crew, Process
+from mem0 import MemoryClient
+
+# Set environment variables for Mem0
+os.environ["MEM0_API_KEY"] = "m0-xx"
+
+# Step 1: Record preferences based on past conversation or user input
+client = MemoryClient()
+messages = [
+    {"role": "user", "content": "Hi there! I'm planning a vacation and could use some advice."},
+    {"role": "assistant", "content": "Hello! I'd be happy to help with your vacation planning. What kind of destination do you prefer?"},
+    {"role": "user", "content": "I am more of a beach person than a mountain person."},
+    {"role": "assistant", "content": "That's interesting. Do you like hotels or Airbnb?"},
+    {"role": "user", "content": "I like Airbnb more."},
+]
+client.add(messages, user_id="john")
+
+# Step 2: Create a Crew with User Memory
+
+crew = Crew(
+    agents=[...],
+    tasks=[...],
+    verbose=True,
+    process=Process.sequential,
+    memory=True,
+    memory_config={
+        "provider": "mem0",
+        "config": {"user_id": "john"},
+    },
+)
+```
+
 
 ## Additional Embedding Providers
 
@@ -254,6 +296,31 @@ my_crew = Crew(
 )
 ```
 
+### Using Watson embeddings
+
+```python Code
+from crewai import Crew, Agent, Task, Process
+
+# Note: Ensure you have installed and imported `ibm_watsonx_ai` for Watson embeddings to work.
+
+my_crew = Crew(
+    agents=[...],
+    tasks=[...],
+    process=Process.sequential,
+    memory=True,
+    verbose=True,
+    embedder={
+        "provider": "watson",
+        "config": {
+            "model": "<model_name>",
+            "api_url": "<api_url>",
+            "api_key": "<YOUR_API_KEY>",
+            "project_id": "<YOUR_PROJECT_ID>",
+        }
+    }
+)
+```
+
 ### Resetting Memory
 
 ```shell

docs/concepts/tools.mdx

@@ -5,13 +5,14 @@ icon: screwdriver-wrench
 ---
 
 ## Introduction
-CrewAI tools empower agents with capabilities ranging from web searching and data analysis to collaboration and delegating tasks among coworkers. 
+
+CrewAI tools empower agents with capabilities ranging from web searching and data analysis to collaboration and delegating tasks among coworkers.
 This documentation outlines how to create, integrate, and leverage these tools within the CrewAI framework, including a new focus on collaboration tools.
 
 ## What is a Tool?
 
-A tool in CrewAI is a skill or function that agents can utilize to perform various actions. 
-This includes tools from the [CrewAI Toolkit](https://github.com/joaomdmoura/crewai-tools) and [LangChain Tools](https://python.langchain.com/docs/integrations/tools), 
+A tool in CrewAI is a skill or function that agents can utilize to perform various actions.
+This includes tools from the [CrewAI Toolkit](https://github.com/joaomdmoura/crewai-tools) and [LangChain Tools](https://python.langchain.com/docs/integrations/tools),
 enabling everything from simple searches to complex interactions and effective teamwork among agents.
 
 ## Key Characteristics of Tools
@@ -103,57 +104,53 @@ crew.kickoff()
 
 Here is a list of the available tools and their descriptions:
 
-| Tool                        | Description                                                                                   |
-| :-------------------------- | :-------------------------------------------------------------------------------------------- |
-| **BrowserbaseLoadTool**     | A tool for interacting with and extracting data from web browsers.                            |
-| **CodeDocsSearchTool**      | A RAG tool optimized for searching through code documentation and related technical documents. |
-| **CodeInterpreterTool**     | A tool for interpreting python code.                                                          |
-| **ComposioTool**            | Enables use of Composio tools.                                                                |
-| **CSVSearchTool**           | A RAG tool designed for searching within CSV files, tailored to handle structured data.       |
-| **DALL-E Tool**             | A tool for generating images using the DALL-E API.                                            |
-| **DirectorySearchTool**     | A RAG tool for searching within directories, useful for navigating through file systems.      |
-| **DOCXSearchTool**          | A RAG tool aimed at searching within DOCX documents, ideal for processing Word files.         |
-| **DirectoryReadTool**       | Facilitates reading and processing of directory structures and their contents.                |
-| **EXASearchTool**           | A tool designed for performing exhaustive searches across various data sources.               |
-| **FileReadTool**            | Enables reading and extracting data from files, supporting various file formats.              |
-| **FirecrawlSearchTool**     | A tool to search webpages using Firecrawl and return the results.                             |
-| **FirecrawlCrawlWebsiteTool** | A tool for crawling webpages using Firecrawl.                                               |
-| **FirecrawlScrapeWebsiteTool** | A tool for scraping webpages URL using Firecrawl and returning its contents.              |
-| **GithubSearchTool**        | A RAG tool for searching within GitHub repositories, useful for code and documentation search.|
-| **SerperDevTool**           | A specialized tool for development purposes, with specific functionalities under development. |
-| **TXTSearchTool**           | A RAG tool focused on searching within text (.txt) files, suitable for unstructured data.     |
-| **JSONSearchTool**          | A RAG tool designed for searching within JSON files, catering to structured data handling.     |
-| **LlamaIndexTool**          | Enables the use of LlamaIndex tools.                                                          |
-| **MDXSearchTool**           | A RAG tool tailored for searching within Markdown (MDX) files, useful for documentation.      |
-| **PDFSearchTool**           | A RAG tool aimed at searching within PDF documents, ideal for processing scanned documents.    |
-| **PGSearchTool**            | A RAG tool optimized for searching within PostgreSQL databases, suitable for database queries. |
-| **Vision Tool**             | A tool for generating images using the DALL-E API.                                            |
-| **RagTool**                 | A general-purpose RAG tool capable of handling various data sources and types.                |
-| **ScrapeElementFromWebsiteTool** | Enables scraping specific elements from websites, useful for targeted data extraction.   |
-| **ScrapeWebsiteTool**       | Facilitates scraping entire websites, ideal for comprehensive data collection.                |
-| **WebsiteSearchTool**       | A RAG tool for searching website content, optimized for web data extraction.                  |
-| **XMLSearchTool**           | A RAG tool designed for searching within XML files, suitable for structured data formats.     |
-| **YoutubeChannelSearchTool**| A RAG tool for searching within YouTube channels, useful for video content analysis.          |
-| **YoutubeVideoSearchTool**  | A RAG tool aimed at searching within YouTube videos, ideal for video data extraction.         |
+| Tool                             | Description                                                                                    |
+| :------------------------------- | :--------------------------------------------------------------------------------------------- |
+| **BrowserbaseLoadTool**          | A tool for interacting with and extracting data from web browsers.                             |
+| **CodeDocsSearchTool**           | A RAG tool optimized for searching through code documentation and related technical documents. |
+| **CodeInterpreterTool**          | A tool for interpreting python code.                                                           |
+| **ComposioTool**                 | Enables use of Composio tools.                                                                 |
+| **CSVSearchTool**                | A RAG tool designed for searching within CSV files, tailored to handle structured data.        |
+| **DALL-E Tool**                  | A tool for generating images using the DALL-E API.                                             |
+| **DirectorySearchTool**          | A RAG tool for searching within directories, useful for navigating through file systems.       |
+| **DOCXSearchTool**               | A RAG tool aimed at searching within DOCX documents, ideal for processing Word files.          |
+| **DirectoryReadTool**            | Facilitates reading and processing of directory structures and their contents.                 |
+| **EXASearchTool**                | A tool designed for performing exhaustive searches across various data sources.                |
+| **FileReadTool**                 | Enables reading and extracting data from files, supporting various file formats.               |
+| **FirecrawlSearchTool**          | A tool to search webpages using Firecrawl and return the results.                              |
+| **FirecrawlCrawlWebsiteTool**    | A tool for crawling webpages using Firecrawl.                                                  |
+| **FirecrawlScrapeWebsiteTool**   | A tool for scraping webpages URL using Firecrawl and returning its contents.                   |
+| **GithubSearchTool**             | A RAG tool for searching within GitHub repositories, useful for code and documentation search. |
+| **SerperDevTool**                | A specialized tool for development purposes, with specific functionalities under development.  |
+| **TXTSearchTool**                | A RAG tool focused on searching within text (.txt) files, suitable for unstructured data.      |
+| **JSONSearchTool**               | A RAG tool designed for searching within JSON files, catering to structured data handling.     |
+| **LlamaIndexTool**               | Enables the use of LlamaIndex tools.                                                           |
+| **MDXSearchTool**                | A RAG tool tailored for searching within Markdown (MDX) files, useful for documentation.       |
+| **PDFSearchTool**                | A RAG tool aimed at searching within PDF documents, ideal for processing scanned documents.    |
+| **PGSearchTool**                 | A RAG tool optimized for searching within PostgreSQL databases, suitable for database queries. |
+| **Vision Tool**                  | A tool for generating images using the DALL-E API.                                             |
+| **RagTool**                      | A general-purpose RAG tool capable of handling various data sources and types.                 |
+| **ScrapeElementFromWebsiteTool** | Enables scraping specific elements from websites, useful for targeted data extraction.         |
+| **ScrapeWebsiteTool**            | Facilitates scraping entire websites, ideal for comprehensive data collection.                 |
+| **WebsiteSearchTool**            | A RAG tool for searching website content, optimized for web data extraction.                   |
+| **XMLSearchTool**                | A RAG tool designed for searching within XML files, suitable for structured data formats.      |
+| **YoutubeChannelSearchTool**     | A RAG tool for searching within YouTube channels, useful for video content analysis.           |
+| **YoutubeVideoSearchTool**       | A RAG tool aimed at searching within YouTube videos, ideal for video data extraction.          |
 
 ## Creating your own Tools
 
 <Tip>
-  Developers can craft `custom tools` tailored for their agent’s needs or utilize pre-built options.
+  Developers can craft `custom tools` tailored for their agent’s needs or
+  utilize pre-built options.
 </Tip>
 
-To create your own CrewAI tools you will need to install our extra tools package:
-
-```bash
-pip install 'crewai[tools]'
-```
-
-Once you do that there are two main ways for one to create a CrewAI tool:
+There are two main ways for one to create a CrewAI tool:
 
 ### Subclassing `BaseTool`
 
 ```python Code
-from crewai_tools import BaseTool
+from crewai.tools import BaseTool
+
 
 class MyCustomTool(BaseTool):
     name: str = "Name of my tool"
@@ -167,7 +164,7 @@ class MyCustomTool(BaseTool):
 ### Utilizing the `tool` Decorator
 
 ```python Code
-from crewai_tools import tool
+from crewai.tools import tool
 @tool("Name of my tool")
 def my_tool(question: str) -> str:
     """Clear description for what this tool is useful for, your agent will need this information to use it."""
@@ -178,11 +175,13 @@ def my_tool(question: str) -> str:
 ### Custom Caching Mechanism
 
 <Tip>
-  Tools can optionally implement a `cache_function` to fine-tune caching behavior. This function determines when to cache results based on specific conditions, offering granular control over caching logic.
+  Tools can optionally implement a `cache_function` to fine-tune caching
+  behavior. This function determines when to cache results based on specific
+  conditions, offering granular control over caching logic.
 </Tip>
 
 ```python Code
-from crewai_tools import tool
+from crewai.tools import tool
 
 @tool
 def multiplication_tool(first_number: int, second_number: int) -> str:
@@ -208,6 +207,6 @@ writer1 = Agent(
 
 ## Conclusion
 
-Tools are pivotal in extending the capabilities of CrewAI agents, enabling them to undertake a broad spectrum of tasks and collaborate effectively. 
-When building solutions with CrewAI, leverage both custom and existing tools to empower your agents and enhance the AI ecosystem. Consider utilizing error handling, 
-caching mechanisms, and the flexibility of tool arguments to optimize your agents' performance and capabilities.
+Tools are pivotal in extending the capabilities of CrewAI agents, enabling them to undertake a broad spectrum of tasks and collaborate effectively.
+When building solutions with CrewAI, leverage both custom and existing tools to empower your agents and enhance the AI ecosystem. Consider utilizing error handling,
+caching mechanisms, and the flexibility of tool arguments to optimize your agents' performance and capabilities.

docs/how-to/create-custom-tools.mdx

@@ -6,25 +6,17 @@ icon: hammer
 
 ## Creating and Utilizing Tools in CrewAI
 
-This guide provides detailed instructions on creating custom tools for the CrewAI framework and how to efficiently manage and utilize these tools, 
-incorporating the latest functionalities such as tool delegation, error handling, and dynamic tool calling. It also highlights the importance of collaboration tools, 
+This guide provides detailed instructions on creating custom tools for the CrewAI framework and how to efficiently manage and utilize these tools,
+incorporating the latest functionalities such as tool delegation, error handling, and dynamic tool calling. It also highlights the importance of collaboration tools,
 enabling agents to perform a wide range of actions.
 
-### Prerequisites
-
-Before creating your own tools, ensure you have the crewAI extra tools package installed:
-
-```bash
-pip install 'crewai[tools]'
-```
-
 ### Subclassing `BaseTool`
 
 To create a personalized tool, inherit from `BaseTool` and define the necessary attributes, including the `args_schema` for input validation, and the `_run` method.
 
 ```python Code
 from typing import Type
-from crewai_tools import BaseTool
+from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
 
 class MyToolInput(BaseModel):
@@ -47,7 +39,7 @@ Alternatively, you can use the tool decorator `@tool`. This approach allows you
 offering a concise and efficient way to create specialized tools tailored to your needs.
 
 ```python Code
-from crewai_tools import tool
+from crewai.tools import tool
 
 @tool("Tool Name")
 def my_simple_tool(question: str) -> str:
@@ -73,5 +65,5 @@ def my_cache_strategy(arguments: dict, result: str) -> bool:
 cached_tool.cache_function = my_cache_strategy
 ```
 
-By adhering to these guidelines and incorporating new functionalities and collaboration tools into your tool creation and management processes, 
+By adhering to these guidelines and incorporating new functionalities and collaboration tools into your tool creation and management processes,
 you can leverage the full capabilities of the CrewAI framework, enhancing both the development experience and the efficiency of your AI agents.

docs/quickstart.mdx

@@ -330,4 +330,4 @@ This will clear the crew's memory, allowing for a fresh start.
 
 ## Deploying Your Project
 
-The easiest way to deploy your crew is through [CrewAI Enterprise](https://www.crewai.com/crewaiplus), where you can deploy your crew in a few clicks.
+The easiest way to deploy your crew is through [CrewAI Enterprise](http://app.crewai.com/), where you can deploy your crew in a few clicks.

docs/tools/githubsearchtool.mdx

@@ -34,6 +34,7 @@ from crewai_tools import GithubSearchTool
 # Initialize the tool for semantic searches within a specific GitHub repository
 tool = GithubSearchTool(
 	github_repo='https://github.com/example/repo',
+	gh_token='your_github_personal_access_token',
 	content_types=['code', 'issue'] # Options: code, repo, pr, issue
 )
 
@@ -41,6 +42,7 @@ tool = GithubSearchTool(
 
 # Initialize the tool for semantic searches within a specific GitHub repository, so the agent can search any repository if it learns about during its execution
 tool = GithubSearchTool(
+	gh_token='your_github_personal_access_token',
 	content_types=['code', 'issue'] # Options: code, repo, pr, issue
 )
 ```
@@ -48,6 +50,7 @@ tool = GithubSearchTool(
 ## Arguments
 
 - `github_repo` : The URL of the GitHub repository where the search will be conducted. This is a mandatory field and specifies the target repository for your search.
+- `gh_token` : Your GitHub Personal Access Token (PAT) required for authentication. You can create one in your GitHub account settings under Developer Settings > Personal Access Tokens.
 - `content_types` : Specifies the types of content to include in your search. You must provide a list of content types from the following options: `code` for searching within the code, 
 `repo` for searching within the repository's general information, `pr` for searching within pull requests, and `issue` for searching within issues. 
 This field is mandatory and allows tailoring the search to specific content types within the GitHub repository.
@@ -77,5 +80,4 @@ tool = GithubSearchTool(
             ),
         ),
     )
-)
-```
+)

poetry.lock

@@ -1597,12 +1597,12 @@ files = [
 google-auth = ">=2.14.1,<3.0.dev0"
 googleapis-common-protos = ">=1.56.2,<2.0.dev0"
 grpcio = [
-    {version = ">=1.49.1,<2.0dev", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
     {version = ">=1.33.2,<2.0dev", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""},
+    {version = ">=1.49.1,<2.0dev", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
 ]
 grpcio-status = [
-    {version = ">=1.49.1,<2.0.dev0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
     {version = ">=1.33.2,<2.0.dev0", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""},
+    {version = ">=1.49.1,<2.0.dev0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
 ]
 proto-plus = ">=1.22.3,<2.0.0dev"
 protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.0 || >4.21.0,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<6.0.0.dev0"
@@ -4286,8 +4286,8 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
     {version = ">=1.22.4", markers = "python_version < \"3.11\""},
+    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
     {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
 ]
 python-dateutil = ">=2.8.2"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.76.9"
+version = "0.80.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<=3.13"
@@ -16,7 +16,7 @@ dependencies = [
     "opentelemetry-exporter-otlp-proto-http>=1.22.0",
     "instructor>=1.3.3",
     "regex>=2024.9.11",
-    "crewai-tools>=0.13.4",
+    "crewai-tools>=0.14.0",
     "click>=8.1.7",
     "python-dotenv>=1.0.0",
     "appdirs>=1.4.4",
@@ -27,8 +27,8 @@ dependencies = [
     "pyvis>=0.3.2",
     "uv>=0.4.25",
     "tomli-w>=1.1.0",
-    "chromadb>=0.4.24",
     "tomli>=2.0.2",
+    "chromadb>=0.5.18",
 ]
 
 [project.urls]
@@ -37,8 +37,19 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools>=0.13.4"]
+tools = ["crewai-tools>=0.14.0"]
 agentops = ["agentops>=0.3.0"]
+fastembed = ["fastembed>=0.4.1"]
+pdfplumber = [
+    "pdfplumber>=0.11.4",
+]
+pandas = [
+    "pandas>=2.2.3",
+]
+openpyxl = [
+    "openpyxl>=3.1.5",
+]
+mem0 = ["mem0ai>=0.1.29"]
 
 [tool.uv]
 dev-dependencies = [
@@ -52,7 +63,7 @@ dev-dependencies = [
     "mkdocs-material-extensions>=1.3.1",
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
-    "crewai-tools>=0.13.4",
+    "crewai-tools>=0.14.0",
     "pytest>=8.0.0",
     "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",

src/crewai/__init__.py

@@ -1,7 +1,9 @@
 import warnings
+
 from crewai.agent import Agent
 from crewai.crew import Crew
 from crewai.flow.flow import Flow
+from crewai.knowledge.knowledge import Knowledge
 from crewai.llm import LLM
 from crewai.pipeline import Pipeline
 from crewai.process import Process
@@ -14,5 +16,15 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.76.9"
-__all__ = ["Agent", "Crew", "Process", "Task", "Pipeline", "Router", "LLM", "Flow"]
+__version__ = "0.80.0"
+__all__ = [
+    "Agent",
+    "Crew",
+    "Process",
+    "Task",
+    "Pipeline",
+    "Router",
+    "LLM",
+    "Flow",
+    "Knowledge",
+]

src/crewai/agent.py

@@ -8,9 +8,11 @@ from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 from crewai.agents import CacheHandler
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
+from crewai.cli.constants import ENV_VARS
 from crewai.llm import LLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
-from crewai.tools.agent_tools import AgentTools
+from crewai.tools import BaseTool
+from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.utilities import Converter, Prompts
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.token_counter_callback import TokenCalcHandler
@@ -50,6 +52,7 @@ class Agent(BaseAgent):
             role: The role of the agent.
             goal: The objective of the agent.
             backstory: The backstory of the agent.
+            knowledge: The knowledge base of the agent.
             config: Dict representation of agent configuration.
             llm: The language model that will run the agent.
             function_calling_llm: The language model that will handle the tool calling for this agent, it overrides the crew function_calling_llm.
@@ -121,6 +124,11 @@ class Agent(BaseAgent):
     @model_validator(mode="after")
     def post_init_setup(self):
         self.agent_ops_agent_name = self.role
+        unnacepted_attributes = [
+            "AWS_ACCESS_KEY_ID",
+            "AWS_SECRET_ACCESS_KEY",
+            "AWS_REGION_NAME",
+        ]
 
         # Handle different cases for self.llm
         if isinstance(self.llm, str):
@@ -130,8 +138,12 @@ class Agent(BaseAgent):
             # If it's already an LLM instance, keep it as is
             pass
         elif self.llm is None:
-            # If it's None, use environment variables or default
-            model_name = os.environ.get("OPENAI_MODEL_NAME", "gpt-4o-mini")
+            # Determine the model name from environment variables or use default
+            model_name = (
+                os.environ.get("OPENAI_MODEL_NAME")
+                or os.environ.get("MODEL")
+                or "gpt-4o-mini"
+            )
             llm_params = {"model": model_name}
 
             api_base = os.environ.get("OPENAI_API_BASE") or os.environ.get(
@@ -140,9 +152,44 @@ class Agent(BaseAgent):
             if api_base:
                 llm_params["base_url"] = api_base
 
-            api_key = os.environ.get("OPENAI_API_KEY")
-            if api_key:
-                llm_params["api_key"] = api_key
+            set_provider = model_name.split("/")[0] if "/" in model_name else "openai"
+
+            # Iterate over all environment variables to find matching API keys or use defaults
+            for provider, env_vars in ENV_VARS.items():
+                if provider == set_provider:
+                    for env_var in env_vars:
+                        if env_var["key_name"] in unnacepted_attributes:
+                            continue
+                        # Check if the environment variable is set
+                        if "key_name" in env_var:
+                            env_value = os.environ.get(env_var["key_name"])
+                            if env_value:
+                                # Map key names containing "API_KEY" to "api_key"
+                                key_name = (
+                                    "api_key"
+                                    if "API_KEY" in env_var["key_name"]
+                                    else env_var["key_name"]
+                                )
+                                # Map key names containing "API_BASE" to "api_base"
+                                key_name = (
+                                    "api_base"
+                                    if "API_BASE" in env_var["key_name"]
+                                    else key_name
+                                )
+                                # Map key names containing "API_VERSION" to "api_version"
+                                key_name = (
+                                    "api_version"
+                                    if "API_VERSION" in env_var["key_name"]
+                                    else key_name
+                                )
+                                llm_params[key_name] = env_value
+                        # Check for default values if the environment variable is not set
+                        elif env_var.get("default", False):
+                            for key, value in env_var.items():
+                                if key not in ["prompt", "key_name", "default"]:
+                                    # Only add default if the key is already set in os.environ
+                                    if key in os.environ:
+                                        llm_params[key] = value
 
             self.llm = LLM(**llm_params)
         else:
@@ -192,7 +239,7 @@ class Agent(BaseAgent):
         self,
         task: Any,
         context: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
+        tools: Optional[List[BaseTool]] = None,
     ) -> str:
         """Execute a task with the agent.
 
@@ -216,14 +263,28 @@ class Agent(BaseAgent):
 
         if self.crew and self.crew.memory:
             contextual_memory = ContextualMemory(
+                self.crew.memory_config,
                 self.crew._short_term_memory,
                 self.crew._long_term_memory,
                 self.crew._entity_memory,
+                self.crew._user_memory,
             )
             memory = contextual_memory.build_context_for_task(task, context)
             if memory.strip() != "":
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 
+        # Integrate the knowledge base
+        if self.crew and self.crew.knowledge:
+            knowledge_snippets = self.crew.knowledge.query([task.prompt()])
+            valid_snippets = [
+                result["context"] 
+                for result in knowledge_snippets 
+                if result and result.get("context")
+            ]
+            if valid_snippets:
+                formatted_knowledge = "\n".join(valid_snippets)
+                task_prompt += f"\n\nAdditional Information:\n{formatted_knowledge}"
+
         tools = tools or self.tools or []
         self.create_agent_executor(tools=tools, task=task)
 
@@ -259,7 +320,9 @@ class Agent(BaseAgent):
 
         return result
 
-    def create_agent_executor(self, tools=None, task=None) -> None:
+    def create_agent_executor(
+        self, tools: Optional[List[BaseTool]] = None, task=None
+    ) -> None:
         """Create an agent executor for the agent.
 
         Returns:
@@ -332,7 +395,7 @@ class Agent(BaseAgent):
         tools_list = []
         try:
             # tentatively try to import from crewai_tools import BaseTool as CrewAITool
-            from crewai_tools import BaseTool as CrewAITool
+            from crewai.tools import BaseTool as CrewAITool
 
             for tool in tools:
                 if isinstance(tool, CrewAITool):
@@ -391,7 +454,7 @@ class Agent(BaseAgent):
 
         return description
 
-    def _render_text_description_and_args(self, tools: List[Any]) -> str:
+    def _render_text_description_and_args(self, tools: List[BaseTool]) -> str:
         """Render the tool name, description, and args in plain text.
 
             Output will be in the format of:
@@ -404,17 +467,7 @@ class Agent(BaseAgent):
         """
         tool_strings = []
         for tool in tools:
-            args_schema = {
-                name: {
-                    "description": field.description,
-                    "type": field.annotation.__name__,
-                }
-                for name, field in tool.args_schema.model_fields.items()
-            }
-            description = (
-                f"Tool Name: {tool.name}\nTool Description: {tool.description}"
-            )
-            tool_strings.append(f"{description}\nTool Arguments: {args_schema}")
+            tool_strings.append(tool.description)
 
         return "\n".join(tool_strings)
 

src/crewai/agents/agent_builder/base_agent.py

@@ -18,6 +18,7 @@ from pydantic_core import PydanticCustomError
 from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
 from crewai.agents.cache.cache_handler import CacheHandler
 from crewai.agents.tools_handler import ToolsHandler
+from crewai.tools import BaseTool
 from crewai.utilities import I18N, Logger, RPMController
 from crewai.utilities.config import process_config
 
@@ -49,11 +50,11 @@ class BaseAgent(ABC, BaseModel):
 
 
     Methods:
-        execute_task(task: Any, context: Optional[str] = None, tools: Optional[List[Any]] = None) -> str:
+        execute_task(task: Any, context: Optional[str] = None, tools: Optional[List[BaseTool]] = None) -> str:
             Abstract method to execute a task.
         create_agent_executor(tools=None) -> None:
             Abstract method to create an agent executor.
-        _parse_tools(tools: List[Any]) -> List[Any]:
+        _parse_tools(tools: List[BaseTool]) -> List[Any]:
             Abstract method to parse tools.
         get_delegation_tools(agents: List["BaseAgent"]):
             Abstract method to set the agents task tools for handling delegation and question asking to other agents in crew.
@@ -105,7 +106,7 @@ class BaseAgent(ABC, BaseModel):
         default=False,
         description="Enable agent to delegate and ask questions among each other.",
     )
-    tools: Optional[List[Any]] = Field(
+    tools: Optional[List[BaseTool]] = Field(
         default_factory=list, description="Tools at agents' disposal"
     )
     max_iter: Optional[int] = Field(
@@ -188,7 +189,7 @@ class BaseAgent(ABC, BaseModel):
         self,
         task: Any,
         context: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
+        tools: Optional[List[BaseTool]] = None,
     ) -> str:
         pass
 
@@ -197,11 +198,11 @@ class BaseAgent(ABC, BaseModel):
         pass
 
     @abstractmethod
-    def _parse_tools(self, tools: List[Any]) -> List[Any]:
+    def _parse_tools(self, tools: List[BaseTool]) -> List[BaseTool]:
         pass
 
     @abstractmethod
-    def get_delegation_tools(self, agents: List["BaseAgent"]) -> List[Any]:
+    def get_delegation_tools(self, agents: List["BaseAgent"]) -> List[BaseTool]:
         """Set the task tools that init BaseAgenTools class."""
         pass
 

src/crewai/agents/agent_builder/utilities/base_token_process.py

@@ -4,6 +4,7 @@ from crewai.types.usage_metrics import UsageMetrics
 class TokenProcess:
     total_tokens: int = 0
     prompt_tokens: int = 0
+    cached_prompt_tokens: int = 0
     completion_tokens: int = 0
     successful_requests: int = 0
 
@@ -15,6 +16,9 @@ class TokenProcess:
         self.completion_tokens = self.completion_tokens + tokens
         self.total_tokens = self.total_tokens + tokens
 
+    def sum_cached_prompt_tokens(self, tokens: int):
+        self.cached_prompt_tokens = self.cached_prompt_tokens + tokens
+
     def sum_successful_requests(self, requests: int):
         self.successful_requests = self.successful_requests + requests
 
@@ -22,6 +26,7 @@ class TokenProcess:
         return UsageMetrics(
             total_tokens=self.total_tokens,
             prompt_tokens=self.prompt_tokens,
+            cached_prompt_tokens=self.cached_prompt_tokens,
             completion_tokens=self.completion_tokens,
             successful_requests=self.successful_requests,
         )

src/crewai/agents/crew_agent_executor.py

@@ -117,6 +117,15 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         callbacks=self.callbacks,
                     )
 
+                    if answer is None or answer == "":
+                        self._printer.print(
+                            content="Received None or empty response from LLM call.",
+                            color="red",
+                        )
+                        raise ValueError(
+                            "Invalid response from LLM call - None or empty."
+                        )
+
                     if not self.use_stop_words:
                         try:
                             self._format_answer(answer)
@@ -136,25 +145,26 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         formatted_answer.result = action_result
                         self._show_logs(formatted_answer)
 
-                        if self.step_callback:
-                            self.step_callback(formatted_answer)
+                    if self.step_callback:
+                        self.step_callback(formatted_answer)
 
-                        if self._should_force_answer():
-                            if self.have_forced_answer:
-                                return AgentFinish(
-                                    output=self._i18n.errors(
-                                        "force_final_answer_error"
-                                    ).format(formatted_answer.text),
-                                    text=formatted_answer.text,
-                                )
-                            else:
-                                formatted_answer.text += (
-                                    f'\n{self._i18n.errors("force_final_answer")}'
-                                )
-                                self.have_forced_answer = True
-                        self.messages.append(
-                            self._format_msg(formatted_answer.text, role="assistant")
-                        )
+                    if self._should_force_answer():
+                        if self.have_forced_answer:
+                            return AgentFinish(
+                                thought="",
+                                output=self._i18n.errors(
+                                    "force_final_answer_error"
+                                ).format(formatted_answer.text),
+                                text=formatted_answer.text,
+                            )
+                        else:
+                            formatted_answer.text += (
+                                f'\n{self._i18n.errors("force_final_answer")}'
+                            )
+                            self.have_forced_answer = True
+                    self.messages.append(
+                        self._format_msg(formatted_answer.text, role="assistant")
+                    )
 
         except OutputParserException as e:
             self.messages.append({"role": "user", "content": e.error})
@@ -323,9 +333,9 @@ 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(
@@ -376,4 +386,5 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         return CrewAgentParser(agent=self.agent).parse(answer)
 
     def _format_msg(self, prompt: str, role: str = "user") -> Dict[str, str]:
+        prompt = prompt.rstrip()
         return {"role": role, "content": prompt}

src/crewai/agents/tools_handler.py

@@ -1,6 +1,6 @@
 from typing import Any, Optional, Union
 
-from ..tools.cache_tools import CacheTools
+from ..tools.cache_tools.cache_tools import CacheTools
 from ..tools.tool_calling import InstructorToolCalling, ToolCalling
 from .cache.cache_handler import CacheHandler
 

src/crewai/cli/add_crew_to_flow.py

@@ -54,7 +54,7 @@ def create_embedded_crew(crew_name: str, parent_folder: Path) -> None:
 
     templates_dir = Path(__file__).parent / "templates" / "crew"
     config_template_files = ["agents.yaml", "tasks.yaml"]
-    crew_template_file = f"{folder_name}_crew.py"  # Updated file name
+    crew_template_file = f"{folder_name}.py"  # Updated file name
 
     for file_name in config_template_files:
         src_file = templates_dir / "config" / file_name

src/crewai/cli/authentication/main.py

@@ -34,7 +34,9 @@ class AuthenticationCommand:
             "scope": "openid",
             "audience": AUTH0_AUDIENCE,
         }
-        response = requests.post(url=self.DEVICE_CODE_URL, data=device_code_payload)
+        response = requests.post(
+            url=self.DEVICE_CODE_URL, data=device_code_payload, timeout=20
+        )
         response.raise_for_status()
         return response.json()
 
@@ -54,7 +56,7 @@ class AuthenticationCommand:
 
         attempts = 0
         while True and attempts < 5:
-            response = requests.post(self.TOKEN_URL, data=token_payload)
+            response = requests.post(self.TOKEN_URL, data=token_payload, timeout=30)
             token_data = response.json()
 
             if response.status_code == 200:

src/crewai/cli/cli.py

@@ -136,6 +136,7 @@ def log_tasks_outputs() -> None:
 @click.option("-l", "--long", is_flag=True, help="Reset LONG TERM memory")
 @click.option("-s", "--short", is_flag=True, help="Reset SHORT TERM memory")
 @click.option("-e", "--entities", is_flag=True, help="Reset ENTITIES memory")
+@click.option("-kn", "--knowledge", is_flag=True, help="Reset KNOWLEDGE storage")
 @click.option(
     "-k",
     "--kickoff-outputs",
@@ -143,17 +144,24 @@ def log_tasks_outputs() -> None:
     help="Reset LATEST KICKOFF TASK OUTPUTS",
 )
 @click.option("-a", "--all", is_flag=True, help="Reset ALL memories")
-def reset_memories(long, short, entities, kickoff_outputs, all):
+def reset_memories(
+    long: bool,
+    short: bool,
+    entities: bool,
+    knowledge: bool,
+    kickoff_outputs: bool,
+    all: bool,
+) -> None:
     """
     Reset the crew memories (long, short, entity, latest_crew_kickoff_ouputs). This will delete all the data saved.
     """
     try:
-        if not all and not (long or short or entities or kickoff_outputs):
+        if not all and not (long or short or entities or knowledge or kickoff_outputs):
             click.echo(
                 "Please specify at least one memory type to reset using the appropriate flags."
             )
             return
-        reset_memories_command(long, short, entities, kickoff_outputs, all)
+        reset_memories_command(long, short, entities, knowledge, kickoff_outputs, all)
     except Exception as e:
         click.echo(f"An error occurred while resetting memories: {e}", err=True)
 

src/crewai/cli/constants.py

@@ -1,19 +1,161 @@
 ENV_VARS = {
-    'openai': ['OPENAI_API_KEY'],
-    'anthropic': ['ANTHROPIC_API_KEY'],
-    'gemini': ['GEMINI_API_KEY'],
-    'groq': ['GROQ_API_KEY'],
-    'ollama': ['FAKE_KEY'],
+    "openai": [
+        {
+            "prompt": "Enter your OPENAI API key (press Enter to skip)",
+            "key_name": "OPENAI_API_KEY",
+        }
+    ],
+    "anthropic": [
+        {
+            "prompt": "Enter your ANTHROPIC API key (press Enter to skip)",
+            "key_name": "ANTHROPIC_API_KEY",
+        }
+    ],
+    "gemini": [
+        {
+            "prompt": "Enter your GEMINI API key (press Enter to skip)",
+            "key_name": "GEMINI_API_KEY",
+        }
+    ],
+    "groq": [
+        {
+            "prompt": "Enter your GROQ API key (press Enter to skip)",
+            "key_name": "GROQ_API_KEY",
+        }
+    ],
+    "watson": [
+        {
+            "prompt": "Enter your WATSONX URL (press Enter to skip)",
+            "key_name": "WATSONX_URL",
+        },
+        {
+            "prompt": "Enter your WATSONX API Key (press Enter to skip)",
+            "key_name": "WATSONX_APIKEY",
+        },
+        {
+            "prompt": "Enter your WATSONX Project Id (press Enter to skip)",
+            "key_name": "WATSONX_PROJECT_ID",
+        },
+    ],
+    "ollama": [
+        {
+            "default": True,
+            "API_BASE": "http://localhost:11434",
+        }
+    ],
+    "bedrock": [
+        {
+            "prompt": "Enter your AWS Access Key ID (press Enter to skip)",
+            "key_name": "AWS_ACCESS_KEY_ID",
+        },
+        {
+            "prompt": "Enter your AWS Secret Access Key (press Enter to skip)",
+            "key_name": "AWS_SECRET_ACCESS_KEY",
+        },
+        {
+            "prompt": "Enter your AWS Region Name (press Enter to skip)",
+            "key_name": "AWS_REGION_NAME",
+        },
+    ],
+    "azure": [
+        {
+            "prompt": "Enter your Azure deployment name (must start with 'azure/')",
+            "key_name": "model",
+        },
+        {
+            "prompt": "Enter your AZURE API key (press Enter to skip)",
+            "key_name": "AZURE_API_KEY",
+        },
+        {
+            "prompt": "Enter your AZURE API base URL (press Enter to skip)",
+            "key_name": "AZURE_API_BASE",
+        },
+        {
+            "prompt": "Enter your AZURE API version (press Enter to skip)",
+            "key_name": "AZURE_API_VERSION",
+        },
+    ],
+    "cerebras": [
+        {
+            "prompt": "Enter your Cerebras model name (must start with 'cerebras/')",
+            "key_name": "model",
+        },
+        {
+            "prompt": "Enter your Cerebras API version (press Enter to skip)",
+            "key_name": "CEREBRAS_API_KEY",
+        },
+    ],
 }
 
-PROVIDERS = ['openai', 'anthropic', 'gemini', 'groq', 'ollama']
+
+PROVIDERS = [
+    "openai",
+    "anthropic",
+    "gemini",
+    "groq",
+    "ollama",
+    "watson",
+    "bedrock",
+    "azure",
+    "cerebras",
+]
 
 MODELS = {
-    'openai': ['gpt-4', 'gpt-4o', 'gpt-4o-mini', 'o1-mini', 'o1-preview'],
-    'anthropic': ['claude-3-5-sonnet-20240620', 'claude-3-sonnet-20240229', 'claude-3-opus-20240229', 'claude-3-haiku-20240307'],
-    'gemini': ['gemini-1.5-flash', 'gemini-1.5-pro', 'gemini-gemma-2-9b-it', 'gemini-gemma-2-27b-it'],
-    'groq': ['llama-3.1-8b-instant', 'llama-3.1-70b-versatile', 'llama-3.1-405b-reasoning', 'gemma2-9b-it', 'gemma-7b-it'],
-    'ollama': ['llama3.1', 'mixtral'],
+    "openai": ["gpt-4", "gpt-4o", "gpt-4o-mini", "o1-mini", "o1-preview"],
+    "anthropic": [
+        "claude-3-5-sonnet-20240620",
+        "claude-3-sonnet-20240229",
+        "claude-3-opus-20240229",
+        "claude-3-haiku-20240307",
+    ],
+    "gemini": [
+        "gemini/gemini-1.5-flash",
+        "gemini/gemini-1.5-pro",
+        "gemini/gemini-gemma-2-9b-it",
+        "gemini/gemini-gemma-2-27b-it",
+    ],
+    "groq": [
+        "groq/llama-3.1-8b-instant",
+        "groq/llama-3.1-70b-versatile",
+        "groq/llama-3.1-405b-reasoning",
+        "groq/gemma2-9b-it",
+        "groq/gemma-7b-it",
+    ],
+    "ollama": ["ollama/llama3.1", "ollama/mixtral"],
+    "watson": [
+        "watsonx/meta-llama/llama-3-1-70b-instruct",
+        "watsonx/meta-llama/llama-3-1-8b-instruct",
+        "watsonx/meta-llama/llama-3-2-11b-vision-instruct",
+        "watsonx/meta-llama/llama-3-2-1b-instruct",
+        "watsonx/meta-llama/llama-3-2-90b-vision-instruct",
+        "watsonx/meta-llama/llama-3-405b-instruct",
+        "watsonx/mistral/mistral-large",
+        "watsonx/ibm/granite-3-8b-instruct",
+    ],
+    "bedrock": [
+        "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0",
+        "bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
+        "bedrock/anthropic.claude-3-haiku-20240307-v1:0",
+        "bedrock/anthropic.claude-3-opus-20240229-v1:0",
+        "bedrock/anthropic.claude-v2:1",
+        "bedrock/anthropic.claude-v2",
+        "bedrock/anthropic.claude-instant-v1",
+        "bedrock/meta.llama3-1-405b-instruct-v1:0",
+        "bedrock/meta.llama3-1-70b-instruct-v1:0",
+        "bedrock/meta.llama3-1-8b-instruct-v1:0",
+        "bedrock/meta.llama3-70b-instruct-v1:0",
+        "bedrock/meta.llama3-8b-instruct-v1:0",
+        "bedrock/amazon.titan-text-lite-v1",
+        "bedrock/amazon.titan-text-express-v1",
+        "bedrock/cohere.command-text-v14",
+        "bedrock/ai21.j2-mid-v1",
+        "bedrock/ai21.j2-ultra-v1",
+        "bedrock/ai21.jamba-instruct-v1:0",
+        "bedrock/meta.llama2-13b-chat-v1",
+        "bedrock/meta.llama2-70b-chat-v1",
+        "bedrock/mistral.mistral-7b-instruct-v0:2",
+        "bedrock/mistral.mixtral-8x7b-instruct-v0:1",
+    ],
 }
 
-JSON_URL = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"
+JSON_URL = "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"

src/crewai/cli/create_crew.py

@@ -1,11 +1,11 @@
+import shutil
 import sys
 from pathlib import Path
 
 import click
 
-from crewai.cli.constants import ENV_VARS
+from crewai.cli.constants import ENV_VARS, MODELS
 from crewai.cli.provider import (
-    PROVIDERS,
     get_provider_data,
     select_model,
     select_provider,
@@ -29,20 +29,20 @@ def create_folder_structure(name, parent_folder=None):
             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",
-            bold=True,
-        )
+        shutil.rmtree(folder_path)  # Delete the existing folder and its contents
 
-    if not folder_path.exists():
-        folder_path.mkdir(parents=True)
-        (folder_path / "tests").mkdir(exist_ok=True)
-        if not parent_folder:
-            (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)
+    click.secho(
+        f"Creating {'crew' if parent_folder else 'folder'} {folder_name}...",
+        fg="green",
+        bold=True,
+    )
+
+    folder_path.mkdir(parents=True)
+    (folder_path / "tests").mkdir(exist_ok=True)
+    if not parent_folder:
+        (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)
 
     return folder_path, folder_name, class_name
 
@@ -92,7 +92,10 @@ def create_crew(name, provider=None, skip_provider=False, parent_folder=None):
 
         existing_provider = None
         for provider, env_keys in ENV_VARS.items():
-            if any(key in env_vars for key in env_keys):
+            if any(
+                "key_name" in details and details["key_name"] in env_vars
+                for details in env_keys
+            ):
                 existing_provider = provider
                 break
 
@@ -118,47 +121,48 @@ def create_crew(name, provider=None, skip_provider=False, parent_folder=None):
                 "No provider selected. Please try again or press 'q' to exit.", fg="red"
             )
 
-        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"
-            )
+        # Check if the selected provider has predefined models
+        if selected_provider in MODELS and MODELS[selected_provider]:
+            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"] = selected_model
 
-        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="",
-            )
+        # Check if the selected provider requires API keys
+        if selected_provider in ENV_VARS:
+            provider_env_vars = ENV_VARS[selected_provider]
+            for details in provider_env_vars:
+                if details.get("default", False):
+                    # Automatically add default key-value pairs
+                    for key, value in details.items():
+                        if key not in ["prompt", "key_name", "default"]:
+                            env_vars[key] = value
+                elif "key_name" in details:
+                    # Prompt for non-default key-value pairs
+                    prompt = details["prompt"]
+                    key_name = details["key_name"]
+                    api_key_value = click.prompt(prompt, default="", show_default=False)
 
-        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[key_name] = api_key_value
 
-        if api_key_value.strip():
-            env_vars = {api_key_var: api_key_value}
+        if env_vars:
             write_env_file(folder_path, env_vars)
-            click.secho("API key saved to .env file", fg="green")
+            click.secho("API keys and model saved to .env file", fg="green")
         else:
             click.secho(
-                "No API key provided. Skipping .env file creation.", fg="yellow"
+                "No API keys provided. Skipping .env file creation.", fg="yellow"
             )
 
-        env_vars["MODEL"] = selected_model
-        click.secho(f"Selected model: {selected_model}", fg="green")
+        click.secho(f"Selected model: {env_vars.get('MODEL', 'N/A')}", fg="green")
 
     package_dir = Path(__file__).parent
     templates_dir = package_dir / "templates" / "crew"

src/crewai/cli/provider.py

@@ -164,7 +164,7 @@ def fetch_provider_data(cache_file):
     - dict or None: The fetched provider data or None if the operation fails.
     """
     try:
-        response = requests.get(JSON_URL, stream=True, timeout=10)
+        response = requests.get(JSON_URL, stream=True, timeout=60)
         response.raise_for_status()
         data = download_data(response)
         with open(cache_file, "w") as f:

src/crewai/cli/reset_memories_command.py

@@ -5,9 +5,17 @@ from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
 
 
-def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
+def reset_memories_command(
+    long,
+    short,
+    entity,
+    knowledge,
+    kickoff_outputs,
+    all,
+) -> None:
     """
     Reset the crew memories.
 
@@ -17,6 +25,7 @@ def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
       entity (bool): Whether to reset the entity memory.
       kickoff_outputs (bool): Whether to reset the latest kickoff task outputs.
       all (bool): Whether to reset all memories.
+      knowledge (bool): Whether to reset the knowledge.
     """
 
     try:
@@ -25,6 +34,7 @@ def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
             EntityMemory().reset()
             LongTermMemory().reset()
             TaskOutputStorageHandler().reset()
+            KnowledgeStorage().reset()
             click.echo("All memories have been reset.")
         else:
             if long:
@@ -40,6 +50,9 @@ def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
             if kickoff_outputs:
                 TaskOutputStorageHandler().reset()
                 click.echo("Latest Kickoff outputs stored has been reset.")
+            if knowledge:
+                KnowledgeStorage().reset()
+                click.echo("Knowledge has been reset.")
 
     except subprocess.CalledProcessError as e:
         click.echo(f"An error occurred while resetting the memories: {e}", err=True)

src/crewai/cli/run_crew.py

@@ -24,7 +24,6 @@ def run_crew() -> None:
             f"Please run `crewai update` to update your pyproject.toml to use uv.",
             fg="red",
         )
-        print()
 
     try:
         subprocess.run(command, capture_output=False, text=True, check=True)

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

@@ -8,9 +8,12 @@ from crewai.project import CrewBase, agent, crew, task
 # from crewai_tools import SerperDevTool
 
 @CrewBase
-class {{crew_name}}Crew():
+class {{crew_name}}():
 	"""{{crew_name}} crew"""
 
+	agents_config = 'config/agents.yaml'
+	tasks_config = 'config/tasks.yaml'
+
 	@agent
 	def researcher(self) -> Agent:
 		return Agent(
@@ -48,4 +51,4 @@ class {{crew_name}}Crew():
 			process=Process.sequential,
 			verbose=True,
 			# process=Process.hierarchical, # In case you wanna use that instead https://docs.crewai.com/how-to/Hierarchical/
-		)
+		)

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

@@ -1,6 +1,10 @@
 #!/usr/bin/env python
 import sys
-from {{folder_name}}.crew import {{crew_name}}Crew
+import warnings
+
+from {{folder_name}}.crew import {{crew_name}}
+
+warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
 
 # This main file is intended to be a way for you to run your
 # crew locally, so refrain from adding unnecessary logic into this file.
@@ -14,7 +18,7 @@ def run():
     inputs = {
         'topic': 'AI LLMs'
     }
-    {{crew_name}}Crew().crew().kickoff(inputs=inputs)
+    {{crew_name}}().crew().kickoff(inputs=inputs)
 
 
 def train():
@@ -25,7 +29,7 @@ def train():
         "topic": "AI LLMs"
     }
     try:
-        {{crew_name}}Crew().crew().train(n_iterations=int(sys.argv[1]), filename=sys.argv[2], inputs=inputs)
+        {{crew_name}}().crew().train(n_iterations=int(sys.argv[1]), filename=sys.argv[2], inputs=inputs)
 
     except Exception as e:
         raise Exception(f"An error occurred while training the crew: {e}")
@@ -35,7 +39,7 @@ def replay():
     Replay the crew execution from a specific task.
     """
     try:
-        {{crew_name}}Crew().crew().replay(task_id=sys.argv[1])
+        {{crew_name}}().crew().replay(task_id=sys.argv[1])
 
     except Exception as e:
         raise Exception(f"An error occurred while replaying the crew: {e}")
@@ -48,7 +52,7 @@ def test():
         "topic": "AI LLMs"
     }
     try:
-        {{crew_name}}Crew().crew().test(n_iterations=int(sys.argv[1]), openai_model_name=sys.argv[2], inputs=inputs)
+        {{crew_name}}().crew().test(n_iterations=int(sys.argv[1]), openai_model_name=sys.argv[2], inputs=inputs)
 
     except Exception as e:
         raise Exception(f"An error occurred while replaying the crew: {e}")

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]>=0.76.9,<1.0.0"
+    "crewai[tools]>=0.80.0,<1.0.0"
 ]
 
 [project.scripts]

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

@@ -1,7 +1,8 @@
+from crewai.tools import BaseTool
 from typing import Type
-from crewai_tools import BaseTool
 from pydantic import BaseModel, Field
 
+
 class MyCustomToolInput(BaseModel):
     """Input schema for MyCustomTool."""
     argument: str = Field(..., description="Description of the argument.")

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]>=0.76.9,<1.0.0",
+    "crewai[tools]>=0.80.0,<1.0.0",
 ]
 
 [project.scripts]

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

@@ -1,6 +1,6 @@
 from typing import Type
 
-from crewai_tools import BaseTool
+from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
 
 

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 = ">=0.76.9,<1.0.0" }
+crewai = { extras = ["tools"], version = ">=0.80.0,<1.0.0" }
 asyncio = "*"
 
 [tool.poetry.scripts]

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

@@ -1,7 +1,8 @@
 from typing import Type
-from crewai_tools import BaseTool
+from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
 
+
 class MyCustomToolInput(BaseModel):
     """Input schema for MyCustomTool."""
     argument: str = Field(..., description="Description of the argument.")

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]>=0.76.9,<1.0.0"
+    "crewai[tools]>=0.80.0,<1.0.0"
 ]
 
 [project.scripts]

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

@@ -1,7 +1,8 @@
 from typing import Type
-from crewai_tools import BaseTool
+from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
 
+
 class MyCustomToolInput(BaseModel):
     """Input schema for MyCustomTool."""
     argument: str = Field(..., description="Description of the argument.")

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]>=0.76.9"
+    "crewai[tools]>=0.80.0"
 ]
 

src/crewai/cli/templates/tool/src/{{folder_name}}/tool.py

@@ -1,4 +1,5 @@
-from crewai_tools import BaseTool
+from crewai.tools import BaseTool
+
 
 class {{class_name}}(BaseTool):
     name: str = "Name of my tool"

src/crewai/crew.py

@@ -5,7 +5,7 @@ import uuid
 import warnings
 from concurrent.futures import Future
 from hashlib import md5
-from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Tuple, Union
 
 from pydantic import (
     UUID4,
@@ -27,17 +27,17 @@ from crewai.llm import LLM
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
+from crewai.knowledge.knowledge import Knowledge
+from crewai.memory.user.user_memory import UserMemory
 from crewai.process import Process
 from crewai.task import Task
 from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
-from crewai.tools.agent_tools import AgentTools
+from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
-from crewai.utilities.constants import (
-    TRAINING_DATA_FILE,
-)
+from crewai.utilities.constants import TRAINING_DATA_FILE
 from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.formatter import (
@@ -71,6 +71,7 @@ class Crew(BaseModel):
         manager_llm: The language model that will run manager agent.
         manager_agent: Custom agent that will be used as manager.
         memory: Whether the crew should use memory to store memories of it's execution.
+        memory_config: Configuration for the memory to be used for the crew.
         cache: Whether the crew should use a cache to store the results of the tools execution.
         function_calling_llm: The language model that will run the tool calling for all the agents.
         process: The process flow that the crew will follow (e.g., sequential, hierarchical).
@@ -94,6 +95,7 @@ class Crew(BaseModel):
     _short_term_memory: Optional[InstanceOf[ShortTermMemory]] = PrivateAttr()
     _long_term_memory: Optional[InstanceOf[LongTermMemory]] = PrivateAttr()
     _entity_memory: Optional[InstanceOf[EntityMemory]] = PrivateAttr()
+    _user_memory: Optional[InstanceOf[UserMemory]] = PrivateAttr()
     _train: Optional[bool] = PrivateAttr(default=False)
     _train_iteration: Optional[int] = PrivateAttr()
     _inputs: Optional[Dict[str, Any]] = PrivateAttr(default=None)
@@ -114,6 +116,10 @@ class Crew(BaseModel):
         default=False,
         description="Whether the crew should use memory to store memories of it's execution",
     )
+    memory_config: Optional[Dict[str, Any]] = Field(
+        default=None,
+        description="Configuration for the memory to be used for the crew.",
+    )
     short_term_memory: Optional[InstanceOf[ShortTermMemory]] = Field(
         default=None,
         description="An Instance of the ShortTermMemory to be used by the Crew",
@@ -126,7 +132,11 @@ class Crew(BaseModel):
         default=None,
         description="An Instance of the EntityMemory to be used by the Crew",
     )
-    embedder: Optional[Any] = Field(
+    user_memory: Optional[InstanceOf[UserMemory]] = Field(
+        default=None,
+        description="An instance of the UserMemory to be used by the Crew to store/fetch memories of a specific user.",
+    )
+    embedder: Optional[dict] = Field(
         default=None,
         description="Configuration for the embedder to be used for the crew.",
     )
@@ -154,6 +164,16 @@ class Crew(BaseModel):
         default=None,
         description="Callback to be executed after each task for all agents execution.",
     )
+    before_kickoff_callbacks: List[
+        Callable[[Optional[Dict[str, Any]]], Optional[Dict[str, Any]]]
+    ] = Field(
+        default_factory=list,
+        description="List of callbacks to be executed before crew kickoff. It may be used to adjust inputs before the crew is executed.",
+    )
+    after_kickoff_callbacks: List[Callable[[CrewOutput], CrewOutput]] = Field(
+        default_factory=list,
+        description="List of callbacks to be executed after crew kickoff. It may be used to adjust the output of the crew.",
+    )
     max_rpm: Optional[int] = Field(
         default=None,
         description="Maximum number of requests per minute for the crew execution to be respected.",
@@ -182,6 +202,10 @@ class Crew(BaseModel):
         default=[],
         description="List of execution logs for tasks",
     )
+    knowledge: Optional[Dict[str, Any]] = Field(
+        default=None, description="Knowledge for the crew. Add knowledge sources to the knowledge object."
+    )
+
 
     @field_validator("id", mode="before")
     @classmethod
@@ -238,13 +262,31 @@ class Crew(BaseModel):
             self._short_term_memory = (
                 self.short_term_memory
                 if self.short_term_memory
-                else ShortTermMemory(crew=self, embedder_config=self.embedder)
+                else ShortTermMemory(
+                    crew=self,
+                    embedder_config=self.embedder,
+                )
             )
             self._entity_memory = (
                 self.entity_memory
                 if self.entity_memory
                 else EntityMemory(crew=self, embedder_config=self.embedder)
             )
+            if hasattr(self, "memory_config") and self.memory_config is not None:
+                self._user_memory = (
+                    self.user_memory if self.user_memory else UserMemory(crew=self)
+                )
+            else:
+                self._user_memory = None
+        return self
+
+    @model_validator(mode="after")
+    def create_crew_knowledge(self) -> "Crew":
+        if self.knowledge:
+            try:
+                self.knowledge = Knowledge(**self.knowledge) if isinstance(self.knowledge, dict) else self.knowledge
+            except (TypeError, ValueError) as e:
+                raise ValueError(f"Invalid knowledge configuration: {str(e)}")
         return self
 
     @model_validator(mode="after")
@@ -445,18 +487,22 @@ class Crew(BaseModel):
         training_data = CrewTrainingHandler(TRAINING_DATA_FILE).load()
 
         for agent in train_crew.agents:
-            result = TaskEvaluator(agent).evaluate_training_data(
-                training_data=training_data, agent_id=str(agent.id)
-            )
+            if training_data.get(str(agent.id)):
+                result = TaskEvaluator(agent).evaluate_training_data(
+                    training_data=training_data, agent_id=str(agent.id)
+                )
 
-            CrewTrainingHandler(filename).save_trained_data(
-                agent_id=str(agent.role), trained_data=result.model_dump()
-            )
+                CrewTrainingHandler(filename).save_trained_data(
+                    agent_id=str(agent.role), trained_data=result.model_dump()
+                )
 
     def kickoff(
         self,
         inputs: Optional[Dict[str, Any]] = None,
     ) -> CrewOutput:
+        for before_callback in self.before_kickoff_callbacks:
+            inputs = before_callback(inputs)
+
         """Starts the crew to work on its assigned tasks."""
         self._execution_span = self._telemetry.crew_execution_span(self, inputs)
         self._task_output_handler.reset()
@@ -499,6 +545,9 @@ class Crew(BaseModel):
                 f"The process '{self.process}' is not implemented yet."
             )
 
+        for after_callback in self.after_kickoff_callbacks:
+            result = after_callback(result)
+
         metrics += [agent._token_process.get_summary() for agent in self.agents]
 
         self.usage_metrics = UsageMetrics()

src/crewai/flow/flow.py

@@ -1,8 +1,20 @@
 import asyncio
 import inspect
-from typing import Any, Callable, Dict, Generic, List, Set, Type, TypeVar, Union
+from typing import (
+    Any,
+    Callable,
+    Dict,
+    Generic,
+    List,
+    Optional,
+    Set,
+    Type,
+    TypeVar,
+    Union,
+    cast,
+)
 
-from pydantic import BaseModel
+from pydantic import BaseModel, ValidationError
 
 from crewai.flow.flow_visualizer import plot_flow
 from crewai.flow.utils import get_possible_return_constants
@@ -119,7 +131,6 @@ class FlowMeta(type):
                 condition_type = getattr(attr_value, "__condition_type__", "OR")
                 listeners[attr_name] = (condition_type, methods)
 
-            # TODO: should we add a check for __condition_type__ 'AND'?
             elif hasattr(attr_value, "__is_router__"):
                 routers[attr_value.__router_for__] = attr_name
                 possible_returns = get_possible_return_constants(attr_value)
@@ -159,8 +170,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
     def __init__(self) -> None:
         self._methods: Dict[str, Callable] = {}
         self._state: T = self._create_initial_state()
-        self._executed_methods: Set[str] = set()
-        self._scheduled_tasks: Set[str] = set()
+        self._method_execution_counts: Dict[str, int] = {}
         self._pending_and_listeners: Dict[str, Set[str]] = {}
         self._method_outputs: List[Any] = []  # List to store all method outputs
 
@@ -191,10 +201,74 @@ class Flow(Generic[T], metaclass=FlowMeta):
         """Returns the list of all outputs from executed methods."""
         return self._method_outputs
 
-    def kickoff(self) -> Any:
+    def _initialize_state(self, inputs: Dict[str, Any]) -> None:
+        """
+        Initializes or updates the state with the provided inputs.
+
+        Args:
+            inputs: Dictionary of inputs to initialize or update the state.
+
+        Raises:
+            ValueError: If inputs do not match the structured state model.
+            TypeError: If state is neither a BaseModel instance nor a dictionary.
+        """
+        if isinstance(self._state, BaseModel):
+            # Structured state management
+            try:
+                # Define a function to create the dynamic class
+                def create_model_with_extra_forbid(
+                    base_model: Type[BaseModel],
+                ) -> Type[BaseModel]:
+                    class ModelWithExtraForbid(base_model):  # type: ignore
+                        model_config = base_model.model_config.copy()
+                        model_config["extra"] = "forbid"
+
+                    return ModelWithExtraForbid
+
+                # Create the dynamic class
+                ModelWithExtraForbid = create_model_with_extra_forbid(
+                    self._state.__class__
+                )
+
+                # Create a new instance using the combined state and inputs
+                self._state = cast(
+                    T, ModelWithExtraForbid(**{**self._state.model_dump(), **inputs})
+                )
+
+            except ValidationError as e:
+                raise ValueError(f"Invalid inputs for structured state: {e}") from e
+        elif isinstance(self._state, dict):
+            # Unstructured state management
+            self._state.update(inputs)
+        else:
+            raise TypeError("State must be a BaseModel instance or a dictionary.")
+
+    def kickoff(self, inputs: Optional[Dict[str, Any]] = None) -> Any:
+        """
+        Starts the execution of the flow synchronously.
+
+        Args:
+            inputs: Optional dictionary of inputs to initialize or update the state.
+
+        Returns:
+            The final output from the flow execution.
+        """
+        if inputs is not None:
+            self._initialize_state(inputs)
         return asyncio.run(self.kickoff_async())
 
-    async def kickoff_async(self) -> Any:
+    async def kickoff_async(self, inputs: Optional[Dict[str, Any]] = None) -> Any:
+        """
+        Starts the execution of the flow asynchronously.
+
+        Args:
+            inputs: Optional dictionary of inputs to initialize or update the state.
+
+        Returns:
+            The final output from the flow execution.
+        """
+        if inputs is not None:
+            self._initialize_state(inputs)
         if not self._start_methods:
             raise ValueError("No start method defined")
 
@@ -233,7 +307,10 @@ class Flow(Generic[T], metaclass=FlowMeta):
         )
         self._method_outputs.append(result)  # Store the output
 
-        self._executed_methods.add(method_name)
+        # Track method execution counts
+        self._method_execution_counts[method_name] = (
+            self._method_execution_counts.get(method_name, 0) + 1
+        )
 
         return result
 
@@ -243,35 +320,34 @@ class Flow(Generic[T], metaclass=FlowMeta):
         if trigger_method in self._routers:
             router_method = self._methods[self._routers[trigger_method]]
             path = await self._execute_method(
-                trigger_method, router_method
-            )  # TODO: Change or not?
-            # Use the path as the new trigger method
+                self._routers[trigger_method], router_method
+            )
             trigger_method = path
 
         for listener_name, (condition_type, methods) in self._listeners.items():
             if condition_type == "OR":
                 if trigger_method in methods:
-                    if (
-                        listener_name not in self._executed_methods
-                        and listener_name not in self._scheduled_tasks
-                    ):
-                        self._scheduled_tasks.add(listener_name)
-                        listener_tasks.append(
-                            self._execute_single_listener(listener_name, result)
-                        )
+                    # Schedule the listener without preventing re-execution
+                    listener_tasks.append(
+                        self._execute_single_listener(listener_name, result)
+                    )
             elif condition_type == "AND":
-                if all(method in self._executed_methods for method in methods):
-                    if (
-                        listener_name not in self._executed_methods
-                        and listener_name not in self._scheduled_tasks
-                    ):
-                        self._scheduled_tasks.add(listener_name)
-                        listener_tasks.append(
-                            self._execute_single_listener(listener_name, result)
-                        )
+                # Initialize pending methods for this listener if not already done
+                if listener_name not in self._pending_and_listeners:
+                    self._pending_and_listeners[listener_name] = set(methods)
+                # Remove the trigger method from pending methods
+                self._pending_and_listeners[listener_name].discard(trigger_method)
+                if not self._pending_and_listeners[listener_name]:
+                    # All required methods have been executed
+                    listener_tasks.append(
+                        self._execute_single_listener(listener_name, result)
+                    )
+                    # Reset pending methods for this listener
+                    self._pending_and_listeners.pop(listener_name, None)
 
         # Run all listener tasks concurrently and wait for them to complete
-        await asyncio.gather(*listener_tasks)
+        if listener_tasks:
+            await asyncio.gather(*listener_tasks)
 
     async def _execute_single_listener(self, listener_name: str, result: Any) -> None:
         try:
@@ -291,9 +367,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 # If listener does not expect parameters, call without arguments
                 listener_result = await self._execute_method(listener_name, method)
 
-            # Remove from scheduled tasks after execution
-            self._scheduled_tasks.discard(listener_name)
-
             # Execute listeners of this listener
             await self._execute_listeners(listener_name, listener_result)
         except Exception as e:

src/crewai/knowledge/embedder/base_embedder.py

@@ -0,0 +1,55 @@
+from abc import ABC, abstractmethod
+from typing import List
+
+import numpy as np
+
+
+class BaseEmbedder(ABC):
+    """
+    Abstract base class for text embedding models
+    """
+
+    @abstractmethod
+    def embed_chunks(self, chunks: List[str]) -> np.ndarray:
+        """
+        Generate embeddings for a list of text chunks
+
+        Args:
+            chunks: List of text chunks to embed
+
+        Returns:
+            Array of embeddings
+        """
+        pass
+
+    @abstractmethod
+    def embed_texts(self, texts: List[str]) -> np.ndarray:
+        """
+        Generate embeddings for a list of texts
+
+        Args:
+            texts: List of texts to embed
+
+        Returns:
+            Array of embeddings
+        """
+        pass
+
+    @abstractmethod
+    def embed_text(self, text: str) -> np.ndarray:
+        """
+        Generate embedding for a single text
+
+        Args:
+            text: Text to embed
+
+        Returns:
+            Embedding array
+        """
+        pass
+
+    @property
+    @abstractmethod
+    def dimension(self) -> int:
+        """Get the dimension of the embeddings"""
+        pass

src/crewai/knowledge/embedder/fastembed.py

@@ -0,0 +1,93 @@
+from pathlib import Path
+from typing import List, Optional, Union
+
+import numpy as np
+
+from .base_embedder import BaseEmbedder
+
+try:
+    from fastembed_gpu import TextEmbedding  # type: ignore
+
+    FASTEMBED_AVAILABLE = True
+except ImportError:
+    try:
+        from fastembed import TextEmbedding
+
+        FASTEMBED_AVAILABLE = True
+    except ImportError:
+        FASTEMBED_AVAILABLE = False
+
+
+class FastEmbed(BaseEmbedder):
+    """
+    A wrapper class for text embedding models using FastEmbed
+    """
+
+    def __init__(
+        self,
+        model_name: str = "BAAI/bge-small-en-v1.5",
+        cache_dir: Optional[Union[str, Path]] = None,
+    ):
+        """
+        Initialize the embedding model
+
+        Args:
+            model_name: Name of the model to use
+            cache_dir: Directory to cache the model
+            gpu: Whether to use GPU acceleration
+        """
+        if not FASTEMBED_AVAILABLE:
+            raise ImportError(
+                "FastEmbed is not installed. Please install it with: "
+                "uv pip install fastembed or uv pip install fastembed-gpu for GPU support"
+            )
+
+        self.model = TextEmbedding(
+            model_name=model_name,
+            cache_dir=str(cache_dir) if cache_dir else None,
+        )
+
+    def embed_chunks(self, chunks: List[str]) -> List[np.ndarray]:
+        """
+        Generate embeddings for a list of text chunks
+
+        Args:
+            chunks: List of text chunks to embed
+
+        Returns:
+            List of embeddings
+        """
+        embeddings = list(self.model.embed(chunks))
+        return embeddings
+
+    def embed_texts(self, texts: List[str]) -> List[np.ndarray]:
+        """
+        Generate embeddings for a list of texts
+
+        Args:
+            texts: List of texts to embed
+
+        Returns:
+            List of embeddings
+        """
+        embeddings = list(self.model.embed(texts))
+        return embeddings
+
+    def embed_text(self, text: str) -> np.ndarray:
+        """
+        Generate embedding for a single text
+
+        Args:
+            text: Text to embed
+
+        Returns:
+            Embedding array
+        """
+        return self.embed_texts([text])[0]
+
+    @property
+    def dimension(self) -> int:
+        """Get the dimension of the embeddings"""
+        # Generate a test embedding to get dimensions
+        test_embed = self.embed_text("test")
+        return len(test_embed)

src/crewai/knowledge/knowledge.py

@@ -0,0 +1,54 @@
+import os
+
+from typing import List, Optional, Dict, Any
+from pydantic import BaseModel, ConfigDict, Field
+
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+from crewai.utilities.logger import Logger
+from crewai.utilities.constants import DEFAULT_SCORE_THRESHOLD
+os.environ["TOKENIZERS_PARALLELISM"] = "false"  # removes logging from fastembed
+
+
+class Knowledge(BaseModel):
+    """
+    Knowledge is a collection of sources and setup for the vector store to save and query relevant context.
+    Args:
+        sources: List[BaseKnowledgeSource] = Field(default_factory=list)
+        storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+        embedder_config: Optional[Dict[str, Any]] = None
+    """
+    sources: List[BaseKnowledgeSource] = Field(default_factory=list)
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    embedder_config: Optional[Dict[str, Any]] = None
+
+    def __init__(self, embedder_config: Optional[Dict[str, Any]] = None, **data):
+        super().__init__(**data)
+        self.storage = KnowledgeStorage(embedder_config=embedder_config or None)
+
+        try:
+            for source in self.sources:
+                source.add()
+        except Exception as e:
+            Logger(verbose=True).log(
+                "warning",
+                f"Failed to init knowledge: {e}",
+                color="yellow",
+            )
+
+    def query(
+        self, query: List[str], limit: int = 3, preference: Optional[str] = None
+    ) -> List[Dict[str, Any]]:
+        """
+        Query across all knowledge sources to find the most relevant information.
+        Returns the top_k most relevant chunks.
+        """
+
+        results = self.storage.search(
+            query,
+            limit,
+            filter={"preference": preference} if preference else None,
+            score_threshold=DEFAULT_SCORE_THRESHOLD,
+        )
+        return results

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -0,0 +1,36 @@
+from pathlib import Path
+from typing import Union, List
+
+from pydantic import Field
+
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from typing import Dict, Any
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+
+
+class BaseFileKnowledgeSource(BaseKnowledgeSource):
+    """Base class for knowledge sources that load content from files."""
+
+    file_path: Union[Path, List[Path]] = Field(...)
+    content: Dict[Path, str] = Field(init=False, default_factory=dict)
+    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+
+    def model_post_init(self, _):
+        """Post-initialization method to load content."""
+        self.content = self.load_content()
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess file content. Should be overridden by subclasses."""
+        paths = [self.file_path] if isinstance(self.file_path, Path) else self.file_path
+
+        for path in paths:
+            if not path.exists():
+                raise FileNotFoundError(f"File not found: {path}")
+            if not path.is_file():
+                raise ValueError(f"Path is not a file: {path}")
+        return {}
+
+    def save_documents(self, metadata: Dict[str, Any]):
+        """Save the documents to the storage."""
+        chunk_metadatas = [metadata.copy() for _ in self.chunks]
+        self.storage.save(self.chunks, chunk_metadatas)

src/crewai/knowledge/source/base_knowledge_source.py

@@ -0,0 +1,48 @@
+from abc import ABC, abstractmethod
+from typing import List, Dict, Any
+
+import numpy as np
+from pydantic import BaseModel, ConfigDict, Field
+
+from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+
+
+class BaseKnowledgeSource(BaseModel, ABC):
+    """Abstract base class for knowledge sources."""
+
+    chunk_size: int = 4000
+    chunk_overlap: int = 200
+    chunks: List[str] = Field(default_factory=list)
+    chunk_embeddings: List[np.ndarray] = Field(default_factory=list)
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    metadata: Dict[str, Any] = Field(default_factory=dict)
+
+    @abstractmethod
+    def load_content(self) -> Dict[Any, str]:
+        """Load and preprocess content from the source."""
+        pass
+
+    @abstractmethod
+    def add(self) -> None:
+        """Process content, chunk it, compute embeddings, and save them."""
+        pass
+
+    def get_embeddings(self) -> List[np.ndarray]:
+        """Return the list of embeddings for the chunks."""
+        return self.chunk_embeddings
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]
+
+    def save_documents(self, metadata: Dict[str, Any]):
+        """
+        Save the documents to the storage.
+        This method should be called after the chunks and embeddings are generated.
+        """
+        self.storage.save(self.chunks, metadata)

src/crewai/knowledge/source/csv_knowledge_source.py

@@ -0,0 +1,44 @@
+import csv
+from typing import Dict, List
+from pathlib import Path
+
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class CSVKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries CSV file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess CSV file content."""
+        super().load_content()  # Validate the file path
+
+        file_path = (
+            self.file_path[0] if isinstance(self.file_path, list) else self.file_path
+        )
+        file_path = Path(file_path) if isinstance(file_path, str) else file_path
+
+        with open(file_path, "r", encoding="utf-8") as csvfile:
+            reader = csv.reader(csvfile)
+            content = ""
+            for row in reader:
+                content += " ".join(row) + "\n"
+        return {file_path: content}
+
+    def add(self) -> None:
+        """
+        Add CSV file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        content_str = (
+            str(self.content) if isinstance(self.content, dict) else self.content
+        )
+        new_chunks = self._chunk_text(content_str)
+        self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/excel_knowledge_source.py

@@ -0,0 +1,56 @@
+from typing import Dict, List
+from pathlib import Path
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class ExcelKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries Excel file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess Excel file content."""
+        super().load_content()  # Validate the file path
+        pd = self._import_dependencies()
+
+        if isinstance(self.file_path, list):
+            file_path = self.file_path[0]
+        else:
+            file_path = self.file_path
+
+        df = pd.read_excel(file_path)
+        content = df.to_csv(index=False)
+        return {file_path: content}
+
+    def _import_dependencies(self):
+        """Dynamically import dependencies."""
+        try:
+            import openpyxl  # noqa
+            import pandas as pd
+
+            return pd
+        except ImportError as e:
+            missing_package = str(e).split()[-1]
+            raise ImportError(
+                f"{missing_package} is not installed. Please install it with: pip install {missing_package}"
+            )
+
+    def add(self) -> None:
+        """
+        Add Excel file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        # Convert dictionary values to a single string if content is a dictionary
+        if isinstance(self.content, dict):
+            content_str = "\n".join(str(value) for value in self.content.values())
+        else:
+            content_str = str(self.content)
+
+        new_chunks = self._chunk_text(content_str)
+        self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/json_knowledge_source.py

@@ -0,0 +1,54 @@
+import json
+from typing import Any, Dict, List
+from pathlib import Path
+
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class JSONKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries JSON file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess JSON file content."""
+        super().load_content()  # Validate the file path
+        paths = [self.file_path] if isinstance(self.file_path, Path) else self.file_path
+
+        content: Dict[Path, str] = {}
+        for path in paths:
+            with open(path, "r", encoding="utf-8") as json_file:
+                data = json.load(json_file)
+            content[path] = self._json_to_text(data)
+        return content
+
+    def _json_to_text(self, data: Any, level: int = 0) -> str:
+        """Recursively convert JSON data to a text representation."""
+        text = ""
+        indent = "  " * level
+        if isinstance(data, dict):
+            for key, value in data.items():
+                text += f"{indent}{key}: {self._json_to_text(value, level + 1)}\n"
+        elif isinstance(data, list):
+            for item in data:
+                text += f"{indent}- {self._json_to_text(item, level + 1)}\n"
+        else:
+            text += f"{str(data)}"
+        return text
+
+    def add(self) -> None:
+        """
+        Add JSON file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        content_str = (
+            str(self.content) if isinstance(self.content, dict) else self.content
+        )
+        new_chunks = self._chunk_text(content_str)
+        self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/pdf_knowledge_source.py

@@ -0,0 +1,54 @@
+from typing import List, Dict
+from pathlib import Path
+
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class PDFKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries PDF file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess PDF file content."""
+        super().load_content()  # Validate the file paths
+        pdfplumber = self._import_pdfplumber()
+
+        paths = [self.file_path] if isinstance(self.file_path, Path) else self.file_path
+        content = {}
+
+        for path in paths:
+            text = ""
+            with pdfplumber.open(path) as pdf:
+                for page in pdf.pages:
+                    page_text = page.extract_text()
+                    if page_text:
+                        text += page_text + "\n"
+            content[path] = text
+        return content
+
+    def _import_pdfplumber(self):
+        """Dynamically import pdfplumber."""
+        try:
+            import pdfplumber
+
+            return pdfplumber
+        except ImportError:
+            raise ImportError(
+                "pdfplumber is not installed. Please install it with: pip install pdfplumber"
+            )
+
+    def add(self) -> None:
+        """
+        Add PDF file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        for _, text in self.content.items():
+            new_chunks = self._chunk_text(text)
+            self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/string_knowledge_source.py

@@ -0,0 +1,33 @@
+from typing import List
+
+from pydantic import Field
+
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+
+
+class StringKnowledgeSource(BaseKnowledgeSource):
+    """A knowledge source that stores and queries plain text content using embeddings."""
+
+    content: str = Field(...)
+
+    def model_post_init(self, _):
+        """Post-initialization method to validate content."""
+        self.load_content()
+
+    def load_content(self):
+        """Validate string content."""
+        if not isinstance(self.content, str):
+            raise ValueError("StringKnowledgeSource only accepts string content")
+
+    def add(self) -> None:
+        """Add string content to the knowledge source, chunk it, compute embeddings, and save them."""
+        new_chunks = self._chunk_text(self.content)
+        self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/source/text_file_knowledge_source.py

@@ -0,0 +1,35 @@
+from typing import Dict, List
+from pathlib import Path
+
+from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+
+
+class TextFileKnowledgeSource(BaseFileKnowledgeSource):
+    """A knowledge source that stores and queries text file content using embeddings."""
+
+    def load_content(self) -> Dict[Path, str]:
+        """Load and preprocess text file content."""
+        super().load_content()
+        paths = [self.file_path] if isinstance(self.file_path, Path) else self.file_path
+        content = {}
+        for path in paths:
+            with path.open("r", encoding="utf-8") as f:
+                content[path] = f.read()  # type: ignore
+        return content
+
+    def add(self) -> None:
+        """
+        Add text file content to the knowledge source, chunk it, compute embeddings,
+        and save the embeddings.
+        """
+        for _, text in self.content.items():
+            new_chunks = self._chunk_text(text)
+            self.chunks.extend(new_chunks)
+        self.save_documents(metadata=self.metadata)
+
+    def _chunk_text(self, text: str) -> List[str]:
+        """Utility method to split text into chunks."""
+        return [
+            text[i : i + self.chunk_size]
+            for i in range(0, len(text), self.chunk_size - self.chunk_overlap)
+        ]

src/crewai/knowledge/storage/base_knowledge_storage.py

@@ -0,0 +1,29 @@
+from abc import ABC, abstractmethod
+from typing import Dict, Any, List, Optional
+
+
+class BaseKnowledgeStorage(ABC):
+    """Abstract base class for knowledge storage implementations."""
+
+    @abstractmethod
+    def search(
+        self,
+        query: List[str],
+        limit: int = 3,
+        filter: Optional[dict] = None,
+        score_threshold: float = 0.35,
+    ) -> List[Dict[str, Any]]:
+        """Search for documents in the knowledge base."""
+        pass
+
+    @abstractmethod
+    def save(
+        self, documents: List[str], metadata: Dict[str, Any] | List[Dict[str, Any]]
+    ) -> None:
+        """Save documents to the knowledge base."""
+        pass
+
+    @abstractmethod
+    def reset(self) -> None:
+        """Reset the knowledge base."""
+        pass

src/crewai/knowledge/storage/knowledge_storage.py

@@ -0,0 +1,132 @@
+import contextlib
+import io
+import logging
+import chromadb
+import os
+from crewai.utilities.paths import db_storage_path
+from typing import Optional, List
+from typing import Dict, Any
+from crewai.utilities import EmbeddingConfigurator
+from crewai.knowledge.storage.base_knowledge_storage import BaseKnowledgeStorage
+import hashlib
+
+
+@contextlib.contextmanager
+def suppress_logging(
+    logger_name="chromadb.segment.impl.vector.local_persistent_hnsw",
+    level=logging.ERROR,
+):
+    logger = logging.getLogger(logger_name)
+    original_level = logger.getEffectiveLevel()
+    logger.setLevel(level)
+    with (
+        contextlib.redirect_stdout(io.StringIO()),
+        contextlib.redirect_stderr(io.StringIO()),
+        contextlib.suppress(UserWarning),
+    ):
+        yield
+    logger.setLevel(original_level)
+
+
+class KnowledgeStorage(BaseKnowledgeStorage):
+    """
+    Extends Storage to handle embeddings for memory entries, improving
+    search efficiency.
+    """
+
+    collection: Optional[chromadb.Collection] = None
+
+    def __init__(self, embedder_config: Optional[Dict[str, Any]] = None):
+        self._initialize_app(embedder_config or {})
+
+    def search(
+        self,
+        query: List[str],
+        limit: int = 3,
+        filter: Optional[dict] = None,
+        score_threshold: float = 0.35,
+    ) -> List[Dict[str, Any]]:
+        with suppress_logging():
+            if self.collection:
+                fetched = self.collection.query(
+                    query_texts=query,
+                    n_results=limit,
+                    where=filter,
+                )
+                results = []
+                for i in range(len(fetched["ids"][0])):  # type: ignore
+                    result = {
+                        "id": fetched["ids"][0][i],  # type: ignore
+                        "metadata": fetched["metadatas"][0][i],  # type: ignore
+                        "context": fetched["documents"][0][i],  # type: ignore
+                        "score": fetched["distances"][0][i],  # type: ignore
+                    }
+                    if result["score"] >= score_threshold:  # type: ignore
+                        results.append(result)
+                return results
+            else:
+                raise Exception("Collection not initialized")
+
+    def _initialize_app(self, embedder_config: Optional[Dict[str, Any]] = None):
+        import chromadb
+        from chromadb.config import Settings
+
+        self._set_embedder_config(embedder_config)
+
+        chroma_client = chromadb.PersistentClient(
+            path=f"{db_storage_path()}/knowledge",
+            settings=Settings(allow_reset=True),
+        )
+
+        self.app = chroma_client
+
+        try:
+            self.collection = self.app.get_or_create_collection(name="knowledge")
+        except Exception:
+            raise Exception("Failed to create or get collection")
+
+    def reset(self):
+        if self.app:
+            self.app.reset()
+
+    def save(
+        self, documents: List[str], metadata: Dict[str, Any] | List[Dict[str, Any]]
+    ):
+        if self.collection:
+            metadatas = [metadata] if isinstance(metadata, dict) else metadata
+
+            ids = [
+                hashlib.sha256(doc.encode("utf-8")).hexdigest() for doc in documents
+            ]
+
+            self.collection.upsert(
+                documents=documents,
+                metadatas=metadatas,
+                ids=ids,
+            )
+        else:
+            raise Exception("Collection not initialized")
+
+    def _create_default_embedding_function(self):
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
+
+        return OpenAIEmbeddingFunction(
+            api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
+        )
+
+    def _set_embedder_config(
+        self, embedder_config: Optional[Dict[str, Any]] = None
+    ) -> None:
+        """Set the embedding configuration for the knowledge storage.
+
+        Args:
+            embedder_config (Optional[Dict[str, Any]]): Configuration dictionary for the embedder.
+                If None or empty, defaults to the default embedding function.
+        """
+        self.embedder_config = (
+            EmbeddingConfigurator().configure_embedder(embedder_config)
+            if embedder_config
+            else self._create_default_embedding_function()
+        )

src/crewai/llm.py

@@ -1,7 +1,10 @@
+import io
+import logging
+import sys
+import warnings
 from contextlib import contextmanager
 from typing import Any, Dict, List, Optional, Union
-import logging
-import warnings
+
 import litellm
 from litellm import get_supported_openai_params
 
@@ -9,9 +12,6 @@ from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
 
-import sys
-import io
-
 
 class FilteredStream(io.StringIO):
     def write(self, s):
@@ -118,12 +118,12 @@ class LLM:
 
         litellm.drop_params = True
         litellm.set_verbose = False
-        litellm.callbacks = callbacks
+        self.set_callbacks(callbacks)
 
     def call(self, messages: List[Dict[str, str]], callbacks: List[Any] = []) -> str:
         with suppress_warnings():
             if callbacks and len(callbacks) > 0:
-                litellm.callbacks = callbacks
+                self.set_callbacks(callbacks)
 
             try:
                 params = {
@@ -181,3 +181,15 @@ class LLM:
     def get_context_window_size(self) -> int:
         # Only using 75% of the context window size to avoid cutting the message in the middle
         return int(LLM_CONTEXT_WINDOW_SIZES.get(self.model, 8192) * 0.75)
+
+    def set_callbacks(self, callbacks: List[Any]):
+        callback_types = [type(callback) for callback in callbacks]
+        for callback in litellm.success_callback[:]:
+            if type(callback) in callback_types:
+                litellm.success_callback.remove(callback)
+
+        for callback in litellm._async_success_callback[:]:
+            if type(callback) in callback_types:
+                litellm._async_success_callback.remove(callback)
+
+        litellm.callbacks = callbacks

src/crewai/memory/__init__.py

@@ -1,5 +1,6 @@
 from .entity.entity_memory import EntityMemory
 from .long_term.long_term_memory import LongTermMemory
 from .short_term.short_term_memory import ShortTermMemory
+from .user.user_memory import UserMemory
 
-__all__ = ["EntityMemory", "LongTermMemory", "ShortTermMemory"]
+__all__ = ["UserMemory", "EntityMemory", "LongTermMemory", "ShortTermMemory"]

src/crewai/memory/contextual/contextual_memory.py

@@ -1,13 +1,25 @@
-from typing import Optional
+from typing import Optional, Dict, Any
 
-from crewai.memory import EntityMemory, LongTermMemory, ShortTermMemory
+from crewai.memory import EntityMemory, LongTermMemory, ShortTermMemory, UserMemory
 
 
 class ContextualMemory:
-    def __init__(self, stm: ShortTermMemory, ltm: LongTermMemory, em: EntityMemory):
+    def __init__(
+        self,
+        memory_config: Optional[Dict[str, Any]],
+        stm: ShortTermMemory,
+        ltm: LongTermMemory,
+        em: EntityMemory,
+        um: UserMemory,
+    ):
+        if memory_config is not None:
+            self.memory_provider = memory_config.get("provider")
+        else:
+            self.memory_provider = None
         self.stm = stm
         self.ltm = ltm
         self.em = em
+        self.um = um
 
     def build_context_for_task(self, task, context) -> str:
         """
@@ -23,6 +35,8 @@ class ContextualMemory:
         context.append(self._fetch_ltm_context(task.description))
         context.append(self._fetch_stm_context(query))
         context.append(self._fetch_entity_context(query))
+        if self.memory_provider == "mem0":
+            context.append(self._fetch_user_context(query))
         return "\n".join(filter(None, context))
 
     def _fetch_stm_context(self, query) -> str:
@@ -32,7 +46,10 @@ class ContextualMemory:
         """
         stm_results = self.stm.search(query)
         formatted_results = "\n".join(
-            [f"- {result['context']}" for result in stm_results]
+            [
+                f"- {result['memory'] if self.memory_provider == 'mem0' else result['context']}"
+                for result in stm_results
+            ]
         )
         return f"Recent Insights:\n{formatted_results}" if stm_results else ""
 
@@ -62,6 +79,26 @@ class ContextualMemory:
         """
         em_results = self.em.search(query)
         formatted_results = "\n".join(
-            [f"- {result['context']}" for result in em_results]  # type: ignore #  Invalid index type "str" for "str"; expected type "SupportsIndex | slice"
+            [
+                f"- {result['memory'] if self.memory_provider == 'mem0' else result['context']}"
+                for result in em_results
+            ]  # type: ignore #  Invalid index type "str" for "str"; expected type "SupportsIndex | slice"
         )
         return f"Entities:\n{formatted_results}" if em_results else ""
+
+    def _fetch_user_context(self, query: str) -> str:
+        """
+        Fetches and formats relevant user information from User Memory.
+        Args:
+            query (str): The search query to find relevant user memories.
+        Returns:
+            str: Formatted user memories as bullet points, or an empty string if none found.
+        """
+        user_memories = self.um.search(query)
+        if not user_memories:
+            return ""
+
+        formatted_memories = "\n".join(
+            f"- {result['memory']}" for result in user_memories
+        )
+        return f"User memories/preferences:\n{formatted_memories}"

src/crewai/memory/entity/entity_memory.py

@@ -11,21 +11,43 @@ class EntityMemory(Memory):
     """
 
     def __init__(self, crew=None, embedder_config=None, storage=None):
-        storage = (
-            storage
-            if storage
-            else RAGStorage(
-                type="entities",
-                allow_reset=True,
-                embedder_config=embedder_config,
-                crew=crew,
+        if hasattr(crew, "memory_config") and crew.memory_config is not None:
+            self.memory_provider = crew.memory_config.get("provider")
+        else:
+            self.memory_provider = None
+
+        if self.memory_provider == "mem0":
+            try:
+                from crewai.memory.storage.mem0_storage import Mem0Storage
+            except ImportError:
+                raise ImportError(
+                    "Mem0 is not installed. Please install it with `pip install mem0ai`."
+                )
+            storage = Mem0Storage(type="entities", crew=crew)
+        else:
+            storage = (
+                storage
+                if storage
+                else RAGStorage(
+                    type="entities",
+                    allow_reset=True,
+                    embedder_config=embedder_config,
+                    crew=crew,
+                )
             )
-        )
         super().__init__(storage)
 
     def save(self, item: EntityMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
         """Saves an entity item into the SQLite storage."""
-        data = f"{item.name}({item.type}): {item.description}"
+        if self.memory_provider == "mem0":
+            data = f"""
+            Remember details about the following entity:
+            Name: {item.name}
+            Type: {item.type}
+            Entity Description: {item.description}
+            """
+        else:
+            data = f"{item.name}({item.type}): {item.description}"
         super().save(data, item.metadata)
 
     def reset(self) -> None:

src/crewai/memory/memory.py

@@ -23,5 +23,12 @@ class Memory:
 
         self.storage.save(value, metadata)
 
-    def search(self, query: str) -> List[Dict[str, Any]]:
-        return self.storage.search(query)
+    def search(
+        self,
+        query: str,
+        limit: int = 3,
+        score_threshold: float = 0.35,
+    ) -> List[Any]:
+        return self.storage.search(
+            query=query, limit=limit, score_threshold=score_threshold
+        )

src/crewai/memory/short_term/short_term_memory.py

@@ -14,13 +14,27 @@ class ShortTermMemory(Memory):
     """
 
     def __init__(self, crew=None, embedder_config=None, storage=None):
-        storage = (
-            storage
-            if storage
-            else RAGStorage(
-                type="short_term", embedder_config=embedder_config, crew=crew
+        if hasattr(crew, "memory_config") and crew.memory_config is not None:
+            self.memory_provider = crew.memory_config.get("provider")
+        else:
+            self.memory_provider = None
+
+        if self.memory_provider == "mem0":
+            try:
+                from crewai.memory.storage.mem0_storage import Mem0Storage
+            except ImportError:
+                raise ImportError(
+                    "Mem0 is not installed. Please install it with `pip install mem0ai`."
+                )
+            storage = Mem0Storage(type="short_term", crew=crew)
+        else:
+            storage = (
+                storage
+                if storage
+                else RAGStorage(
+                    type="short_term", embedder_config=embedder_config, crew=crew
+                )
             )
-        )
         super().__init__(storage)
 
     def save(
@@ -30,11 +44,20 @@ class ShortTermMemory(Memory):
         agent: Optional[str] = None,
     ) -> None:
         item = ShortTermMemoryItem(data=value, metadata=metadata, agent=agent)
+        if self.memory_provider == "mem0":
+            item.data = f"Remember the following insights from Agent run: {item.data}"
 
         super().save(value=item.data, metadata=item.metadata, agent=item.agent)
 
-    def search(self, query: str, score_threshold: float = 0.35):
-        return self.storage.search(query=query, score_threshold=score_threshold)  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
+    def search(
+        self,
+        query: str,
+        limit: int = 3,
+        score_threshold: float = 0.35,
+    ):
+        return self.storage.search(
+            query=query, limit=limit, score_threshold=score_threshold
+        )  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
 
     def reset(self) -> None:
         try:

src/crewai/memory/storage/interface.py

@@ -7,8 +7,10 @@ class Storage:
     def save(self, value: Any, metadata: Dict[str, Any]) -> None:
         pass
 
-    def search(self, key: str) -> List[Dict[str, Any]]:  # type: ignore
-        pass
+    def search(
+        self, query: str, limit: int, score_threshold: float
+    ) -> Dict[str, Any] | List[Any]:
+        return {}
 
     def reset(self) -> None:
         pass

src/crewai/memory/storage/kickoff_task_outputs_storage.py

@@ -103,7 +103,7 @@ class KickoffTaskOutputsSQLiteStorage:
                         else value
                     )
 
-                query = f"UPDATE latest_kickoff_task_outputs SET {', '.join(fields)} WHERE task_index = ?"
+                query = f"UPDATE latest_kickoff_task_outputs SET {', '.join(fields)} WHERE task_index = ?"  # nosec
                 values.append(task_index)
 
                 cursor.execute(query, tuple(values))

src/crewai/memory/storage/ltm_sqlite_storage.py

@@ -83,7 +83,7 @@ class LTMSQLiteStorage:
                     WHERE task_description = ?
                     ORDER BY datetime DESC, score ASC
                     LIMIT {latest_n}
-                """,
+                """,  # nosec
                     (task_description,),
                 )
                 rows = cursor.fetchall()

src/crewai/memory/storage/mem0_storage.py

@@ -0,0 +1,104 @@
+import os
+from typing import Any, Dict, List
+
+from mem0 import MemoryClient
+from crewai.memory.storage.interface import Storage
+
+
+class Mem0Storage(Storage):
+    """
+    Extends Storage to handle embedding and searching across entities using Mem0.
+    """
+
+    def __init__(self, type, crew=None):
+        super().__init__()
+
+        if type not in ["user", "short_term", "long_term", "entities"]:
+            raise ValueError("Invalid type for Mem0Storage. Must be 'user' or 'agent'.")
+
+        self.memory_type = type
+        self.crew = crew
+        self.memory_config = crew.memory_config
+
+        # User ID is required for user memory type "user" since it's used as a unique identifier for the user.
+        user_id = self._get_user_id()
+        if type == "user" and not user_id:
+            raise ValueError("User ID is required for user memory type")
+
+        # API key in memory config overrides the environment variable
+        mem0_api_key = self.memory_config.get("config", {}).get("api_key") or os.getenv(
+            "MEM0_API_KEY"
+        )
+        self.memory = MemoryClient(api_key=mem0_api_key)
+
+    def _sanitize_role(self, role: str) -> str:
+        """
+        Sanitizes agent roles to ensure valid directory names.
+        """
+        return role.replace("\n", "").replace(" ", "_").replace("/", "_")
+
+    def save(self, value: Any, metadata: Dict[str, Any]) -> None:
+        user_id = self._get_user_id()
+        agent_name = self._get_agent_name()
+        if self.memory_type == "user":
+            self.memory.add(value, user_id=user_id, metadata={**metadata})
+        elif self.memory_type == "short_term":
+            agent_name = self._get_agent_name()
+            self.memory.add(
+                value, agent_id=agent_name, metadata={"type": "short_term", **metadata}
+            )
+        elif self.memory_type == "long_term":
+            agent_name = self._get_agent_name()
+            self.memory.add(
+                value,
+                agent_id=agent_name,
+                infer=False,
+                metadata={"type": "long_term", **metadata},
+            )
+        elif self.memory_type == "entities":
+            entity_name = None
+            self.memory.add(
+                value, user_id=entity_name, metadata={"type": "entity", **metadata}
+            )
+
+    def search(
+        self,
+        query: str,
+        limit: int = 3,
+        score_threshold: float = 0.35,
+    ) -> List[Any]:
+        params = {"query": query, "limit": limit}
+        if self.memory_type == "user":
+            user_id = self._get_user_id()
+            params["user_id"] = user_id
+        elif self.memory_type == "short_term":
+            agent_name = self._get_agent_name()
+            params["agent_id"] = agent_name
+            params["metadata"] = {"type": "short_term"}
+        elif self.memory_type == "long_term":
+            agent_name = self._get_agent_name()
+            params["agent_id"] = agent_name
+            params["metadata"] = {"type": "long_term"}
+        elif self.memory_type == "entities":
+            agent_name = self._get_agent_name()
+            params["agent_id"] = agent_name
+            params["metadata"] = {"type": "entity"}
+
+        # Discard the filters for now since we create the filters
+        # automatically when the crew is created.
+        results = self.memory.search(**params)
+        return [r for r in results if r["score"] >= score_threshold]
+
+    def _get_user_id(self):
+        if self.memory_type == "user":
+            if hasattr(self, "memory_config") and self.memory_config is not None:
+                return self.memory_config.get("config", {}).get("user_id")
+            else:
+                return None
+        return None
+
+    def _get_agent_name(self):
+        agents = self.crew.agents if self.crew else []
+        agents = [self._sanitize_role(agent.role) for agent in agents]
+        agents = "_".join(agents)
+        return agents

src/crewai/memory/storage/rag_storage.py

@@ -4,13 +4,12 @@ import logging
 import os
 import shutil
 import uuid
+
 from typing import Any, Dict, List, Optional
+from chromadb.api import ClientAPI
 from crewai.memory.storage.base_rag_storage import BaseRAGStorage
 from crewai.utilities.paths import db_storage_path
-from chromadb.api import ClientAPI
-from chromadb.api.types import validate_embedding_function
-from chromadb import Documents, EmbeddingFunction, Embeddings
-from typing import cast
+from crewai.utilities import EmbeddingConfigurator
 
 
 @contextlib.contextmanager
@@ -21,9 +20,11 @@ def suppress_logging(
     logger = logging.getLogger(logger_name)
     original_level = logger.getEffectiveLevel()
     logger.setLevel(level)
-    with contextlib.redirect_stdout(io.StringIO()), contextlib.redirect_stderr(
-        io.StringIO()
-    ), contextlib.suppress(UserWarning):
+    with (
+        contextlib.redirect_stdout(io.StringIO()),
+        contextlib.redirect_stderr(io.StringIO()),
+        contextlib.suppress(UserWarning),
+    ):
         yield
     logger.setLevel(original_level)
 
@@ -49,77 +50,8 @@ class RAGStorage(BaseRAGStorage):
         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
+        configurator = EmbeddingConfigurator()
+        self.embedder_config = configurator.configure_embedder(self.embedder_config)
 
     def _initialize_app(self):
         import chromadb
@@ -211,8 +143,10 @@ class RAGStorage(BaseRAGStorage):
                 )
 
     def _create_default_embedding_function(self):
-        import chromadb.utils.embedding_functions as embedding_functions
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
 
-        return embedding_functions.OpenAIEmbeddingFunction(
+        return OpenAIEmbeddingFunction(
             api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
         )

src/crewai/memory/user/user_memory.py

@@ -0,0 +1,45 @@
+from typing import Any, Dict, Optional
+
+from crewai.memory.memory import Memory
+
+
+class UserMemory(Memory):
+    """
+    UserMemory class for handling user memory storage and retrieval.
+    Inherits from the Memory class and utilizes an instance of a class that
+    adheres to the Storage for data storage, specifically working with
+    MemoryItem instances.
+    """
+
+    def __init__(self, crew=None):
+        try:
+            from crewai.memory.storage.mem0_storage import Mem0Storage
+        except ImportError:
+            raise ImportError(
+                "Mem0 is not installed. Please install it with `pip install mem0ai`."
+            )
+        storage = Mem0Storage(type="user", crew=crew)
+        super().__init__(storage)
+
+    def save(
+        self,
+        value,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent: Optional[str] = None,
+    ) -> None:
+        # TODO: Change this function since we want to take care of the case where we save memories for the usr
+        data = f"Remember the details about the user: {value}"
+        super().save(data, metadata)
+
+    def search(
+        self,
+        query: str,
+        limit: int = 3,
+        score_threshold: float = 0.35,
+    ):
+        results = super().search(
+            query=query,
+            limit=limit,
+            score_threshold=score_threshold,
+        )
+        return results

src/crewai/memory/user/user_memory_item.py

@@ -0,0 +1,8 @@
+from typing import Any, Dict, Optional
+
+
+class UserMemoryItem:
+    def __init__(self, data: Any, user: str, metadata: Optional[Dict[str, Any]] = None):
+        self.data = data
+        self.user = user
+        self.metadata = metadata if metadata is not None else {}

src/crewai/project/__init__.py

@@ -1,5 +1,7 @@
 from .annotations import (
+    after_kickoff,
     agent,
+    before_kickoff,
     cache_handler,
     callback,
     crew,
@@ -26,4 +28,6 @@ __all__ = [
     "llm",
     "cache_handler",
     "pipeline",
+    "before_kickoff",
+    "after_kickoff",
 ]

src/crewai/project/annotations.py

@@ -5,6 +5,16 @@ from crewai import Crew
 from crewai.project.utils import memoize
 
 
+def before_kickoff(func):
+    func.is_before_kickoff = True
+    return func
+
+
+def after_kickoff(func):
+    func.is_after_kickoff = True
+    return func
+
+
 def task(func):
     func.is_task = True
 
@@ -99,6 +109,19 @@ def crew(func) -> Callable[..., Crew]:
         self.agents = instantiated_agents
         self.tasks = instantiated_tasks
 
-        return func(self, *args, **kwargs)
+        crew = func(self, *args, **kwargs)
 
-    return wrapper
+        def callback_wrapper(callback, instance):
+            def wrapper(*args, **kwargs):
+                return callback(instance, *args, **kwargs)
+
+            return wrapper
+
+        for _, callback in self._before_kickoff.items():
+            crew.before_kickoff_callbacks.append(callback_wrapper(callback, self))
+        for _, callback in self._after_kickoff.items():
+            crew.after_kickoff_callbacks.append(callback_wrapper(callback, self))
+
+        return crew
+
+    return memoize(wrapper)

src/crewai/project/crew_base.py

@@ -34,18 +34,39 @@ def CrewBase(cls: T) -> T:
             self.map_all_agent_variables()
             self.map_all_task_variables()
 
-            # Preserve task and agent information
-            self._original_tasks = {
+            # Preserve all decorated functions
+            self._original_functions = {
                 name: method
                 for name, method in cls.__dict__.items()
-                if hasattr(method, "is_task") and method.is_task
-            }
-            self._original_agents = {
-                name: method
-                for name, method in cls.__dict__.items()
-                if hasattr(method, "is_agent") and method.is_agent
+                if any(
+                    hasattr(method, attr)
+                    for attr in [
+                        "is_task",
+                        "is_agent",
+                        "is_before_kickoff",
+                        "is_after_kickoff",
+                        "is_kickoff",
+                    ]
+                )
             }
 
+            # Store specific function types
+            self._original_tasks = self._filter_functions(
+                self._original_functions, "is_task"
+            )
+            self._original_agents = self._filter_functions(
+                self._original_functions, "is_agent"
+            )
+            self._before_kickoff = self._filter_functions(
+                self._original_functions, "is_before_kickoff"
+            )
+            self._after_kickoff = self._filter_functions(
+                self._original_functions, "is_after_kickoff"
+            )
+            self._kickoff = self._filter_functions(
+                self._original_functions, "is_kickoff"
+            )
+
         @staticmethod
         def load_yaml(config_path: Path):
             try:

src/crewai/task.py

@@ -20,6 +20,7 @@ from pydantic import (
 from pydantic_core import PydanticCustomError
 
 from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.tools.base_tool import BaseTool
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry.telemetry import Telemetry
@@ -91,7 +92,7 @@ class Task(BaseModel):
     output: Optional[TaskOutput] = Field(
         description="Task output, it's final result after being executed", default=None
     )
-    tools: Optional[List[Any]] = Field(
+    tools: Optional[List[BaseTool]] = Field(
         default_factory=list,
         description="Tools the agent is limited to use for this task.",
     )
@@ -185,7 +186,7 @@ class Task(BaseModel):
         self,
         agent: Optional[BaseAgent] = None,
         context: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
+        tools: Optional[List[BaseTool]] = None,
     ) -> TaskOutput:
         """Execute the task synchronously."""
         return self._execute_core(agent, context, tools)
@@ -202,7 +203,7 @@ class Task(BaseModel):
         self,
         agent: BaseAgent | None = None,
         context: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
+        tools: Optional[List[BaseTool]] = None,
     ) -> Future[TaskOutput]:
         """Execute the task asynchronously."""
         future: Future[TaskOutput] = Future()

src/crewai/tools/__init__.py

@@ -0,0 +1 @@
+from .base_tool import BaseTool, tool

src/crewai/tools/agent_tools.py

@@ -1,25 +0,0 @@
-from crewai.agents.agent_builder.utilities.base_agent_tool import BaseAgentTools
-
-
-class AgentTools(BaseAgentTools):
-    """Default tools around agent delegation"""
-
-    def tools(self):
-        from langchain.tools import StructuredTool
-
-        coworkers = ", ".join([f"{agent.role}" for agent in self.agents])
-        tools = [
-            StructuredTool.from_function(
-                func=self.delegate_work,
-                name="Delegate work to coworker",
-                description=self.i18n.tools("delegate_work").format(
-                    coworkers=coworkers
-                ),
-            ),
-            StructuredTool.from_function(
-                func=self.ask_question,
-                name="Ask question to coworker",
-                description=self.i18n.tools("ask_question").format(coworkers=coworkers),
-            ),
-        ]
-        return tools

src/crewai/tools/agent_tools/agent_tools.py

@@ -0,0 +1,32 @@
+from crewai.tools.base_tool import BaseTool
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.utilities import I18N
+
+from .delegate_work_tool import DelegateWorkTool
+from .ask_question_tool import AskQuestionTool
+
+
+class AgentTools:
+    """Manager class for agent-related tools"""
+
+    def __init__(self, agents: list[BaseAgent], i18n: I18N = I18N()):
+        self.agents = agents
+        self.i18n = i18n
+
+    def tools(self) -> list[BaseTool]:
+        """Get all available agent tools"""
+        coworkers = ", ".join([f"{agent.role}" for agent in self.agents])
+
+        delegate_tool = DelegateWorkTool(
+            agents=self.agents,
+            i18n=self.i18n,
+            description=self.i18n.tools("delegate_work").format(coworkers=coworkers),
+        )
+
+        ask_tool = AskQuestionTool(
+            agents=self.agents,
+            i18n=self.i18n,
+            description=self.i18n.tools("ask_question").format(coworkers=coworkers),
+        )
+
+        return [delegate_tool, ask_tool]

src/crewai/tools/agent_tools/ask_question_tool.py

@@ -0,0 +1,26 @@
+from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
+from typing import Optional
+from pydantic import BaseModel, Field
+
+
+class AskQuestionToolSchema(BaseModel):
+    question: str = Field(..., description="The question to ask")
+    context: str = Field(..., description="The context for the question")
+    coworker: str = Field(..., description="The role/name of the coworker to ask")
+
+
+class AskQuestionTool(BaseAgentTool):
+    """Tool for asking questions to coworkers"""
+
+    name: str = "Ask question to coworker"
+    args_schema: type[BaseModel] = AskQuestionToolSchema
+
+    def _run(
+        self,
+        question: str,
+        context: str,
+        coworker: Optional[str] = None,
+        **kwargs,
+    ) -> str:
+        coworker = self._get_coworker(coworker, **kwargs)
+        return self._execute(coworker, question, context)

src/crewai/tools/agent_tools/base_agent_tools.py

@@ -1,22 +1,19 @@
-from abc import ABC, abstractmethod
-from typing import List, Optional, Union
-
-from pydantic import BaseModel, Field
+from typing import Optional, Union
+from pydantic import Field
 
+from crewai.tools.base_tool import BaseTool
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.task import Task
 from crewai.utilities import I18N
 
 
-class BaseAgentTools(BaseModel, ABC):
-    """Default tools around agent delegation"""
+class BaseAgentTool(BaseTool):
+    """Base class for agent-related tools"""
 
-    agents: List[BaseAgent] = Field(description="List of agents in this crew.")
-    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
-
-    @abstractmethod
-    def tools(self):
-        pass
+    agents: list[BaseAgent] = Field(description="List of available agents")
+    i18n: I18N = Field(
+        default_factory=I18N, description="Internationalization settings"
+    )
 
     def _get_coworker(self, coworker: Optional[str], **kwargs) -> Optional[str]:
         coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
@@ -24,27 +21,11 @@ class BaseAgentTools(BaseModel, ABC):
             is_list = coworker.startswith("[") and coworker.endswith("]")
             if is_list:
                 coworker = coworker[1:-1].split(",")[0]
-
         return coworker
 
-    def delegate_work(
-        self, task: str, context: str, coworker: Optional[str] = None, **kwargs
-    ):
-        """Useful to delegate a specific task to a coworker passing all necessary context and names."""
-        coworker = self._get_coworker(coworker, **kwargs)
-        return self._execute(coworker, task, context)
-
-    def ask_question(
-        self, question: str, context: str, coworker: Optional[str] = None, **kwargs
-    ):
-        """Useful to ask a question, opinion or take from a coworker passing all necessary context and names."""
-        coworker = self._get_coworker(coworker, **kwargs)
-        return self._execute(coworker, question, context)
-
     def _execute(
         self, agent_name: Union[str, None], task: str, context: Union[str, None]
-    ):
-        """Execute the command."""
+    ) -> str:
         try:
             if agent_name is None:
                 agent_name = ""
@@ -57,7 +38,6 @@ class BaseAgentTools(BaseModel, ABC):
             # when it should look like this:
             # {"task": "....", "coworker": "...."}
             agent_name = agent_name.casefold().replace('"', "").replace("\n", "")
-
             agent = [  # type: ignore # Incompatible types in assignment (expression has type "list[BaseAgent]", variable has type "str | None")
                 available_agent
                 for available_agent in self.agents

src/crewai/tools/agent_tools/delegate_work_tool.py

@@ -0,0 +1,29 @@
+from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class DelegateWorkToolSchema(BaseModel):
+    task: str = Field(..., description="The task to delegate")
+    context: str = Field(..., description="The context for the task")
+    coworker: str = Field(
+        ..., description="The role/name of the coworker to delegate to"
+    )
+
+
+class DelegateWorkTool(BaseAgentTool):
+    """Tool for delegating work to coworkers"""
+
+    name: str = "Delegate work to coworker"
+    args_schema: type[BaseModel] = DelegateWorkToolSchema
+
+    def _run(
+        self,
+        task: str,
+        context: str,
+        coworker: Optional[str] = None,
+        **kwargs,
+    ) -> str:
+        coworker = self._get_coworker(coworker, **kwargs)
+        return self._execute(coworker, task, context)

src/crewai/tools/base_tool.py

@@ -0,0 +1,186 @@
+from abc import ABC, abstractmethod
+from typing import Any, Callable, Type, get_args, get_origin
+
+from langchain_core.tools import StructuredTool
+from pydantic import BaseModel, ConfigDict, Field, validator
+from pydantic import BaseModel as PydanticBaseModel
+
+
+class BaseTool(BaseModel, ABC):
+    class _ArgsSchemaPlaceholder(PydanticBaseModel):
+        pass
+
+    model_config = ConfigDict()
+
+    name: str
+    """The unique name of the tool that clearly communicates its purpose."""
+    description: str
+    """Used to tell the model how/when/why to use the tool."""
+    args_schema: Type[PydanticBaseModel] = Field(default_factory=_ArgsSchemaPlaceholder)
+    """The schema for the arguments that the tool accepts."""
+    description_updated: bool = False
+    """Flag to check if the description has been updated."""
+    cache_function: Callable = lambda _args=None, _result=None: True
+    """Function that will be used to determine if the tool should be cached, should return a boolean. If None, the tool will be cached."""
+    result_as_answer: bool = False
+    """Flag to check if the tool should be the final agent answer."""
+
+    @validator("args_schema", always=True, pre=True)
+    def _default_args_schema(
+        cls, v: Type[PydanticBaseModel]
+    ) -> Type[PydanticBaseModel]:
+        if not isinstance(v, cls._ArgsSchemaPlaceholder):
+            return v
+
+        return type(
+            f"{cls.__name__}Schema",
+            (PydanticBaseModel,),
+            {
+                "__annotations__": {
+                    k: v for k, v in cls._run.__annotations__.items() if k != "return"
+                },
+            },
+        )
+
+    def model_post_init(self, __context: Any) -> None:
+        self._generate_description()
+
+        super().model_post_init(__context)
+
+    def run(
+        self,
+        *args: Any,
+        **kwargs: Any,
+    ) -> Any:
+        print(f"Using Tool: {self.name}")
+        return self._run(*args, **kwargs)
+
+    @abstractmethod
+    def _run(
+        self,
+        *args: Any,
+        **kwargs: Any,
+    ) -> Any:
+        """Here goes the actual implementation of the tool."""
+
+    def to_langchain(self) -> StructuredTool:
+        self._set_args_schema()
+        return StructuredTool(
+            name=self.name,
+            description=self.description,
+            args_schema=self.args_schema,
+            func=self._run,
+        )
+
+    @classmethod
+    def from_langchain(cls, tool: StructuredTool) -> "BaseTool":
+        if cls == Tool:
+            if tool.func is None:
+                raise ValueError("StructuredTool must have a callable 'func'")
+            return Tool(
+                name=tool.name,
+                description=tool.description,
+                args_schema=tool.args_schema,
+                func=tool.func,
+            )
+        raise NotImplementedError(f"from_langchain not implemented for {cls.__name__}")
+
+    def _set_args_schema(self):
+        if self.args_schema is None:
+            class_name = f"{self.__class__.__name__}Schema"
+            self.args_schema = type(
+                class_name,
+                (PydanticBaseModel,),
+                {
+                    "__annotations__": {
+                        k: v
+                        for k, v in self._run.__annotations__.items()
+                        if k != "return"
+                    },
+                },
+            )
+
+    def _generate_description(self):
+        args_schema = {
+            name: {
+                "description": field.description,
+                "type": BaseTool._get_arg_annotations(field.annotation),
+            }
+            for name, field in self.args_schema.model_fields.items()
+        }
+
+        self.description = f"Tool Name: {self.name}\nTool Arguments: {args_schema}\nTool Description: {self.description}"
+
+    @staticmethod
+    def _get_arg_annotations(annotation: type[Any] | None) -> str:
+        if annotation is None:
+            return "None"
+
+        origin = get_origin(annotation)
+        args = get_args(annotation)
+
+        if origin is None:
+            return (
+                annotation.__name__
+                if hasattr(annotation, "__name__")
+                else str(annotation)
+            )
+
+        if args:
+            args_str = ", ".join(BaseTool._get_arg_annotations(arg) for arg in args)
+            return f"{origin.__name__}[{args_str}]"
+
+        return origin.__name__
+
+
+class Tool(BaseTool):
+    func: Callable
+    """The function that will be executed when the tool is called."""
+
+    def _run(self, *args: Any, **kwargs: Any) -> Any:
+        return self.func(*args, **kwargs)
+
+
+def to_langchain(
+    tools: list[BaseTool | StructuredTool],
+) -> list[StructuredTool]:
+    return [t.to_langchain() if isinstance(t, BaseTool) else t for t in tools]
+
+
+def tool(*args):
+    """
+    Decorator to create a tool from a function.
+    """
+
+    def _make_with_name(tool_name: str) -> Callable:
+        def _make_tool(f: Callable) -> BaseTool:
+            if f.__doc__ is None:
+                raise ValueError("Function must have a docstring")
+            if f.__annotations__ is None:
+                raise ValueError("Function must have type annotations")
+
+            class_name = "".join(tool_name.split()).title()
+            args_schema = type(
+                class_name,
+                (PydanticBaseModel,),
+                {
+                    "__annotations__": {
+                        k: v for k, v in f.__annotations__.items() if k != "return"
+                    },
+                },
+            )
+
+            return Tool(
+                name=tool_name,
+                description=f.__doc__,
+                func=f,
+                args_schema=args_schema,
+            )
+
+        return _make_tool
+
+    if len(args) == 1 and callable(args[0]):
+        return _make_with_name(args[0].__name__)(args[0])
+    if len(args) == 1 and isinstance(args[0], str):
+        return _make_with_name(args[0])
+    raise ValueError("Invalid arguments")

src/crewai/tools/tool_usage.py

@@ -10,6 +10,7 @@ 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 import BaseTool
 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
@@ -49,7 +50,7 @@ class ToolUsage:
     def __init__(
         self,
         tools_handler: ToolsHandler,
-        tools: List[Any],
+        tools: List[BaseTool],
         original_tools: List[Any],
         tools_description: str,
         tools_names: str,
@@ -298,22 +299,7 @@ class ToolUsage:
         """Render the tool name and description in plain text."""
         descriptions = []
         for tool in self.tools:
-            args = {
-                name: {
-                    "description": field.description,
-                    "type": field.annotation.__name__,
-                }
-                for name, field in tool.args_schema.model_fields.items()
-            }
-            descriptions.append(
-                "\n".join(
-                    [
-                        f"Tool Name: {tool.name.lower()}",
-                        f"Tool Description: {tool.description}",
-                        f"Tool Arguments: {args}",
-                    ]
-                )
-            )
+            descriptions.append(tool.description)
         return "\n--\n".join(descriptions)
 
     def _function_calling(self, tool_string: str):

src/crewai/types/usage_metrics.py

@@ -8,6 +8,7 @@ class UsageMetrics(BaseModel):
     Attributes:
         total_tokens: Total number of tokens used.
         prompt_tokens: Number of tokens used in prompts.
+        cached_prompt_tokens: Number of cached prompt tokens used.
         completion_tokens: Number of tokens used in completions.
         successful_requests: Number of successful requests made.
     """
@@ -16,6 +17,9 @@ class UsageMetrics(BaseModel):
     prompt_tokens: int = Field(
         default=0, description="Number of tokens used in prompts."
     )
+    cached_prompt_tokens: int = Field(
+        default=0, description="Number of cached prompt tokens used."
+    )
     completion_tokens: int = Field(
         default=0, description="Number of tokens used in completions."
     )
@@ -32,5 +36,6 @@ class UsageMetrics(BaseModel):
         """
         self.total_tokens += usage_metrics.total_tokens
         self.prompt_tokens += usage_metrics.prompt_tokens
+        self.cached_prompt_tokens += usage_metrics.cached_prompt_tokens
         self.completion_tokens += usage_metrics.completion_tokens
         self.successful_requests += usage_metrics.successful_requests

src/crewai/utilities/__init__.py

@@ -10,6 +10,7 @@ from .rpm_controller import RPMController
 from .exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
+from .embedding_configurator import EmbeddingConfigurator
 
 __all__ = [
     "Converter",
@@ -23,4 +24,5 @@ __all__ = [
     "RPMController",
     "YamlParser",
     "LLMContextLengthExceededException",
+    "EmbeddingConfigurator",
 ]

src/crewai/utilities/constants.py

@@ -1,2 +1,3 @@
 TRAINING_DATA_FILE = "training_data.pkl"
 TRAINED_AGENTS_DATA_FILE = "trained_agents_data.pkl"
+DEFAULT_SCORE_THRESHOLD = 0.35

src/crewai/utilities/embedding_configurator.py

@@ -0,0 +1,183 @@
+import os
+from typing import Any, Dict, cast
+from chromadb import EmbeddingFunction, Documents, Embeddings
+from chromadb.api.types import validate_embedding_function
+
+
+class EmbeddingConfigurator:
+    def __init__(self):
+        self.embedding_functions = {
+            "openai": self._configure_openai,
+            "azure": self._configure_azure,
+            "ollama": self._configure_ollama,
+            "vertexai": self._configure_vertexai,
+            "google": self._configure_google,
+            "cohere": self._configure_cohere,
+            "bedrock": self._configure_bedrock,
+            "huggingface": self._configure_huggingface,
+            "watson": self._configure_watson,
+        }
+
+    def configure_embedder(
+        self,
+        embedder_config: Dict[str, Any] | None = None,
+    ) -> EmbeddingFunction:
+        """Configures and returns an embedding function based on the provided config."""
+        if embedder_config is None:
+            return self._create_default_embedding_function()
+
+        provider = embedder_config.get("provider")
+        config = embedder_config.get("config", {})
+        model_name = config.get("model")
+
+        if isinstance(provider, EmbeddingFunction):
+            try:
+                validate_embedding_function(provider)
+                return provider
+            except Exception as e:
+                raise ValueError(f"Invalid custom embedding function: {str(e)}")
+
+        if provider not in self.embedding_functions:
+            raise Exception(
+                f"Unsupported embedding provider: {provider}, supported providers: {list(self.embedding_functions.keys())}"
+            )
+
+        return self.embedding_functions[provider](config, model_name)
+
+    @staticmethod
+    def _create_default_embedding_function():
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
+
+        return OpenAIEmbeddingFunction(
+            api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small"
+        )
+
+    @staticmethod
+    def _configure_openai(config, model_name):
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
+
+        return OpenAIEmbeddingFunction(
+            api_key=config.get("api_key") or os.getenv("OPENAI_API_KEY"),
+            model_name=model_name,
+        )
+
+    @staticmethod
+    def _configure_azure(config, model_name):
+        from chromadb.utils.embedding_functions.openai_embedding_function import (
+            OpenAIEmbeddingFunction,
+        )
+
+        return 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,
+        )
+
+    @staticmethod
+    def _configure_ollama(config, model_name):
+        from chromadb.utils.embedding_functions.ollama_embedding_function import (
+            OllamaEmbeddingFunction,
+        )
+
+        return OllamaEmbeddingFunction(
+            url=config.get("url", "http://localhost:11434/api/embeddings"),
+            model_name=model_name,
+        )
+
+    @staticmethod
+    def _configure_vertexai(config, model_name):
+        from chromadb.utils.embedding_functions.google_embedding_function import (
+            GoogleVertexEmbeddingFunction,
+        )
+
+        return GoogleVertexEmbeddingFunction(
+            model_name=model_name,
+            api_key=config.get("api_key"),
+        )
+
+    @staticmethod
+    def _configure_google(config, model_name):
+        from chromadb.utils.embedding_functions.google_embedding_function import (
+            GoogleGenerativeAiEmbeddingFunction,
+        )
+
+        return GoogleGenerativeAiEmbeddingFunction(
+            model_name=model_name,
+            api_key=config.get("api_key"),
+        )
+
+    @staticmethod
+    def _configure_cohere(config, model_name):
+        from chromadb.utils.embedding_functions.cohere_embedding_function import (
+            CohereEmbeddingFunction,
+        )
+
+        return CohereEmbeddingFunction(
+            model_name=model_name,
+            api_key=config.get("api_key"),
+        )
+
+    @staticmethod
+    def _configure_bedrock(config, model_name):
+        from chromadb.utils.embedding_functions.amazon_bedrock_embedding_function import (
+            AmazonBedrockEmbeddingFunction,
+        )
+
+        return AmazonBedrockEmbeddingFunction(
+            session=config.get("session"),
+        )
+
+    @staticmethod
+    def _configure_huggingface(config, model_name):
+        from chromadb.utils.embedding_functions.huggingface_embedding_function import (
+            HuggingFaceEmbeddingServer,
+        )
+
+        return HuggingFaceEmbeddingServer(
+            url=config.get("api_url"),
+        )
+
+    @staticmethod
+    def _configure_watson(config, model_name):
+        try:
+            import ibm_watsonx_ai.foundation_models as watson_models
+            from ibm_watsonx_ai import Credentials
+            from ibm_watsonx_ai.metanames import EmbedTextParamsMetaNames as EmbedParams
+        except ImportError as e:
+            raise ImportError(
+                "IBM Watson dependencies are not installed. Please install them to use Watson embedding."
+            ) from e
+
+        class WatsonEmbeddingFunction(EmbeddingFunction):
+            def __call__(self, input: Documents) -> Embeddings:
+                if isinstance(input, str):
+                    input = [input]
+
+                embed_params = {
+                    EmbedParams.TRUNCATE_INPUT_TOKENS: 3,
+                    EmbedParams.RETURN_OPTIONS: {"input_text": True},
+                }
+
+                embedding = watson_models.Embeddings(
+                    model_id=config.get("model"),
+                    params=embed_params,
+                    credentials=Credentials(
+                        api_key=config.get("api_key"), url=config.get("api_url")
+                    ),
+                    project_id=config.get("project_id"),
+                )
+
+                try:
+                    embeddings = embedding.embed_documents(input)
+                    return cast(Embeddings, embeddings)
+                except Exception as e:
+                    print("Error during Watson embedding:", e)
+                    raise e
+
+        return WatsonEmbeddingFunction()

src/crewai/utilities/file_handler.py

@@ -16,7 +16,11 @@ class FileHandler:
 
     def log(self, **kwargs):
         now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-        message = f"{now}: " + ", ".join([f"{key}=\"{value}\"" for key, value in kwargs.items()]) + "\n"
+        message = (
+            f"{now}: "
+            + ", ".join([f'{key}="{value}"' for key, value in kwargs.items()])
+            + "\n"
+        )
         with open(self._path, "a", encoding="utf-8") as file:
             file.write(message + "\n")
 
@@ -63,7 +67,7 @@ class PickleHandler:
 
         with open(self.file_path, "rb") as file:
             try:
-                return pickle.load(file)
+                return pickle.load(file)  # nosec
             except EOFError:
                 return {}  # Return an empty dictionary if the file is empty or corrupted
             except Exception:

src/crewai/utilities/token_counter_callback.py

@@ -1,5 +1,5 @@
 from litellm.integrations.custom_logger import CustomLogger
-
+from litellm.types.utils import Usage
 from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
 
 
@@ -11,8 +11,11 @@ class TokenCalcHandler(CustomLogger):
         if self.token_cost_process is None:
             return
 
+        usage : Usage = response_obj["usage"]
         self.token_cost_process.sum_successful_requests(1)
-        self.token_cost_process.sum_prompt_tokens(response_obj["usage"].prompt_tokens)
-        self.token_cost_process.sum_completion_tokens(
-            response_obj["usage"].completion_tokens
-        )
+        self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens)
+        self.token_cost_process.sum_completion_tokens(usage.completion_tokens)
+        if usage.prompt_tokens_details:
+            self.token_cost_process.sum_cached_prompt_tokens(
+                usage.prompt_tokens_details.cached_tokens
+            )

tests/agent_test.py

@@ -5,13 +5,14 @@ from unittest import mock
 from unittest.mock import patch
 
 import pytest
-from crewai_tools import tool
 
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.agents.parser import AgentAction, CrewAgentParser, OutputParserException
+from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
+from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.tools.tool_usage_events import ToolUsageFinished
@@ -277,9 +278,10 @@ def test_cache_hitting():
         "multiplier-{'first_number': 12, 'second_number': 3}": 36,
     }
 
-    with patch.object(CacheHandler, "read") as read, patch.object(
-        Emitter, "emit"
-    ) as emit:
+    with (
+        patch.object(CacheHandler, "read") as read,
+        patch.object(Emitter, "emit") as emit,
+    ):
         read.return_value = "0"
         task = Task(
             description="What is 2 times 6? Ignore correctness and just return the result of the multiplication tool, you must use the tool.",
@@ -604,7 +606,7 @@ def test_agent_respect_the_max_rpm_set(capsys):
 def test_agent_respect_the_max_rpm_set_over_crew_rpm(capsys):
     from unittest.mock import patch
 
-    from crewai_tools import tool
+    from crewai.tools import tool
 
     @tool
     def get_final_answer() -> float:
@@ -642,7 +644,7 @@ def test_agent_respect_the_max_rpm_set_over_crew_rpm(capsys):
 def test_agent_without_max_rpm_respet_crew_rpm(capsys):
     from unittest.mock import patch
 
-    from crewai_tools import tool
+    from crewai.tools import tool
 
     @tool
     def get_final_answer() -> float:
@@ -696,7 +698,7 @@ def test_agent_without_max_rpm_respet_crew_rpm(capsys):
 def test_agent_error_on_parsing_tool(capsys):
     from unittest.mock import patch
 
-    from crewai_tools import tool
+    from crewai.tools import tool
 
     @tool
     def get_final_answer() -> float:
@@ -739,7 +741,7 @@ def test_agent_error_on_parsing_tool(capsys):
 def test_agent_remembers_output_format_after_using_tools_too_many_times():
     from unittest.mock import patch
 
-    from crewai_tools import tool
+    from crewai.tools import tool
 
     @tool
     def get_final_answer() -> float:
@@ -863,11 +865,16 @@ def test_agent_function_calling_llm():
 
     from crewai.tools.tool_usage import ToolUsage
 
-    with patch.object(
-        instructor, "from_litellm", wraps=instructor.from_litellm
-    ) as mock_from_litellm, patch.object(
-        ToolUsage, "_original_tool_calling", side_effect=Exception("Forced exception")
-    ) as mock_original_tool_calling:
+    with (
+        patch.object(
+            instructor, "from_litellm", wraps=instructor.from_litellm
+        ) as mock_from_litellm,
+        patch.object(
+            ToolUsage,
+            "_original_tool_calling",
+            side_effect=Exception("Forced exception"),
+        ) as mock_original_tool_calling,
+    ):
         crew.kickoff()
         mock_from_litellm.assert_called()
         mock_original_tool_calling.assert_called()
@@ -894,7 +901,7 @@ def test_agent_count_formatting_error():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_tool_result_as_answer_is_the_final_answer_for_the_agent():
-    from crewai_tools import BaseTool
+    from crewai.tools import BaseTool
 
     class MyCustomTool(BaseTool):
         name: str = "Get Greetings"
@@ -924,7 +931,7 @@ def test_tool_result_as_answer_is_the_final_answer_for_the_agent():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_tool_usage_information_is_appended_to_agent():
-    from crewai_tools import BaseTool
+    from crewai.tools import BaseTool
 
     class MyCustomTool(BaseTool):
         name: str = "Decide Greetings"
@@ -1568,3 +1575,42 @@ def test_agent_execute_task_with_ollama():
     result = agent.execute_task(task)
     assert len(result.split(".")) == 2
     assert "AI" in result or "artificial intelligence" in result.lower()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_with_knowledge_sources():
+    # Create a knowledge source with some content
+    content = "Brandon's favorite color is blue and he likes Mexican food."
+    string_source = StringKnowledgeSource(
+        content=content, metadata={"preference": "personal"}
+    )
+    
+
+    with patch('crewai.knowledge.storage.knowledge_storage.KnowledgeStorage') as MockKnowledge:
+        mock_knowledge_instance = MockKnowledge.return_value
+        mock_knowledge_instance.sources = [string_source]
+        mock_knowledge_instance.query.return_value = [{
+            "content": content,
+            "metadata": {"preference": "personal"}
+        }]
+        
+        agent = Agent(
+            role="Information Agent",
+            goal="Provide information based on knowledge sources",
+            backstory="You have access to specific knowledge sources.",
+            llm=LLM(model="gpt-4o-mini"),
+        )
+
+        # Create a task that requires the agent to use the knowledge
+        task = Task(
+            description="What is Brandon's favorite color?",
+            expected_output="Brandon's favorite color.",
+            agent=agent,
+        )
+
+        crew = Crew(agents=[agent], tasks=[task])
+        result = crew.kickoff()
+
+        # Assert that the agent provides the correct information
+        assert "blue" in result.raw.lower()
+

tests/agents/agent_builder/base_agent_test.py

@@ -2,6 +2,7 @@ import hashlib
 from typing import Any, List, Optional
 
 from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.tools.base_tool import BaseTool
 from pydantic import BaseModel
 
 
@@ -10,13 +11,13 @@ class TestAgent(BaseAgent):
         self,
         task: Any,
         context: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
+        tools: Optional[List[BaseTool]] = None,
     ) -> str:
         return ""
 
     def create_agent_executor(self, tools=None) -> None: ...
 
-    def _parse_tools(self, tools: List[Any]) -> List[Any]:
+    def _parse_tools(self, tools: List[BaseTool]) -> List[BaseTool]:
         return []
 
     def get_delegation_tools(self, agents: List["BaseAgent"]): ...

tests/cassettes/test_after_crew_modification.yaml

@@ -0,0 +1,449 @@
+interactions:
+- request:
+    body: !!binary |
+      CuMOCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSug4KEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKSDAoQK+dPhrB8w3HKFlxX60XzYRIIk5aB+A8oCWQqDENyZXcgQ3JlYXRlZDABObix
+      K+HWrwgYQcBiMeHWrwgYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODAuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZjM0NmE5YWQ2ZDczMDYzZTA2NzdiMTdjZTlj
+      NTAxNzdKMQoHY3Jld19pZBImCiQ3NjRjZWM1YS04NzkxLTRmN2MtOWY0MC1hNTMzMzJmOTk3YzBK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAkobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSqwFCgtjcmV3
+      X2FnZW50cxKcBQqZBVt7ImtleSI6ICI3M2MzNDljOTNjMTYzYjVkNGRmOThhNjRmYWMxYzQzMCIs
+      ICJpZCI6ICJjZDgwYjlhNy1hN2QzLTQzNTQtYjUyOC1jMzAyODA0MjA3YzgiLCAicm9sZSI6ICJ7
+      dG9waWN9IFNlbmlvciBEYXRhIFJlc2VhcmNoZXJcbiIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4
+      X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwg
+      ImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29k
+      ZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMi
+      OiBbXX0sIHsia2V5IjogImJiMDY4Mzc3YzE2NDFiZTZkN2Q5N2E1MTY1OWRiNjEzIiwgImlkIjog
+      ImJmZjc3YmUyLWU4MjQtNGEyOS1hZTFlLTQyMWFjMzc2MjY2YyIsICJyb2xlIjogInt0b3BpY30g
+      UmVwb3J0aW5nIEFuYWx5c3RcbiIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwg
+      Im1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQt
+      NG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/
+      IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSpMECgpj
+      cmV3X3Rhc2tzEoQECoEEW3sia2V5IjogIjZhZmM0YjM5NjI1OWZiYjc2ODFmNTZjNzc1NWNjOTM3
+      IiwgImlkIjogIjRmNTFlYzM2LTVlMDctNGU4Ni1iYzIxLWU1MTQ0Mzg2YmIyYSIsICJhc3luY19l
+      eGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAi
+      e3RvcGljfSBTZW5pb3IgRGF0YSBSZXNlYXJjaGVyXG4iLCAiYWdlbnRfa2V5IjogIjczYzM0OWM5
+      M2MxNjNiNWQ0ZGY5OGE2NGZhYzFjNDMwIiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICJi
+      MTdiMTg4ZGJmMTRmOTNhOThlNWI5NWFhZDM2NzU3NyIsICJpZCI6ICIwMGJmZDY5ZC03OWZiLTRj
+      MjctYTM0Yi02NzBkZWJlMzU0NWYiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5f
+      aW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInt0b3BpY30gUmVwb3J0aW5nIEFuYWx5c3Rc
+      biIsICJhZ2VudF9rZXkiOiAiYmIwNjgzNzdjMTY0MWJlNmQ3ZDk3YTUxNjU5ZGI2MTMiLCAidG9v
+      bHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQsN5cQC9ZzBr2B0OKBR2WCxII3ULL7Wk965Yq
+      DFRhc2sgQ3JlYXRlZDABOWB9ROHWrwgYQfg0ReHWrwgYSi4KCGNyZXdfa2V5EiIKIGYzNDZhOWFk
+      NmQ3MzA2M2UwNjc3YjE3Y2U5YzUwMTc3SjEKB2NyZXdfaWQSJgokNzY0Y2VjNWEtODc5MS00Zjdj
+      LTlmNDAtYTUzMzMyZjk5N2MwSi4KCHRhc2tfa2V5EiIKIDZhZmM0YjM5NjI1OWZiYjc2ODFmNTZj
+      Nzc1NWNjOTM3SjEKB3Rhc2tfaWQSJgokNGY1MWVjMzYtNWUwNy00ZTg2LWJjMjEtZTUxNDQzODZi
+      YjJhegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1894'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sun, 17 Nov 2024 07:09:57 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are LLMs Senior Data Researcher\n.
+      You''re a seasoned researcher with a knack for uncovering the latest developments
+      in LLMs. Known for your ability to find the most relevant information and present
+      it in a clear and concise manner.\n\nYour personal goal is: Uncover cutting-edge
+      developments in LLMs\n\nTo give my best complete final answer to the task use
+      the exact following format:\n\nThought: I now can give a great answer\nFinal
+      Answer: Your final answer must be the great and the most complete as possible,
+      it must be outcome described.\n\nI MUST use these formats, my job depends on
+      it!"}, {"role": "user", "content": "\nCurrent Task: Conduct a thorough research
+      about LLMs Make sure you find any interesting and relevant information given
+      the current year is 2024.\n\n\nThis is the expect criteria for your final answer:
+      A list with 10 bullet points of the most relevant information about LLMs\n\nyou
+      MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1235'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=08pKRcLhS1PDw0mYfL2jz19ac6M.T31GoiMuI5DlX6w-1731827382-1.0.1.1-UfOLu3AaIUuXP1sGzdV6oggJ1q7iMTC46t08FDhYVrKcW5YmD4CbifudOJiSgx8h0JLTwZdgk.aG05S0eAO_PQ;
+        _cfuvid=74kaPOoAcp8YRSA0XocQ1FFNksu9V0_KiWdQfo7wQuQ-1731827382509-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA2RXwW4cOQ69z1cQffFMUG04iWeS8a2xmcn2wkYMr4MFdnNhS6wqTlRSjSh1pz0/
+        vyBVbfdmL4atkijq8b1H+q8fAFbsVzewciMWN81hvfn8OP75+fDu3+Ufh08fNuHvzPt//sHxbvzX
+        08dVpyfS7g9y5XTq0qVpDlQ4xfbZZcJCGvX1u7ev37959/bXa/swJU9Bjw1zWV+n9ZurN9frq/fr
+        q1+Wg2NiR7K6gf/8AADwl/3UFKOnb6sbuOpOKxOJ4ECrm+dNAKucgq6sUISlYCyr7uWjS7FQtKwf
+        x1SHsdzAFmI6gMMIA+8JEAZNHTDKgTLAl/g7Rwywsb9v4Ev8El9fwqtXn2aKm+2FwMf7x/U1PFAg
+        FPKvXt1A+wR5WWo7OjiM7Eboay4jZeBpzmlPApbUt1IxQI2esmbtOQ6A0cNAkTIqruBwxh0HLkxy
+        CdsCqe8pC3BUsPUedK5mdMcODH7eczl2FsalkTJFR8ARMsmcotjV04yZPJQEXATmTJ4ciaQsHUz4
+        VdNgBQNIhGJhDFBSCtCnDLsqHHVdOiBfHRY7pvd52lNIM2W5VMDeKGAfUxoCKWA0cWS4UyYoXNsI
+        yoIO2g4IWKMbNauRTpuNNh30yemlA6QIE+VBfw0Yh4oDfYfegcsIUw2Fp+QxfAff48jSglrp55z0
+        2aCF6ACr59QewhMOJCCskTBSqhKOHVAcMbqGjgDOc2BnVdJyQM8UvEDgrwR7pTM8s1FeompGeoTj
+        YCC9VZA2sYw5zewuBP4WsHpShNpvHeyO8LyhAxbwJDzEVsA5c8pc+IlAsKdytKuojOz0+SkK+4VL
+        luXt7R1UFZCS6UJgVzkUDaSATxpmxDz1NUCqZa5L6jtGZc6caY+BYtFIhDkw5ZdKGLDSgacpRSl6
+        qfIZZORerzhg9nLiIe8CwWYLnuaQjhPFYnBcKxx3VPBCTFBwn2ldMrI+9zFjlD7liTL8+On+8Sd4
+        e3mlSOkBGFEfWHLy1ZGHT/eP+rmDXUKxTKjv2bFmbwEtuXnOCd1IAmXEAiGp/FUgtRhmhqEUURkH
+        ggk5luXsyMMIM2VNCKMjpdcCAtA3R8HwLppzaFouKF8bnprrjlya1HrmNNeAGZoJmsjQoaeJnaJF
+        mN0IvtJJr2mmuEZn1J1TYHc06H5W6G5PxTCdwQeWwmG5fuP3mqcoYg/kFAhcljTTlrk/P1HIjZH/
+        rCQwotpkUIDOha45tRKCTBgC5Q6mlOkM7O/4oSImP5AGUc83yaZaIKaCu3A09HOa2BR/hm8H9G1e
+        ZK4e0RBgU3dj/ZkiIfVK9eVhO62d7timx9O9htkvitnvHGn9WOOzf9zyxIU8fMCCC73G5MUq0+vm
+        0jbbBXYiLCc8GhH3dDJ6r66Bu6DbXZWSJn5qCWqwyE4fcm4kJzT0hZHI2749SrHYQuVkY0sNVDlG
+        J2WFZpBSq0pzzBMGMpNjDPxEHjj6KiWzOri5VaABg+EzkTffEHJq64bRO8Xot8VQdJPJUDtILKrg
+        z2JupWZuiQhRVNXzELlnh7EATfOIwq32S6TNtmvYpTxgXFARIFEWsIyavdk6Zm9p9xknOqT8tRVC
+        jaw8Z+IWBjiXaizN8o+XcKdUtH4XmQQwE6BPs9nBnNEVY6CBsNk+dwa1KeU1iwtJ6Hn9pZV0reIt
+        56X5aekl1Xzi1nvFTS3hgYWUj/c5TXOB3+LAkShzHBS3jZyEsRiCyWcRpu+0SekpejllKJM2Qu3+
+        AgguV2dN+qRXQ0jfOfGTnmgvWBx9IRDHfQo6irR2YngrS3p2wHGuZbl6scahsqfGp5LgqM3OTuog
+        kUlqKNJBGauctckqSyWUgssYtkwpKbYRxTRBGYSyytKQ+1WR28ZCwzIEGU82dVCyk4cHQg2q6N1+
+        Zy7cpgqr9DIicRzCEXZkfXsJSn6J+dAwSyENShBrqGmvL82EYV14ohcDO/PyDvacbXo7a/IcgaeJ
+        suhISXHPOUVNeWGIXm6c0682ObUGo6OVDlMxsxtP7laF8oWo5VFmm+Es4Zex0TSx2T7fv2D3+krB
+        e6ChBp3MjvDhxSfM+T+mPeWWFhxSDv6gr1W85pyGrJaqKSzd2sw3NBLlFtRkijnV6F+mif8d0kwL
+        c+a9jaVCrubnofRsNHGUo7GRhM79TAB50lroRDNUzN7gODVhii7VjEMraEz7RhKOCsdzOVtTbLHn
+        xBo1Ux/INW91tagLrK0VLWpb7o4eSqboW/8eqU12quCAeaD/a2g/qih+UiWmfplpdTYIPIxlKSdn
+        GHI6tIz7UK2gdtF4ztMG4rlL6p7FqDCcD0vn/+Dk/wIAAP//jJdBDsIgEEX3nIKwdqO20csYgjBU
+        IgKB6cJF726AprSxJm7nD5/5LMg80GMSma/caO1cnxZisn4I0d/TrC91bZxJD57v9i7TUUIfWFEn
+        QumtkNm4gS1WvwSO/gkuG57Ol+rHGgs2ta/4RylDj8I24Xo+HnYMuQIUxqYV3DGZ1zPVjjYSLAv7
+        SiCr2N/j7HnX6MYN/9g3QUoICIpncDJyG7m1Rcis/KtteeYyMEvvhPDi2rgBYoim4qoOvOul7jsF
+        AhiZyAcAAP//AwCidyXxtw8AAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e3de5de7b6c6217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 17 Nov 2024 07:10:00 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '6026'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999713'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_553f04a622d026a28dd3c5da55568fcd
+    status:
+      code: 200
+      message: OK
+- request:
+    body: !!binary |
+      Cs4CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpQIKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKOAgoQIn+FuHJydyMnR3y/Qfb8GBII2zXFs4gynEgqDFRhc2sgQ3JlYXRlZDABOShs
+      9ljYrwgYQQiP+FjYrwgYSi4KCGNyZXdfa2V5EiIKIGYzNDZhOWFkNmQ3MzA2M2UwNjc3YjE3Y2U5
+      YzUwMTc3SjEKB2NyZXdfaWQSJgokNzY0Y2VjNWEtODc5MS00ZjdjLTlmNDAtYTUzMzMyZjk5N2Mw
+      Si4KCHRhc2tfa2V5EiIKIGIxN2IxODhkYmYxNGY5M2E5OGU1Yjk1YWFkMzY3NTc3SjEKB3Rhc2tf
+      aWQSJgokMDBiZmQ2OWQtNzlmYi00YzI3LWEzNGItNjcwZGViZTM1NDVmegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '337'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sun, 17 Nov 2024 07:10:01 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are LLMs Reporting Analyst\n.
+      You''re a meticulous analyst with a keen eye for detail. You''re known for your
+      ability to turn complex data into clear and concise reports, making it easy
+      for others to understand and act on the information you provide.\nYour personal
+      goal is: Create detailed reports based on LLMs data analysis and research findings\n\nTo
+      give my best complete final answer to the task use the exact following format:\n\nThought:
+      I now can give a great answer\nFinal Answer: Your final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
+      Task: Review the context you got and expand each topic into a full section for
+      a report. Make sure the report is detailed and contains any and all relevant
+      information.\n\n\nThis is the expect criteria for your final answer: A fully
+      fledge reports with the mains topics, each with a full section of information.
+      Formatted as markdown without ''```''\n\nyou MUST return the actual complete
+      content as the final answer, not a summary.\n\nThis is the context you''re working
+      with:\n1. **OpenAI''s GPT-4 Released**: OpenAI released GPT-4, which further
+      improves contextual understanding and generation capabilities. It offers increased
+      accuracy, creativity, and coherence in responses compared to its predecessors,
+      making it an essential tool for businesses, educators, and developers.\n\n2.
+      **Google''s Gemini Model**: In 2024, Google launched the Gemini model, focusing
+      on merging language understanding with multimodal capabilities. This model can
+      process text, audio, and images simultaneously, enhancing its applications in
+      fields like voice assistants and image captioning.\n\n3. **Anthropic''s Claude**:
+      Claude, by Anthropic, is designed to prioritize safety and ethical considerations
+      in LLM usage. It''s built to minimize harmful outputs and biases prevalent in
+      earlier language models, demonstrating a shift towards responsible AI deployment.\n\n4.
+      **Meta''s Open Pre-trained Transformer (OPT) 3.0**: Meta has introduced OPT
+      3.0, boasting efficient training approaches that lower computational costs while
+      maintaining high performance. The model excels in translation tasks and has
+      become a popular choice for academic research due to its open-access policy.\n\n5.
+      **Language Model Distillation Advances**: Recent advances in model distillation
+      techniques have allowed developers to deploy smaller, more efficient language
+      models on edge devices without notably compromising performance, expanding the
+      accessibility and application of LLMs in mobile and IoT devices.\n\n6. **Fine-Tuning
+      with Limited Data**: Methods for fine-tuning LLMs with limited data have improved,
+      enabling customization for niche applications without the need for vast datasets.
+      This development has opened doors to using LLMs in specialized industries, like
+      legal and medical sectors.\n\n7. **Ethical and Transparent AI Use**: 2024 has
+      seen a significant emphasis on ethical AI, with organizations establishing standardized
+      frameworks for LLM transparency and accountability. More companies are adopting
+      practices like AI model cards to disclose model capabilities, limitations, and
+      data sources.\n\n8. **The Rise of Prompt Engineering**: As models become more
+      advanced, prompt engineering has emerged as a crucial technique for optimizing
+      model outputs. This involves designing specific input prompts that guide LLMs
+      to yield desired results, thus enhancing usability in content creation and customer
+      service.\n\n9. **Integration with Augmented Reality**: Language models in 2024
+      are increasingly being integrated with AR technologies to provide real-time
+      language translation, virtual assistants in immersive environments, and interactive
+      educational tools, enriching the user''s experience with contextualized AI assistance.\n\n10.
+      **Regulatory Developments**: Governments worldwide are progressing towards formalizing
+      regulations around LLM usage, focusing on data privacy, security, and ethical
+      concerns. These developments aim to safeguard users while encouraging innovation
+      in AI technology.\n\nThese points reflect the cutting-edge advancements and
+      trends in the field of large language models (LLMs) as of 2024, highlighting
+      their growing influence and the increasing focus on ethical and practical deployment.\n\nBegin!
+      This is VERY important to you, use the tools available and give your best Final
+      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '4624'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=08pKRcLhS1PDw0mYfL2jz19ac6M.T31GoiMuI5DlX6w-1731827382-1.0.1.1-UfOLu3AaIUuXP1sGzdV6oggJ1q7iMTC46t08FDhYVrKcW5YmD4CbifudOJiSgx8h0JLTwZdgk.aG05S0eAO_PQ;
+        _cfuvid=74kaPOoAcp8YRSA0XocQ1FFNksu9V0_KiWdQfo7wQuQ-1731827382509-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA3RXS28bRxK+51cUlIMTYEjIlvOAbso6zhIrI4KjXSyyuRS7izO16umeVHWTovPn
+        F9U9Q5GG92JY0696fI/iX18BXLG/uoUrN2B24xRWd/98HA75/u//0u3z4V3+DftPP+82P/3+799/
+        vrm56uxE2v6XXF5OrV0ap0CZU2zLTggz2a2vf7h5/eObH95eX9eFMXkKdqyf8uptWr25fvN2df3j
+        6vr7+eCQ2JFe3cJ/vgIA+Kv+ayFGT89Xt1CvqV9GUsWerm5PmwCuJAX7coWqrBljvupeFl2KmWKN
+        +nFIpR/yLWwgpgM4jNDzngCht9ABox5I/oh/xPccMcBd/fvWPnwNH2lKkiFFuPN7jI5GilmBI9yj
+        9AT3GPuCPcEHy1bhm/v7D/otrMCyrVd8Da/X8OtE8W7zSuGXh8fVW/hIgVDJ24ZNrHu7eQ9wzJJ8
+        ceTb5g5GlCeOPSAo95F37DBmoDgs8Vg4YQmklh0yuSGmkPrjGn4qHLxdkCJwVpiEPDlSTaLdHFHa
+        7UgUhHYcyYPDCbccODPVZGs5n3PBACV6Eqt3vRKjByGdUlSCniIJGjTW8A86Ao+TpP2pZC4UTzAQ
+        90MmewWdK4Lu2Nmi1IpAhRPvOR+7evmWciYBlwYSio4smjzQ6VEFzsvDpGt4HEgJ8LxZA+4JRvQ0
+        54oROHrWiaLiNhDklAKgk6QKexRORUHJ5SS6hvdJYFuUI6nSqV5z9RVc0ZxGEusbCTrLHvIghrml
+        AB6MOduUtaa0Z6mVPAFX17CJQL64WrzOUlKSPSmgHVnS8S3SXRKYSDRFDPyJPARCiRz7DpBrV9pV
+        SWrvPO0ppMm+j0kIKPbY218zR1qK8y4ySFh9T6HfPWwAQ0gHrQ/XKyRti2bAaQrcYq4vRcxFMLxg
+        cZJkOLPHMuqTrmdGvFnDLyn1gYwRNHLkxh9b/nyh4rmDgCW6gby90/giNAlp7TDCxCkSib2kmSbb
+        NZaQeUzeKL25JMSxdqs3rMb+JdxLaB84D5dEyGnJCIwNHWDxnBpOecSeFJTtWYyUioZjtySxFcIn
+        hUgH6CWVWNO421xU0LDLOvP3jOnhCFj6BmXrzK7EijIMnI+QdrA3HT1DU2dR7hsS8kBjy8SOtlSO
+        lojJuNBA0c8cRpeX74GeQR1Fo4I1dp/CvsLHKjoFAo8ZDQ2jruHOe27hWL5NX9LBasSxVcWKaDuq
+        BDWdsUJMSZXPRQZdBcsS49IwW7UQseQ0mtUswD3Tmw48jSlqnltKz5mimsqX3K4zQJBn7ICMqBk5
+        Wklb804kNtZZMXdMwZ/gerOGu2icnti9UvhbwOLJ1tr/uhN5PGyPL1u7GVAuiaUATjizwwA68M6K
+        fUDxVi5OtvKpghd3lI81KMpD3e1SVPZzojoDx9MU0nGs9K2wCdWOPnMB9F6qbNkljiSq4WVAGXcl
+        QCp5KrMmbRmruh0GdkNTzC1RNOEKgWLfOlRDne9+Kb5WRu2SKzq7TBPxalmzTrPp7N2mQdEoMVbl
+        EtYn7eaKglLjspAjbw02wTHcLqV4ydryOGc1m/Zv7Pi5JqHJnU7k2NAJQoH22PxSDR+5zgHmPKDF
+        Daa2A2HIg0OhDgL1GGaEJJmSWYwRZCxxecIqRmL2wtEwVcE3R1uVpLaYFSYUHFOJeQHV2zV8oIyv
+        tBo/PAitsmB130fBqEYvEvjm14fHb+FmfW3HlgMPj/bFcBRJW02NeLTbsWOrTr2pUpbykPxCozxg
+        BjF3qHlMJWOjrtEHo1frf7jMZiJ8MruxeMyELmSKnp1NPRNKZlcCSqhMy5ZAwOaFWFs8WxQc2JNO
+        QugBfaq60LiPnkZ2hhdCcQP4YsZc80oTxVVTh+YxSxC2YL4MFF0qUhXYpRBwa72y5l6MIDtJY8VT
+        H9LWDHh5dO6pzRzN2GfpbFm+0tnw6lNVirwpWuzNqHMCz3sSJQgc+8Ka6411YKqgvHSq8xmuWtWi
+        A6ZgzsKuQnC3scGvzX2L+//fGe8knXWYAYStJPQkIBh7Mq5MdTSxapv8zlNbLTTJSee+W382z8I7
+        yybMnZwnYLXdH8kZziZJvcxa34Ly5ydqhPxnIRvCrEs2bvla2Usq62gyIx0M3A/heIbky5zV1IV8
+        b+dNqL888PkEMeXPPLQaXhpZ6RzNNuwUnesVl7abGw4Wl03zLbet8cLqtkmPF48bxF4UxxTr0sdM
+        gyZJO3P9c2dOk/2yMNQZM+2cEIZV5pG+OECZpcnssrSnyhohTUUcrVzzvqoeFPcsqbqbruE307WL
+        KUZLffkLXbjQzqZrghN78ORYOcXVgsg2MczRclQb6ZvcxvrLAuXYnSTVjDum0abqPQ3swmzoFgU2
+        X1h5YcvJLLoJfSvwDMzv1/CeI60eSzxNZvc8sg0D7zCjbXscLthu5bHfMqtczoSwFbp2tV4S5kvq
+        QGMQLTEk90QWnI0YjG3cbgMCf8JFryI7m6deCjbbiN2ailH+z8JyOYrYI2Zxs3idmnIEGqd0MGLO
+        XlW9kaMvmqW1rFWyGlKt3VKo+WeKsX5AqQJlfa3XWUsbkv4HAAD//4xZO4/jNhDu91cQWyWAYuSQ
+        PdxtaSRXbBcsEKQKDFoaycRJokBSdlzsfw++mSEl2T4gpS2Jj+HMfA8u5ZOs631gJYEXXZApW+68
+        WLKWEOZIFAa3RleFDvTYmEoX4Qw0RxuCwxbSdcLKwFpj9LVjxiYMNIOScJX9my6qMq2PSci7G0d/
+        1oCi0a4CLIgP6F4FifMo0Nkx3xbC9Qtrp3UAcx592ZlvCs74kHF2sgHpsn8zf0XKiXQlG1hmsPjG
+        PNu+vSJwBe73b9plaxApTejjNWtb7C6jLPOaMnktfM/WNfhBzolbnhd35nc/THZkPoxK8xeFUBY9
+        wjU4KG2wA118+L5kTg62qRlrGLRi3ftI5f+lRVRSF5nhYHFcIHLUpec69C6G2WisGzDoEVaDSQHq
+        kM98jsiJ43XV+GrI1Qc2QqTEW0FjERClfyeqdRl6/Otl3moPZorDdLLRCU7gYJh89WRFDXnVr67z
+        Af0oUUx5/rPtXSOppm0XkaAxzkG0MxcQZBJOKuQBkeOUNnRPR5uXxPsqUPEO9PGt+TP4YUrm29g5
+        Va3qBBUrRcrTRD+dOBalBNC7GEYwAC0DCMAOFDpk60ZuFBTmvEPCDMIx5ORVBjCJb4jTHAmV24Ib
+        pznphLHSA2UTbXbN0leUxGRVoECK8dBtAsW5L50vlwmv+Ui1FxBJYUai216UI2fM2Jk55pLgTqza
+        TySGtok7/bZGskrsCwxVDAxxnpIg+sZLWdk4ihH7Nzk88cYyVmpAFiOIsw+0xdbXNXXI5HDpRpUQ
+        Ue4sSbNIzog7usBzpa1auODWXfJ8CmYkWjTqKzwk9TT8qCsX24Aa807sFhScXL35ACT4Y1s+DvKx
+        +Wn//vNWluP8wMGpYUXfBj8mBoE7d2PHS7hhNyuZUD1wxSQNBgqMnmtao5ZLjgmeZvMM+e59H1eG
+        AEkpXUcKvOojpQu07f6dh8FBLS2tBAZHGyCGOdZoRcERn/S2mxVnlNMHu9YNgFwqX9okFSegG9Os
+        8pN3wnwUv3fm7xOlExuKm11pe4zGh62FYabeJjZjKmyp9sOReaAQnFv8z9IympO/aDWzI0jyQeM6
+        l8R14DpjJ2LNKLOp/SuOtJt7+IxX84c4IPwK3tjHB/ySS0LqXcOwqMHKdP5MYVT6ISYZhrj40Deq
+        5EEXHVQvUKLMvYI7iB/xPBbHI1DPHASYBxSbgjuz6RypnkMxmgUtciLo8MVFqMMMzsH0w7bUzVYA
+        gJODj5dAiUQ+ozd4xbLF/VhRGymPrXkhLaZsaiNoGIRI5Dto4M2hdsFfJJ4ThbNFuVTK7jYMtQGl
+        5yAtRPLerOBZpuAT1clM87FnEJAdVmay59zcL1ZacpwjcpGpPPNGwP/Fh3S65taVmw3Cx3h53Sni
+        xXkYWC2kex0ngxEYE+tCqAyeuWRxEfmAZe5k9y5YzJbxzuyj5GBn2czygxtJRSCJgVV4w8Ztqh5Y
+        K5o10v5vbkxQPG6cJdbMBPU4mqVM7vjt4wuIysSTnXLI2xnuBzbYxNpO9MgGW1+DBWrnaHELN859
+        r/9/lHu13ndT8Meoz8v/rRtdPB1AW/2IO7SY/PTMTz+ejPmH7+/mzZXcswDiIfnvNGLAry8vMt7z
+        cmO4PP306fNv+jj5ZPvVk9fXL9WDIQ8NARHj6hLwuba4Eli+XW4M2ZlfPXhabfx+QY/Gls27sfs/
+        wy8P6pqmRM0Bl2yu3m56eS0Q7lR/9FoJNC/4OV5jouHQurGjMAUn15rtdHj5XLefXxqy9Pz08fQf
+        AAAA//8DAMIhqlTfHQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e3de605dca06217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 17 Nov 2024 07:10:10 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '9951'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29998873'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 2ms
+      x-request-id:
+      - req_52a4f98f9c08fbaa1724634d237f3245
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_after_kickoff_modification.yaml

@@ -0,0 +1,487 @@
+interactions:
+- request:
+    body: !!binary |
+      CusOCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSwg4KEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKaDAoQJ2RtlOW3xhPcNjmbKwSJaxIIMUF8zJjQkvQqDENyZXcgQ3JlYXRlZDABOThF
+      x7PrrgkYQWiczLPrrgkYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODAuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjEyLjdKLgoIY3Jld19rZXkSIgogMWYxMjhiZGI3YmFhNGI2NzcxNGYxZGFlZGMy
+      ZjNhYjZKMQoHY3Jld19pZBImCiQzNGJiYzZjYS03MmRiLTQwMzktODQzMy01NTFmOWNmNDM0YTdK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAkobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSrQFCgtjcmV3
+      X2FnZW50cxKkBQqhBVt7ImtleSI6ICI3M2MzNDljOTNjMTYzYjVkNGRmOThhNjRmYWMxYzQzMCIs
+      ICJpZCI6ICI4MjJkOGM2OC01NzlkLTQ4ZWUtOTBhMi1hNjJiNDgzY2JhNGUiLCAicm9sZSI6ICJ7
+      dG9waWN9IFNlbmlvciBEYXRhIFJlc2VhcmNoZXJcbiIsICJ2ZXJib3NlPyI6IHRydWUsICJtYXhf
+      aXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAi
+      bGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93
+      X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25h
+      bWVzIjogW119LCB7ImtleSI6ICIxMDRmZTA2NTllMTBiNDI2Y2Y4OGYwMjRmYjU3MTU1MyIsICJp
+      ZCI6ICI0YTY4NDQwZi0xMjRkLTQ3YmEtYWEzNy1hZTZmMTI2NzlkMmIiLCAicm9sZSI6ICJ7dG9w
+      aWN9IFJlcG9ydGluZyBBbmFseXN0XG4iLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAy
+      MCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
+      cHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4
+      ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtd
+      fV1KkwQKCmNyZXdfdGFza3MShAQKgQRbeyJrZXkiOiAiNmFmYzRiMzk2MjU5ZmJiNzY4MWY1NmM3
+      NzU1Y2M5MzciLCAiaWQiOiAiODE2YzI1ZDgtNDg3NC00MmMxLWJmNzEtODc2OTcxZDNmYmExIiwg
+      ImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRf
+      cm9sZSI6ICJ7dG9waWN9IFNlbmlvciBEYXRhIFJlc2VhcmNoZXJcbiIsICJhZ2VudF9rZXkiOiAi
+      NzNjMzQ5YzkzYzE2M2I1ZDRkZjk4YTY0ZmFjMWM0MzAiLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsi
+      a2V5IjogImIxN2IxODhkYmYxNGY5M2E5OGU1Yjk1YWFkMzY3NTc3IiwgImlkIjogIjM4YzU1NTI5
+      LTc2ODAtNDc5OS1iODdiLTFmMDY2NjE5MGU2NyIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2Us
+      ICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAie3RvcGljfSBSZXBvcnRpbmcg
+      QW5hbHlzdFxuIiwgImFnZW50X2tleSI6ICIxMDRmZTA2NTllMTBiNDI2Y2Y4OGYwMjRmYjU3MTU1
+      MyIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChCo3E4xT/U6O20NrD4/Zkt6EggD
+      /w74tbrrOCoMVGFzayBDcmVhdGVkMAE5SPTas+uuCRhB6IDbs+uuCRhKLgoIY3Jld19rZXkSIgog
+      MWYxMjhiZGI3YmFhNGI2NzcxNGYxZGFlZGMyZjNhYjZKMQoHY3Jld19pZBImCiQzNGJiYzZjYS03
+      MmRiLTQwMzktODQzMy01NTFmOWNmNDM0YTdKLgoIdGFza19rZXkSIgogNmFmYzRiMzk2MjU5ZmJi
+      NzY4MWY1NmM3NzU1Y2M5MzdKMQoHdGFza19pZBImCiQ4MTZjMjVkOC00ODc0LTQyYzEtYmY3MS04
+      NzY5NzFkM2ZiYTF6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1902'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Wed, 20 Nov 2024 13:04:24 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Bicycles Senior Data
+      Researcher\n. You''re a seasoned researcher with a knack for uncovering the
+      latest developments in Bicycles. Known for your ability to find the most relevant
+      information and present it in a clear and concise manner.\n\nYour personal goal
+      is: Uncover cutting-edge developments in Bicycles\n\nTo give my best complete
+      final answer to the task use the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your final answer must be the great and the
+      most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      Conduct a thorough research about Bicycles Make sure you find any interesting
+      and relevant information given the current year is 2024.\n\n\nThis is the expect
+      criteria for your final answer: A list with 10 bullet points of the most relevant
+      information about Bicycles\n\nyou MUST return the actual complete content as
+      the final answer, not a summary.\n\nBegin! This is VERY important to you, use
+      the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1260'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=CkK4UvBd9ukXvn50uJwGambJcz5zERAJfeXJ9xge6H4-1732107842-1.0.1.1-IOK2yVL3RlD75MgmnKzIEyE38HNknwn6I8BBJ1wjGz4jCTd0YWIBPnvUm9gB8D_zLlUA9G7p_wbrfyc4mO_Bmg;
+        _cfuvid=MmeN9oHWrBLThkEJdaSFHBfWe95JvA8iFnnt7CC92tk-1732107842102-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AVefTnyhy126z54bX4Wq0TjWFUGJI\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1732107859,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer.  \\nFinal
+      Answer: \\n\\n1. **E-Bike Boom**: Electric bikes (e-bikes) have seen a significant
+      rise in popularity, with industry reports indicating a projected growth of 60%
+      in sales compared to previous years. Many cities are paving bike lanes specifically
+      designed for e-bikes to accommodate this surge.\\n\\n2. **Sustainability in
+      Manufacturing**: Bicycle manufacturers are increasingly adopting sustainable
+      practices, such as using recycled materials for frames and parts, and implementing
+      environmentally friendly production processes. This shift is driven by consumer
+      demand for greener products.\\n\\n3. **Smart Bicycles**: The integration of
+      technology in bicycles has progressed with smart bikes featuring built-in GPS,
+      automated gear shifting, and performance analytics. These innovations enhance
+      the cycling experience and cater to data-driven enthusiasts.\\n\\n4. **Bike
+      Sharing Programs**: Urban areas are continuing to expand bike-sharing programs,
+      with some cities introducing electric bike options and introducing smartphone
+      apps to streamline the renting process, increasing accessibility and convenience
+      for riders.\\n\\n5. **Safety Innovations**: Advances in safety technology such
+      as smart helmets that incorporate lights and indicators, anti-collision systems
+      using sensor technology, and built-in communication systems to connect with
+      smartphones are on the rise, aimed at reducing accidents.\\n\\n6. **Adventure
+      Cycling Trends**: There is a growing popularity in adventure and gravel cycling,
+      with more cyclists seeking off-road experiences. This has prompted manufacturers
+      to develop dedicated bikes that cater to rugged terrains, with features such
+      as wider tires and durable frames.\\n\\n7. **Customization and Personalization**:
+      The market for customizable bicycles is expanding. Consumers are now able to
+      choose colors, styles, and features that suit their personal preferences, leading
+      to a more personalized cycling experience.\\n\\n8. **Communities and Events**:
+      Cycling communities are thriving globally, with an increase in events such as
+      group rides, competitive races, and festivals celebrating biking culture. This
+      fosters social engagement and promotes cycling as a lifestyle.\\n\\n9. **Cargo
+      Bikes for Urban Living**: The rise of cargo bikes, particularly in urban environments,
+      allows for efficient transportation of goods, making them an appealing choice
+      for small businesses and families. This trend is encouraged by city planners
+      promoting cycling as an alternative to car deliveries.\\n\\n10. **Regulatory
+      Changes**: Governments around the world are increasingly implementing policies
+      to support cycling infrastructure, such as funding for bike lanes, subsidies
+      for bicycle purchases, and stricter emissions standards for motor vehicles,
+      making cycling a more attractive option for commuting.\\n\\nEach of these points
+      represents the latest developments in the bicycle industry as we move through
+      2024, highlighting advancements in technology, trends in user preferences, and
+      a broader societal shift towards sustainability and health.\",\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 237,\n    \"completion_tokens\":
+      539,\n    \"total_tokens\": 776,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0705bf87c0\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e58a5276a096225-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Nov 2024 13:04:26 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '7355'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999708'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_5536f2a242886d3949f0cdc1628b2996
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      Cs4CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpQIKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKOAgoQpBIRwGH/fJtGJT1cIWsC5BIIM3YyJZEYUUgqDFRhc2sgQ3JlYXRlZDABOYgb
+      lILtrgkYQZBnlYLtrgkYSi4KCGNyZXdfa2V5EiIKIDFmMTI4YmRiN2JhYTRiNjc3MTRmMWRhZWRj
+      MmYzYWI2SjEKB2NyZXdfaWQSJgokMzRiYmM2Y2EtNzJkYi00MDM5LTg0MzMtNTUxZjljZjQzNGE3
+      Si4KCHRhc2tfa2V5EiIKIGIxN2IxODhkYmYxNGY5M2E5OGU1Yjk1YWFkMzY3NTc3SjEKB3Rhc2tf
+      aWQSJgokMzhjNTU1MjktNzY4MC00Nzk5LWI4N2ItMWYwNjY2MTkwZTY3egIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '337'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Wed, 20 Nov 2024 13:04:29 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Bicycles Reporting
+      Analyst\n. You''re a meticulous analyst with a keen eye for detail. You''re
+      known for your ability to turn complex data into clear and concise reports,
+      making it easy for others to understand and act on the information you provide.\n\nYour
+      personal goal is: Create detailed reports based on Bicycles data analysis and
+      research findings\n\nTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      Your final answer must be the great and the most complete as possible, it must
+      be outcome described.\n\nI MUST use these formats, my job depends on it!"},
+      {"role": "user", "content": "\nCurrent Task: Review the context you got and
+      expand each topic into a full section for a report. Make sure the report is
+      detailed and contains any and all relevant information.\n\n\nThis is the expect
+      criteria for your final answer: A fully fledge reports with the mains topics,
+      each with a full section of information. Formatted as markdown without ''```''\n\nyou
+      MUST return the actual complete content as the final answer, not a summary.\n\nThis
+      is the context you''re working with:\n1. **E-Bike Boom**: Electric bikes (e-bikes)
+      have seen a significant rise in popularity, with industry reports indicating
+      a projected growth of 60% in sales compared to previous years. Many cities are
+      paving bike lanes specifically designed for e-bikes to accommodate this surge.\n\n2.
+      **Sustainability in Manufacturing**: Bicycle manufacturers are increasingly
+      adopting sustainable practices, such as using recycled materials for frames
+      and parts, and implementing environmentally friendly production processes. This
+      shift is driven by consumer demand for greener products.\n\n3. **Smart Bicycles**:
+      The integration of technology in bicycles has progressed with smart bikes featuring
+      built-in GPS, automated gear shifting, and performance analytics. These innovations
+      enhance the cycling experience and cater to data-driven enthusiasts.\n\n4. **Bike
+      Sharing Programs**: Urban areas are continuing to expand bike-sharing programs,
+      with some cities introducing electric bike options and introducing smartphone
+      apps to streamline the renting process, increasing accessibility and convenience
+      for riders.\n\n5. **Safety Innovations**: Advances in safety technology such
+      as smart helmets that incorporate lights and indicators, anti-collision systems
+      using sensor technology, and built-in communication systems to connect with
+      smartphones are on the rise, aimed at reducing accidents.\n\n6. **Adventure
+      Cycling Trends**: There is a growing popularity in adventure and gravel cycling,
+      with more cyclists seeking off-road experiences. This has prompted manufacturers
+      to develop dedicated bikes that cater to rugged terrains, with features such
+      as wider tires and durable frames.\n\n7. **Customization and Personalization**:
+      The market for customizable bicycles is expanding. Consumers are now able to
+      choose colors, styles, and features that suit their personal preferences, leading
+      to a more personalized cycling experience.\n\n8. **Communities and Events**:
+      Cycling communities are thriving globally, with an increase in events such as
+      group rides, competitive races, and festivals celebrating biking culture. This
+      fosters social engagement and promotes cycling as a lifestyle.\n\n9. **Cargo
+      Bikes for Urban Living**: The rise of cargo bikes, particularly in urban environments,
+      allows for efficient transportation of goods, making them an appealing choice
+      for small businesses and families. This trend is encouraged by city planners
+      promoting cycling as an alternative to car deliveries.\n\n10. **Regulatory Changes**:
+      Governments around the world are increasingly implementing policies to support
+      cycling infrastructure, such as funding for bike lanes, subsidies for bicycle
+      purchases, and stricter emissions standards for motor vehicles, making cycling
+      a more attractive option for commuting.\n\nEach of these points represents the
+      latest developments in the bicycle industry as we move through 2024, highlighting
+      advancements in technology, trends in user preferences, and a broader societal
+      shift towards sustainability and health.\n\nBegin! This is VERY important to
+      you, use the tools available and give your best Final Answer, your job depends
+      on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream":
+      false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '4457'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=CkK4UvBd9ukXvn50uJwGambJcz5zERAJfeXJ9xge6H4-1732107842-1.0.1.1-IOK2yVL3RlD75MgmnKzIEyE38HNknwn6I8BBJ1wjGz4jCTd0YWIBPnvUm9gB8D_zLlUA9G7p_wbrfyc4mO_Bmg;
+        _cfuvid=MmeN9oHWrBLThkEJdaSFHBfWe95JvA8iFnnt7CC92tk-1732107842102-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AVefbpMLcvelEguI3pyXOpfbaXLGG\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1732107867,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: \\n\\n# Comprehensive Report on the Latest Developments in the Bicycle
+      Industry (2024)\\n\\n## 1. E-Bike Boom\\nThe popularity of electric bikes (e-bikes)
+      has surged dramatically in recent years, with industry reports indicating a
+      projected growth of 60% in sales compared to previous years. This growth can
+      be attributed to increasing urbanization, the rising need for more sustainable
+      modes of transport, and technological advancements that have made e-bikes more
+      accessible and desirable. Cities worldwide are responding to this boom by developing
+      dedicated bike lanes specifically designed for e-bikes, which not only promotes
+      safety but also encourages more individuals to consider cycling as a primary
+      mode of transportation.\\n\\n## 2. Sustainability in Manufacturing\\nIn line
+      with global trends towards sustainability, bicycle manufacturers are increasingly
+      adopting eco-friendlier practices. They are utilizing recycled materials for
+      frames and components and implementing environmentally friendly production processes.
+      This shift is not just a response to regulatory pressures but also driven by
+      consumer demand for greener products. Companies that prioritize sustainability
+      are seeing a competitive edge in an increasingly eco-conscious market, as consumers
+      are more likely to align their purchases with their values regarding environmental
+      responsibility.\\n\\n## 3. Smart Bicycles\\nThe integration of technology in
+      bicycles has advanced significantly, resulting in the emergence of smart bikes.
+      These bicycles often feature built-in GPS for navigation, automated gear shifting
+      for smoother rides, and performance analytics that allow users to track their
+      cycling metrics. Such innovations enhance the overall cycling experience and
+      cater to performance-focused cyclists who seek data to optimize their rides.
+      By merging cycling with technology, manufacturers are not only attracting tech
+      enthusiasts but also making cycling more mainstream.\\n\\n## 4. Bike Sharing
+      Programs\\nBike-sharing programs are rapidly expanding, particularly in urban
+      areas. Many cities have started introducing electric bike options within these
+      programs to meet the growing demand. The introduction of smartphone apps has
+      streamlined the renting process, increasing accessibility and convenience for
+      users. This trend not only promotes a healthier lifestyle but also reduces traffic
+      congestion and environmental impact in densely populated areas, making cycling
+      a more viable option for commuting.\\n\\n## 5. Safety Innovations\\nRecent advancements
+      in safety technology are working towards making cycling safer. Innovations such
+      as smart helmets equipped with lights and turn indicators, anti-collision systems
+      utilizing sensor technology, and integrated communication systems linking bicycles
+      with smartphones are increasingly gaining traction. These developments aim to
+      minimize accidents and enhance the overall sense of security for cyclists, thereby
+      encouraging more people to take up cycling as a daily activity.\\n\\n## 6. Adventure
+      Cycling Trends\\nAdventure and gravel cycling are witnessing a renaissance,
+      with many cyclists seeking off-road experiences that enable a connection with
+      nature. This trend has led manufacturers to innovate by developing dedicated
+      bikes suited for rugged terrains, characterized by features like wider tires
+      and durable frames. As consumers become more adventurous in their hobbies, manufacturers
+      are recognizing the need to cater to this niche market, fostering the growth
+      of adventure cycling as a distinct segment in the industry.\\n\\n## 7. Customization
+      and Personalization\\nThe demand for customizable bicycles is on the rise, allowing
+      consumers to choose various aspects of their bikes, including colors, styles,
+      and features. This trend towards personalization is enhancing the cycling experience,
+      as riders can tailor their bicycles to their preferences. The flourishing market
+      for custom bikes reflects a broader societal shift towards individuality and
+      self-expression, as consumers are no longer content with one-size-fits-all solutions.\\n\\n##
+      8. Communities and Events\\nCycling communities are thriving worldwide, reflected
+      in an increase in events such as group rides, competitive races, and festivals
+      celebrating biking culture. These gatherings not only foster a sense of camaraderie
+      among cyclists but also promote cycling as a lifestyle choice to the wider community.
+      The growth of these events is instrumental in building a culture around cycling,
+      driving advocacy for cycling infrastructure and safety, and ultimately increasing
+      the number of people who cycle.\\n\\n## 9. Cargo Bikes for Urban Living\\nThe
+      rise of cargo bikes, especially in urban settings, represents an innovative
+      solution for transporting goods efficiently while reducing reliance on motor
+      vehicles. Such bikes serve as an appealing alternative for small businesses
+      and families alike, allowing for easy deliveries and shopping. City planners
+      are increasingly promoting cargo bikes within urban transport strategies, recognizing
+      them as a sustainable option that aligns with broader goals for reducing carbon
+      footprints and enhancing urban mobility.\\n\\n## 10. Regulatory Changes\\nGovernments
+      around the globe are progressively enacting regulations to support and grow
+      cycling infrastructure. Initiatives include funding for bike lanes, subsidies
+      for bicycle purchases, and stricter emissions standards for cars. These regulatory
+      changes are making cycling a more attractive option for commuting and are an
+      acknowledgment of the role that cycling plays in reducing pollution and traffic
+      congestion. Such policies are instrumental in fostering a cycling-friendly environment
+      and encouraging more people to adopt biking as a daily mode of transportation.\\n\\nThis
+      report highlights the most significant developments in the bicycle industry
+      as we advance through 2024, showcasing the technological breakthroughs, shifts
+      in user preferences, and an overarching movement toward sustainability and health.
+      These trends are indicative of a vibrant cycling culture that continues to evolve
+      to meet the needs of modern society.\",\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 790,\n    \"completion_tokens\": 1022,\n
+      \   \"total_tokens\": 1812,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+      \"fp_0705bf87c0\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e58a5580add6225-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Nov 2024 13:04:46 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '18921'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149998916'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_32b801874a2fed46b91251052364ec47
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_with_knowledge_sources.yaml

@@ -0,0 +1,115 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Information Agent.
+      You have access to specific knowledge sources.\nYour personal goal is: Provide
+      information based on knowledge sources\nTo give my best complete final answer
+      to the task use the exact following format:\n\nThought: I now can give a great
+      answer\nFinal Answer: Your final answer must be the great and the most complete
+      as possible, it must be outcome described.\n\nI MUST use these formats, my job
+      depends on it!"}, {"role": "user", "content": "\nCurrent Task: What is Brandon''s
+      favorite color?\n\nThis is the expect criteria for your final answer: Brandon''s
+      favorite color.\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '931'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.9
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xSQW7bMBC86xULXnqxAtmxI1e3FEWBtJekCXJpC4GmVhIdapcgqbhN4L8HlB1L
+        QVOgFwGa2RnOLPmcAAhdiQKEamVQnTXp5f3d9lsdbndh++C+757Or6/bm6uvn59WH/FGzKKCN1tU
+        4VV1prizBoNmOtDKoQwYXef5+SK7WK3ny4HouEITZY0N6ZLTTpNOF9limWZ5Ol8f1S1rhV4U8CMB
+        AHgevjEnVfhbFJDNXpEOvZcNiuI0BCAcm4gI6b32QVIQs5FUTAFpiH4FxDtQkqDRjwgSmhgbJPkd
+        OoCf9EWTNHA5/BfwyUmqmD54qOUjOx0QFBt2oD1sTI9n02Mc1r2XsSr1xhzx/Sm34cY63vgjf8Jr
+        Tdq3pUPpmWJGH9iKgd0nAL+G/fRvKgvruLOhDPyAFA3nF/nBT4zXMmHXRzJwkGaKr2bv+JUVBqmN
+        n2xYKKlarEbpeB2yrzRPiGTS+u8073kfmmtq/sd+JJRCG7AqrcNKq7eNxzGH8dX+a+y05SGw8H98
+        wK6sNTXorNOHN1PbMsuz1aZe5yoTyT55AQAA//8DAPaYLdRBAwAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e54a2a7d81467f7-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Nov 2024 01:23:34 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=DoHo1Z11nN9bxkwZmJGnaxRhyrWE0UfyimYuUVRU6A4-1732065814-1.0.1.1-JVRvFrIJLHEq9OaFQS0qcgYcawE7t2XQ4Tpqd58n2Yfx3mvEqD34MJmooi1LtvdvjB2J8x1Rs.rCdXD.msLlKw;
+        path=/; expires=Wed, 20-Nov-24 01:53:34 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=n3RrNhFMqC3HtJ7n3e3agyxnM1YOQ6eKESz_eeXLtZA-1732065814630-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '344'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999790'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_8f1622677c64913753a595f679596614
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_before_crew_modification.yaml

@@ -0,0 +1,445 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Bicycles Senior Data
+      Researcher\n. You''re a seasoned researcher with a knack for uncovering the
+      latest developments in Bicycles. Known for your ability to find the most relevant
+      information and present it in a clear and concise manner.\n\nYour personal goal
+      is: Uncover cutting-edge developments in Bicycles\n\nTo give my best complete
+      final answer to the task use the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your final answer must be the great and the
+      most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      Conduct a thorough research about Bicycles Make sure you find any interesting
+      and relevant information given the current year is 2024.\n\n\nThis is the expect
+      criteria for your final answer: A list with 10 bullet points of the most relevant
+      information about Bicycles\n\nyou MUST return the actual complete content as
+      the final answer, not a summary.\n\nBegin! This is VERY important to you, use
+      the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1255'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xX247cyA19n68g+ikxugc9vuzMzpvttTdGMtjAHsPAxoHBrqKkypSKSpHqnvZi
+        /z0gpb4MsgHy0mipqljk4eEh9dsFwCLFxS0sQoca+iGvXn/u8fuX9cPDX7tffu1vtlkffv5l/fnX
+        j9uPN68WSzvBm39R0MOpy8D9kEkTl2k5VEIls3p1/eLqx/V6vX7lCz1HynasHXT1klfP189frtY3
+        q/UP88GOUyBZ3MI/LgAAfvNfc7FEelzcwnp5eNOTCLa0uD1uAlhUzvZmgSJJFIsulqfFwEWpuNf3
+        HY9tp7fwAQrvIGCBNm0JEFpzHbDIjirA1/I+Fczw2p9v4Wv5Wq4u4dmzd5mC1hTgTQr7kEngT+9W
+        b9IDyZ/hJ+5TQSXQjuAO6wPp7bNn8KGAhbsEWm1sI5g/qYwEypAJI6QCgmarrbzTDtrMG8x5fwn3
+        HaUKAw9jxpp0D0mgGSlThM3e78G4xRKop6JmZ4OqVPegFLrCmdv9ErhpqKbSQubSUoWKpSUBLBGk
+        46pUIXRYW9uiqSdZQo8P9hS470e1fz1XAmqaFJLd5GdHUUwFN5ns5rFusACVbapczB25NNSeG2of
+        ilJb0YgCu6QdfOqxKtwfnTScZkShxzI2GHSsVAWwmnUjlqTS5r09cB3YrJUWPvD9WayGKJXOAIFR
+        qAI9DlQTlUCX8J7QbArk9EDw898/gVYMFucSmqSFRCCiImRuW39rUWLRtNKOGgXZi1IvEFOloHkP
+        OZUHinapWDxDx4UmjzcUjAwtGBkjVs9xIeOWl8KEzQvD5tMZjHfH0O2sw5P+PZIYPO9OyGI2DgWq
+        RaDDLcEwSkfR0jVgSSTmEkYe1GhNxW59YnmoHEjEMi1j6AAFRk05fbfFSp6HCD0q1YRZllApjsEZ
+        gXXDBRpmHWoqKhbYUDmOwbI7YZZMFcxRP5FqMPYCBS7cm3dGgVScvps56anEUbTuHZeXE2cKb50y
+        fsffUtvpjuwX7g6OGS73HUGkLWUevAi4MaAdC5akdB5GKiGP8SwO87atOHRUyKKUMU8h0aNW6smT
+        fLrYtsexeq6aij2JlWiSp1UoMGDV5FHnPRTWFOhQJhUdR7PU81gs9eCysJyZ6/mh2nDtncdeagNR
+        dGheGTRvR1Hu03e3aet3HB1iEyL4iSS1RZ5Ij3ZkdSSA5o6f00rFuLszdk7C5KXZz7biZAa0M13M
+        mXdQU7SSVIYwe0Ae6qQlGIxTXC3DVq2TfiWZbwqWBj8c05aqkHFYxp4qFKI42Rgq96xWo5NUmV+Q
+        U0Mwq+1mP/liKDVc5+srDRmPIihqosoN7DrONMXm4P3gCv44YBFTIm7gs4vW233ILialqShaRxcf
+        A/DOZC8kddZyzXGXIs2atCVxgqfizqXSrhrTmugidW7pVGWRYjIg4hwZllmI7XElHXp5SujIZdjl
+        LPBYsSWrn9MFJ2W2016ellI0hTZgW3OOi4d9bWH/hTBr57u/UM6udm+oUJPUqfLFcm/9x23usJJv
+        4Qa608lZJpdTOxiIhzyhETpm8bqaoUSjWsSU90CPVEMSgsrmMXlXOxY8CBkEIGNt6dQJuTlctjJG
+        lQmymQQTNSfl7fExORED1ph4izKpjZeNMa/VzoBJxdzazBE7LjeGy0fzjBt4i7VlP/XZlFD3xw4/
+        i8xcP+XQjdzZSL3jwtXub/no4xJ2XbKcV+9E0xatWGTg6nlrmaMAb6lOXRiiTy6BXG4bmzMcSJAu
+        NToXqjzpuptR0tS2KFtN7YEHF8zlUwU6dmchNaNT+D+6lHA/kCa1IehQBhbRO/fTYz/fckhvhwLU
+        byoGihBTm6wnDRnVZMuCNzZtU9URM1RCB9RFYmz7KZuHt2ZDoJ0TZC3ZxwTs+YxOVLQbJaHoUSca
+        EqtizIDaZTLRmDGeLNm2cHCdCwxjHVhmJbhaW/DvOYwCXCbd/IQN6R7O+o5F/3pSdm8Kh2Yl087z
+        GevUWXwUgI5yTzpL6mZMWVemE1a1xRTAPDrME47LdE2c2s1B3Yp3nW2StHFOLqdi4yKmxLix3PZD
+        5a33bXsHQmGsvvUwwx2y6m5P84cR/kjGy/NZuVIzCtqoXsac5/e/H4fvzO1QeSPz+vF9k0qS7pvV
+        BRcbtEV5WPjq7xcA//Qhf3wyty9M6wf9pvxAxQw+f3E92VucPitOqy+vb+ZVZcV8Wri+erX8A4Pf
+        IimmLGffCYuAoaN4Onr6qMAxJj5buDgL+7/d+SPbU+iptP+P+dNCCDQoxW9Dtc7wNOTTtkr22fW/
+        tl3AfwAAAP//ggYz2MFKkGQVn5YJqkHBjTRQhKQVxJunGlkYG6eaplkqcdVyAQAAAP//AwB8fdED
+        Ag4AAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e44d29989a61ab0-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 18 Nov 2024 03:20:10 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=elWqsM.3Jt5.vyzDrpCmVftKrlxb0_fRVMZxBGUYfcE-1731900010-1.0.1.1-AxUZI4aRPPnqgUcewvytSN0TcEpcfBqYEZ.h2A96g3wUsy6Ui_pr4y81nyHf2Pcn1S3lz4zSmufsGDmnNKtHDQ;
+        path=/; expires=Mon, 18-Nov-24 03:50:10 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=lzrs54cKet3l28qlaoF9_vtIs55.7H9Sbr6IhTssBmk-1731900010790-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '5249'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999708'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_a9781a68655042f161d8089cc3819728
+    status:
+      code: 200
+      message: OK
+- request:
+    body: !!binary |
+      CuEOCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSuA4KEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKQDAoQ2G6ncUKutPIsOmTplHC6bBIIclCMqGiNvUoqDENyZXcgQ3JlYXRlZDABOcBv
+      KPXg8QgYQXAFLvXg8QgYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODAuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogMWYxMjhiZGI3YmFhNGI2NzcxNGYxZGFlZGMy
+      ZjNhYjZKMQoHY3Jld19pZBImCiQzNDEwYmI2Mi01NzYxLTRhMGQtOGY1Zi1hOTliZWY5NDYxM2VK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAkobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSqoFCgtjcmV3
+      X2FnZW50cxKaBQqXBVt7ImtleSI6ICI3M2MzNDljOTNjMTYzYjVkNGRmOThhNjRmYWMxYzQzMCIs
+      ICJpZCI6ICI1YzgyZGRkOS1kMTM3LTQ3MDMtODY0My1iNTFmZDBlMTUxMjkiLCAicm9sZSI6ICJ7
+      dG9waWN9IFNlbmlvciBEYXRhIFJlc2VhcmNoZXJcbiIsICJ2ZXJib3NlPyI6IHRydWUsICJtYXhf
+      aXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAi
+      bGxtIjogImdwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2Rl
+      X2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6
+      IFtdfSwgeyJrZXkiOiAiMTA0ZmUwNjU5ZTEwYjQyNmNmODhmMDI0ZmI1NzE1NTMiLCAiaWQiOiAi
+      ODdlYmRiYTMtNDRmZS00ODBmLWI2MWQtMWYzZjIyMWE5MDE2IiwgInJvbGUiOiAie3RvcGljfSBS
+      ZXBvcnRpbmcgQW5hbHlzdFxuIiwgInZlcmJvc2U/IjogdHJ1ZSwgIm1heF9pdGVyIjogMjAsICJt
+      YXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRv
+      IiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6
+      IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqTBAoKY3Jl
+      d190YXNrcxKEBAqBBFt7ImtleSI6ICI2YWZjNGIzOTYyNTlmYmI3NjgxZjU2Yzc3NTVjYzkzNyIs
+      ICJpZCI6ICI2ZTIzZmMzMS02OGI2LTRjZTMtODZjNC0zMDcxZGUwZDdjMWIiLCAiYXN5bmNfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInt0
+      b3BpY30gU2VuaW9yIERhdGEgUmVzZWFyY2hlclxuIiwgImFnZW50X2tleSI6ICI3M2MzNDljOTNj
+      MTYzYjVkNGRmOThhNjRmYWMxYzQzMCIsICJ0b29sc19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiYjE3
+      YjE4OGRiZjE0ZjkzYTk4ZTViOTVhYWQzNjc1NzciLCAiaWQiOiAiNzRhOWVhMjMtNzVmYy00NWFi
+      LWIyMDAtMTllZTk0ZjU0Y2JkIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lu
+      cHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ7dG9waWN9IFJlcG9ydGluZyBBbmFseXN0XG4i
+      LCAiYWdlbnRfa2V5IjogIjEwNGZlMDY1OWUxMGI0MjZjZjg4ZjAyNGZiNTcxNTUzIiwgInRvb2xz
+      X25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEDkgSkh9vBYObKyMriyidxwSCG3RsAoOYBU/KgxU
+      YXNrIENyZWF0ZWQwATkgjkr14PEIGEHYFkv14PEIGEouCghjcmV3X2tleRIiCiAxZjEyOGJkYjdi
+      YWE0YjY3NzE0ZjFkYWVkYzJmM2FiNkoxCgdjcmV3X2lkEiYKJDM0MTBiYjYyLTU3NjEtNGEwZC04
+      ZjVmLWE5OWJlZjk0NjEzZUouCgh0YXNrX2tleRIiCiA2YWZjNGIzOTYyNTlmYmI3NjgxZjU2Yzc3
+      NTVjYzkzN0oxCgd0YXNrX2lkEiYKJDZlMjNmYzMxLTY4YjYtNGNlMy04NmM0LTMwNzFkZTBkN2Mx
+      YnoCGAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1892'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Mon, 18 Nov 2024 03:20:10 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: !!binary |
+      Cs4CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpQIKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKOAgoQwB8k3adY9mK031pcBVZJKhII3fxizKFNiGkqDFRhc2sgQ3JlYXRlZDABOaj7
+      K0Xi8QgYQUiCLUXi8QgYSi4KCGNyZXdfa2V5EiIKIDFmMTI4YmRiN2JhYTRiNjc3MTRmMWRhZWRj
+      MmYzYWI2SjEKB2NyZXdfaWQSJgokMzQxMGJiNjItNTc2MS00YTBkLThmNWYtYTk5YmVmOTQ2MTNl
+      Si4KCHRhc2tfa2V5EiIKIGIxN2IxODhkYmYxNGY5M2E5OGU1Yjk1YWFkMzY3NTc3SjEKB3Rhc2tf
+      aWQSJgokNzRhOWVhMjMtNzVmYy00NWFiLWIyMDAtMTllZTk0ZjU0Y2JkegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '337'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Mon, 18 Nov 2024 03:20:15 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Bicycles Reporting
+      Analyst\n. You''re a meticulous analyst with a keen eye for detail. You''re
+      known for your ability to turn complex data into clear and concise reports,
+      making it easy for others to understand and act on the information you provide.\n\nYour
+      personal goal is: Create detailed reports based on Bicycles data analysis and
+      research findings\n\nTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      Your final answer must be the great and the most complete as possible, it must
+      be outcome described.\n\nI MUST use these formats, my job depends on it!"},
+      {"role": "user", "content": "\nCurrent Task: Review the context you got and
+      expand each topic into a full section for a report. Make sure the report is
+      detailed and contains any and all relevant information.\n\n\nThis is the expect
+      criteria for your final answer: A fully fledge reports with the mains topics,
+      each with a full section of information. Formatted as markdown without ''```''\n\nyou
+      MUST return the actual complete content as the final answer, not a summary.\n\nThis
+      is the context you''re working with:\n1. **Electric Bicycles (E-Bikes) Dominate
+      the Market:** In 2024, e-bikes continue to lead in sales growth globally. Their
+      popularity is fueled by the advancement in battery technology, offering longer
+      ranges and shorter charging times, making commuting more efficient and sustainable
+      in urban environments.\n\n2. **Integration with Smart Technology:** Bicycle
+      manufacturers are increasingly incorporating IoT technology to enhance user
+      experience. Features like GPS tracking, fitness data logging, and anti-theft
+      systems directly linked to smartphones are becoming standard in newer models.\n\n3.
+      **Sustainable Manufacturing Techniques:** Environmental concerns have pushed
+      companies to adopt greener manufacturing processes, such as utilizing recycled
+      materials, reducing carbon footprints in production, and implementing circular
+      economies within the bicycle industry.\n\n4. **Innovations in Lightweight Materials:**
+      The development of new composite materials, including carbon and graphene, results
+      in extremely lightweight and durable frames. This advancement is particularly
+      noticeable in racing and mountain bikes, enhancing performance and speed.\n\n5.
+      **Customizable and Modular Bike Designs:** In 2024, there is a notable trend
+      toward bikes with modular designs that allow riders to customize parts and accessories
+      easily. This trend caters to diverse consumer needs and promotes longer bike
+      life cycles by allowing for parts replacement instead of whole bikes.\n\n6.
+      **Expansion of Urban Cycling Infrastructure:** More cities worldwide are investing
+      in cycling-friendly infrastructure, such as dedicated bike lanes and bike-sharing
+      schemes, to encourage eco-friendly commuting and reduce traffic congestion.\n\n7.
+      **Health and Wellness Benefits:** With growing awareness of health and fitness,
+      more people are choosing cycling as a daily exercise routine. The industry sees
+      a surge in sales of fitness-oriented bicycles designed to maximize cardiovascular
+      and strength training benefits.\n\n8. **Rise of Cargo and Utility Bicycles:**
+      There is an increase in demand for cargo bicycles, which are used for transporting
+      goods over short distances, reflecting a shift towards sustainable business
+      delivery options, particularly in urban settings.\n\n9. **Competitive Cycling
+      and Esports:** Competitive cycling has embraced digital platforms, with virtual
+      reality and augmented reality races gaining traction among cycling enthusiasts
+      and professional athletes for training and competition purposes.\n\n10. **Focus
+      on Bike Safety Innovations:** Advances in bicycle safety technology, including
+      smart helmets with built-in communication systems and advanced lighting for
+      night visibility, are considerably improving rider security, making cycling
+      a safer mode of transport.\n\nBegin! This is VERY important to you, use the
+      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '4197'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=elWqsM.3Jt5.vyzDrpCmVftKrlxb0_fRVMZxBGUYfcE-1731900010-1.0.1.1-AxUZI4aRPPnqgUcewvytSN0TcEpcfBqYEZ.h2A96g3wUsy6Ui_pr4y81nyHf2Pcn1S3lz4zSmufsGDmnNKtHDQ;
+        _cfuvid=lzrs54cKet3l28qlaoF9_vtIs55.7H9Sbr6IhTssBmk-1731900010790-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4RXTY/kxg29+1cQ44sNdDdmdm0nmdvueh1s4gGM3UkCJ75QVZTETH3IrFL3avzn
+        A7Kk7mknQC4NtFRkkY+Pj9RvXwDcsL+5hxs3YnVxCvs3f4vdtz++G37++88fX//lp6f4/vM/n6eH
+        +Ne75+8+3uzUInf/Jlc3q4PLcQpUOaf22glhJfV694fXd3+6vb29u7MXMXsKajZMdf9N3r+6ffXN
+        /vaP+9vvVsMxs6Nycw//+gIA4Df71RCTp88393C7255EKgUHurk/HwK4kRz0yQ2WwqViqje7y0uX
+        U6VkUT+OeR7Geg8fIOUTOEww8JEAYdDQAVM5kfySfkk/cMIAb+z/vT74Et7lOAmNlIqafKQpS4Wc
+        4C27xQWCD8nPpcoCj0LJF+AEmqcZfwl3B3gfyFVht1kU+Or9/i0/Ufkavs+RE1aCOhI8oDxRVcMP
+        zccOaLPtVtsduBxjTmGBp5RPCbAA7Tv1pq9S5TSbNxaYpxOKhyqo5cuyaGxDyB0GKGjOSg7suV84
+        DauRt4iSIz2sUUWL6gCPI0GZZbAX7UqY8jQHFK6LgdoRYK3C3VzJQ81QeEjcs8NUAf1R3UZK1UDq
+        sFaSBSq5MeWQh+UAD9mTbN6LFavLWCqEnAYSEEwDgcMJOw5cWVPAEPJJ4++zAH2ulDxZ0kcKWieE
+        wmkIBG5EGegAb7xnJS+GsOwsRSE/O32kcdkxw4MjFRixGK4vsmpA4TQRhh1EfFrRi4BwZOwCASYP
+        1PfsmFKFPJlzDXCWDpPVcK6chgO8KeAsE0DJc/IW0ClL8DAITlMgOHEdNYaBivlR51MOYdZ/LQP0
+        6x25P6M3CRUDG6HMpSInC63kZnhQZse5khToKFHPFXrJsaFxgbDBgGtkDfhFYUh45MG4K6iptjgJ
+        C1lR4DSyor5hZyBl8KRyUcivUFDkUjinclg75tUBPqRKg6AlZE4/RZQKj2em6NGt/yKmuUdXZ9FM
+        RjwqQe0OLfsCFDtBy2fUNxfPuYdifi8M1AApjUZ/IwZ7UlJNJEzJUeuCuZAa6wGNVBJV/f84choK
+        fPUhP34NXODEnsokhH7XsugJNcoCZXajNu6ff/qk4DkjUFlKpai1cNqCg5atYvLawpwg0YlkkwEw
+        ZS0aDperpKwbSgu8aDohD9BzTVQKeKy4azeC5Lla+yQPMSeuWWAi6bPErfuFMOy1/OBZyNWwQB1F
+        pXRtAYNvGnOicoAfZqkjScyi9W/N7gFT5X0dqa/nBK1EHVECT0cKeSK/g9z3JJr1ROgM3sjJQ7fA
+        JPnIXl9xMpHHRHkuELJrKc+Tx0oFuAc8A8QFYj6ShyxQMU4k5K0KVsJCl6Kzw3AtTijG6VQUDL14
+        E19FOiujEznVAk9HnV+argV4xDC33u/n5JrGaLNo45uUNnlTZ1zqRvjXB/j0oj8fznxWl8Z5/nWm
+        oqffpyNLThqmavhm1VpSKCInbfdJOMvLi8+obLNqHVKHF7cpXzTzq+ZpupIGIJf3vTaBD1YSR6Vo
+        5q27jL8vcohXOdRzDlBHrFpZjvxMQFfpcJzQ1QO8gZQrOzJPVYeqVrN171k7Kgd+PvexkOXnIWIl
+        YQxtwqxZT5JXfd/9lxzhtfgLns4+9GyZ43QWywlT02kCDCVDn92sweS0qZo6dSidiX2uk7DyqVts
+        AkR+NoKfo7ngaJxh3aoUC8M7kQzL/jJDJkGnqJT/NcBcTo4mUyEEx+J0KmvNUo6L0X4d5hcCFBiQ
+        k6FgnhWc00hCreU0xJaqJ53i5I1MNoePSi2NuMG+8m8HfVMANY95zeJlgYXKlFPhdn6j/zeq9ykf
+        rZhWtx95GOuJ9BcetoLq6Rfiy6vJkSC8OH6p/7YLmQgKHdepp7TbeNEyO8A/VJx/v57okpsLm0Zu
+        er2VljsSA0An9EiJdheJWNXN5bhGth5VXQQ/S2P1qJPvqIJOfRbaROkSviI/oVS2UqryboLUkl7r
+        ufZeu2BO2oDQcZsnNFgya1mvxH2dcRe5c8JVhfDQwCeBXlDnPkfVXwIkyX5JGNlpfXsOG2vXnoQy
+        kQr5Ra4VQaps4Rq6FQcqRiP1QDb2tc2aHDZ3qBDMKkWBn9Z5W1QEBq1R8g3CJnhtBhfS2fgSOu1N
+        SmUWupRFe8DG6TrXhyw6RDxF1KU993BEYX1USUR1dLdueGeh6CSjPy+huW+BG8vrOBfGUs9LzLcH
+        eDeXmiM/n/fBh+ytLXX1h++Ne2dWL4RiigyFFFgYpC21Tf9q1k2+gPu9z7j6vKZ0+b+6btKl/nMC
+        +3y7GnOm0rZJtGqRlFap7fomF5GorqsveD6SWCnIt0pOQj2Jbk0GbxNTknI4A7EGCz06LaiukoRl
+        ub5GbbURVno4Fcws3GbPlE9ta7jsOxU5tKnH8iKjrPx0+i0CQr/OLBv5ryNdN6qGesr6oadT0IjQ
+        vNQl0F6TccaWc1rQzbVRr8mfrXkv5/MB3i5AOh+35shJhX2eBkG/dpPQFHBtzCbtgXsqExoOlz2k
+        nL90dm2AbXVQ/K1o60c6rS7/AwAA//+MWU1vGzcQvftXELq0AWShbuPGPTaBi+bqIOmpEKjd2V3W
+        XHJBctdVAf/3Yj74IdsFehNEiuIMh2/ee2zClfaLv3jSMUGu2Z8P6v7vRbsoWf9K/PyTFPlnNwQd
+        U1ippkSkCqIDZqY2Z75UtIuWFBCCoXqWc6XGiqqV5Q9pHuTMUq0bqh3iFSeifQbbHeKeSCjZl7nY
+        l5wflDiM6+zaQ8xtkmdKhD30pkProtwfqx1WFgqo6zhpqq3YTTBnqlw4hQ6EslK7BkvnC7YJ4bSS
+        bjOzpOj8GvQIlzSqqEAubWthM3gJOMCsqqrwO6jPjMb9i6hV1ANIT+YbIj2WUpn/Hf+IuhAm/B9w
+        VM9+SVwukk4d5eoswcw6nImzEtKSGtwrC7oXSJxA2zQZCHte96Lb23NzSzgidgtSK/Y+HNTvtArt
+        /Q+wloTKR9ajBI/cnQsg6icdgCb5QXbAjJs1jmzFuN5spl9zK600tQlUuyydLEGMNBSDig9CZyJe
+        ntHM4CpfLh5OhhOqyguOlNXWsobFx0wJqojsSZCLkUI+jGT9zCrowjXpdOiN33RkSoeR5nZ4fVqN
+        pbMQ+R65XSIQ61Ra5GXAObK9OgF+a/3TNRNvXns1iS4rBoIiHls2eRyIOgm1BVs+ir07pWfvRjmH
+        5sCb/P8Hv6qie18ZAJpIaPpkQcqnIac8AzphAtkNmemsj4BMOIBxgw/tMX8XFaEfRa82k4jWZ+gl
+        ujx5/G+0L3L16WUJXndTLtK7g3owTDs/6TB62sFXyXAuiNzJG/DryuRVJjcsMTaAWfQOBTGg5ycG
+        wGSGxGyU24w6waQ3g6kRStAi7Al7Ogl9sNiPzxlkM78s/493IoKeLcRIqMoOAiFL8nJfURxjZmIj
+        z7GEWgzTFg0Q5qSkNjPI4+TRe+RWyHPjhLZpTzat9Fk4v2a5pKD7ivINpEThsSnoLH/UBpOheGZ9
+        RvfRuMZ0C0ReSTUhsf0oyZHoLdJvBkU+p5YrWOQVyi/ArgoVTWaobI+9lnl7jPGpYxGoiQUY+jys
+        hNEv2yEHOHtB6mzLFWj8hTVnZtC5D+MW7inDVHLtlNoSmUqK8xVVb0aq/FZDeLaOeSVadTMhrSjT
+        6DeoDht/96C+5WFgU+P7bw/vuOOsJDSgr0O/PrxrDBbJeFUGyNf1BqTOpGhYiuJyRTZgw7uv1Fqo
+        WiMcdJqQ4QjCu5FP0zhlZmRkZoO9imbGnoObY/yvOCw8lzG3m7D/uvGFamXh4NfU8AdNot4PagRP
+        ApAcJGtmk/TFbctpX6xOmHXZKHITSoNfMPmrY/5DiLv2tDWOhsCSw6Y7YhY+N7bwESyK952PnrSu
+        7iZK8USaOBatCNrOTMVrzfD555q7+eGgfkNpwA8cj6C+MLNoFDpOlW9fWfpCjhpDtZXDGmUH5sMb
+        l/ZIjmTL2F5qnyI2E1ri0dDGA5e2P0UIG2RbKFVPpbi6E9gZUlTI9pdF3D+FPTNdG7HgnREPUbzJ
+        F68J1QBFgBSbJHu5JI8utCvMEEZw3Vnh5l56NcWyYJeDaGn1SckqaG3gp8l0U0sFEKZFjDvyOjZT
+        aR7iEnnVzAQL3gfQj+LZcvUVTcMWQJYN+OPmarCYyT6XIdacXTrXKMlXbw/5EE9YHH3Aq4oxcbmQ
+        SxVcLG8mRCiIr1WpLbyCHnOwhfW6IcqH9oEvwLBGje+LbrVWvn8uL4bWj0vwpyjj5fvBOBOnI0bg
+        Hb4OxuSXHY0+Xyn1J71MrhePjTsE8yUdk38Ehwt++PGO19vVt9A6enNz+5MMJ5+0bUbu7m72byx5
+        7AF1a2yeN3ed7ibo62/rWyiihG8GrprAX2/orbU5eOPG/7N8HejQZIT+uAQUTpdB12kB/iJ7/O1p
+        JdG04R2X+3Ew+L5HjRSPZFiO72+74fZ9Dxp2V89X/wIAAP//AwC/JrUuuR4AAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e44d2bc2bec1ab0-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 18 Nov 2024 03:20:25 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '13936'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29998979'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 2ms
+      x-request-id:
+      - req_602e9ec1c4bc0da2fdb284f809c50872
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_before_crew_with_none_input.yaml

@@ -0,0 +1,438 @@
+interactions:
+- request:
+    body: !!binary |
+      CuMOCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSug4KEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKSDAoQf/zeqxfqyNP5BgW6rZrC0BIIiXyYjb3bUBcqDENyZXcgQ3JlYXRlZDABOXha
+      vrnarwgYQcCbxrnarwgYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODAuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogZjM0NmE5YWQ2ZDczMDYzZTA2NzdiMTdjZTlj
+      NTAxNzdKMQoHY3Jld19pZBImCiQ2Yzg5NDczNy0zNWJjLTRhZDEtYjE2Ni1hZTY3ODhhMTA4YWZK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAkobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSqwFCgtjcmV3
+      X2FnZW50cxKcBQqZBVt7ImtleSI6ICI3M2MzNDljOTNjMTYzYjVkNGRmOThhNjRmYWMxYzQzMCIs
+      ICJpZCI6ICIzNDQ2YWRlOS05YWM0LTQ1NTUtOTlkNS0zYWM0MzdhMmMxNmUiLCAicm9sZSI6ICJ7
+      dG9waWN9IFNlbmlvciBEYXRhIFJlc2VhcmNoZXJcbiIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4
+      X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwg
+      ImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29k
+      ZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMi
+      OiBbXX0sIHsia2V5IjogImJiMDY4Mzc3YzE2NDFiZTZkN2Q5N2E1MTY1OWRiNjEzIiwgImlkIjog
+      IjExMzVjODkzLTRlZGUtNDRiNC1hMjZmLTIxYWUxNzA0ZDRlZCIsICJyb2xlIjogInt0b3BpY30g
+      UmVwb3J0aW5nIEFuYWx5c3RcbiIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwg
+      Im1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQt
+      NG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/
+      IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSpMECgpj
+      cmV3X3Rhc2tzEoQECoEEW3sia2V5IjogIjZhZmM0YjM5NjI1OWZiYjc2ODFmNTZjNzc1NWNjOTM3
+      IiwgImlkIjogImIxZjQ5ODJiLTRjZGItNDk1MC04ZmNjLWMwZDcxNzRhYzY0NiIsICJhc3luY19l
+      eGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAi
+      e3RvcGljfSBTZW5pb3IgRGF0YSBSZXNlYXJjaGVyXG4iLCAiYWdlbnRfa2V5IjogIjczYzM0OWM5
+      M2MxNjNiNWQ0ZGY5OGE2NGZhYzFjNDMwIiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICJi
+      MTdiMTg4ZGJmMTRmOTNhOThlNWI5NWFhZDM2NzU3NyIsICJpZCI6ICIyY2VkNGVhNC01YjcwLTRh
+      MDctOTEyOS00MzQ2ZDQ1OWM4NjIiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5f
+      aW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInt0b3BpY30gUmVwb3J0aW5nIEFuYWx5c3Rc
+      biIsICJhZ2VudF9rZXkiOiAiYmIwNjgzNzdjMTY0MWJlNmQ3ZDk3YTUxNjU5ZGI2MTMiLCAidG9v
+      bHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQOaRyuH2UERJ3sHC1ImhOgxIIq8DZc4P2KYMq
+      DFRhc2sgQ3JlYXRlZDABOTA127narwgYQVjV27narwgYSi4KCGNyZXdfa2V5EiIKIGYzNDZhOWFk
+      NmQ3MzA2M2UwNjc3YjE3Y2U5YzUwMTc3SjEKB2NyZXdfaWQSJgokNmM4OTQ3MzctMzViYy00YWQx
+      LWIxNjYtYWU2Nzg4YTEwOGFmSi4KCHRhc2tfa2V5EiIKIDZhZmM0YjM5NjI1OWZiYjc2ODFmNTZj
+      Nzc1NWNjOTM3SjEKB3Rhc2tfaWQSJgokYjFmNDk4MmItNGNkYi00OTUwLThmY2MtYzBkNzE3NGFj
+      NjQ2egIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '1894'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sun, 17 Nov 2024 07:10:11 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are {topic} Senior Data
+      Researcher\n. You''re a seasoned researcher with a knack for uncovering the
+      latest developments in {topic}. Known for your ability to find the most relevant
+      information and present it in a clear and concise manner.\n\nYour personal goal
+      is: Uncover cutting-edge developments in {topic}\n\nTo give my best complete
+      final answer to the task use the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: Your final answer must be the great and the
+      most complete as possible, it must be outcome described.\n\nI MUST use these
+      formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent Task:
+      Conduct a thorough research about {topic} Make sure you find any interesting
+      and relevant information given the current year is 2024.\n\n\nThis is the expect
+      criteria for your final answer: A list with 10 bullet points of the most relevant
+      information about {topic}\n\nyou MUST return the actual complete content as
+      the final answer, not a summary.\n\nBegin! This is VERY important to you, use
+      the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
+      "model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1250'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=08pKRcLhS1PDw0mYfL2jz19ac6M.T31GoiMuI5DlX6w-1731827382-1.0.1.1-UfOLu3AaIUuXP1sGzdV6oggJ1q7iMTC46t08FDhYVrKcW5YmD4CbifudOJiSgx8h0JLTwZdgk.aG05S0eAO_PQ;
+        _cfuvid=74kaPOoAcp8YRSA0XocQ1FFNksu9V0_KiWdQfo7wQuQ-1731827382509-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4RXTW8cRw69+1cQcwlgzAiS5a/oJnu1Wi3irON4N4fNwmBXc7q5rmZ1iuwejYL8
+        9wWrejSjJMBeNFAXi83H9/jRvz4DWHG7uoJV6NHCMMbN9T8/8+vvb374+hAe9MPlntvbf5x/N739
+        9GAPf1+t/UZq/kvBDrfOQhrGSMZJ6nHIhEbu9eLN5cXbF29eXpyXgyG1FP1aN9rmZdq8OH/xcnP+
+        dnP+ernYJw6kqyv49zMAgF/LXw9RWrpfXUFxU54MpIodra4ejQBWOUV/skJVVkOx1fp4GJIYSYn6
+        7psBDPUrtbBj6yGTEubQs3SAoCMF3nIASyOHaoGwTWFSSAKThDRTdtswmbF0G2o7gpZmimkcSEwB
+        pYVMkWYUA5ZtygN6gmCbMjjsM7jlmQSsJ6D7kYLV87QFhJYMOVILkdX80cU5NFOMZDAmFtM13H0T
+        I5DolAkswZjTzC0BgpORqSdRngk80plp5078VRGN1CNS7nrTM/iODAby+4EO6ejQ+grQrwgFz3Xe
+        P8GhRuOm2W/89+xn+Vk+92nqeruCO5C0g4ACnUeA0LkcAEV3lN3yrywY4br8fwX+5OIMnj9/lwm/
+        Wp/dDbDADxOKTQO8T8M4eZqfP7+Cd/uSvTVgO6MEqtlmgV8W63Cwhh5nAk+iJRhSJueDsYkEv0wN
+        W4WsytKtYcT5AHeH+0LSmDEYB4yA4xg5FNjlVSHvR0tdxrHfr6GK/x50r0YDKA9TrLbrooI0Gg/8
+        ULM25tREGrRk7IWjvr6DOzHqcjVggb8RRusDZnLA19lci4wRWIxi5I4kELiaWSZSh2cZRZ0b6B8v
+        ryuX13eAsUuZrR+0MFNygSFMGY3iHlrGTpLnAVpWQiVdw5ip5VDyOKIxiUGaLKSBFlgjZU2CkR9K
+        4pxi5wLGiKJgPQrQTBka2qZMBe+l4/1EQrvCwo1Q7vZwJ5LmmjDH+7kn2BPWIoEeFZRIQLkTz0Mp
+        p8HVfqQ+P7qk6tIo9JJi6pj0DL6ne9t0frQoN0XMMKJQrHW6Y2nBptywkAJmqimireedxNYQCdsC
+        M8GOW9IxE7aArXObZCn2dgrUVpE5QaXWVTnCdqJYGX/pGXh1Czf3I4oerr6+hb8ce8chCV1MDUbI
+        KcY0lSbw6vaIbA+ZMPSkIJ6sYwdeL9HUhuaaSf4CT2RIw+Daac/gc8962rBcmANrVROL5eRoYJIx
+        U6CWxKiFFg0XqVH2LkltTWBIIhSMZ7Z9wfmqKLtWaKHoHadj6I7wloQ21HJR2Clfa9Ap9IAK7z/d
+        /fjx07rW8VLupZgR1LAj2PWUCZxZ4+DaTbmlrKX1NIW/EpRr3OpEWoOOmL/6O8n6UtwtNd4Sl6x1
+        Xrsp7x2ScrtIppL32kH9OGIg5y+mRU4fOJJaEnqUrxYblnZSy3vA0DPNhakdDI/WtTxL+1fDJrL2
+        hYm09doaUPyfOAlmaLwmS4RuvuWsBgOKUAsDq5a+ZAk+YNY1tLnMlWYPTfJe7hNAiudStplnNAKl
+        YMl1EyM2C5SC8k1BOakhS6mp6y5zmKL5oPlYe2KFeueVp2MSLRMoRB7cc+hRuvITI0lXGT26wxN3
+        48HdGlhCnEqNzZRr291iHspALmFT4Fowx/vrUqsdstQW5M6SLIUT92toUtIisG1K7sNF/bRgixJk
+        5pxKirzJDiMGK6l466l4v28oK4Ups+3hRvrHqeM5+Mk5ZPGFZ2mgHbsX611wuq5dTIkUcmomtT/M
+        rfDE/9NKOCbl+m6z8Fo9+4ZA4VjvVONaapSkjChHOpD1qT30Qkf1raP67FU8prwsHcce7KA+Tk30
+        7eepTXlNpGCZA8zUc4h02o8OA8m1QHOKMx0VfugojxvOZEnSkCaF8eRlbMsUrWL/fZ+/+Rc0aEZ5
+        DzFJR95uav/pMXeeJpZtRrU8BddHxXtx7oA/VHbrbIXrHfrQ0MLh9aHVLjx6uLCooY5TwIN9mQRL
+        k6zGLWwnaavI8rHvHoqVT2Z72p7ogzKOvFQ1jmMZmfa4xh1mtO8nXjVPw9FpdF6WtYuUni6HoNMw
+        YOYHejI20eMtQZz0/ZJnMcp1Kywxd1VoZfllWfatnrs++s542JPGnLZpqjRhqAzNmNlJ3TLFVs9O
+        t+9M20nRl3+ZYlye//a4zsfU+W6ky/nj8y0La//FQ0/iq7taGlfl9LdnAP8pnw3Tky+Blc+y0b5Y
+        +kriDl9cvqz+VscxeTx9df5qObVkGI8Hby6/Xf+Jwy91OdeTL49V8FHcHq8eP1NwajmdHDw7gf3H
+        cP7Md4XO0v1/9/8DAAD//0KWSE5OLShJTYmHNeSQvYxQVpQK6sjhUgYPZrCDlSB5Mz4tMy89taig
+        KBPSl0oriDdPNbIwNk41TbNU4qrlAgAAAP//AwCpko/aVA4AAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e3de645a8666217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 17 Nov 2024 07:10:16 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '5537'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999711'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_220e7945d04e84ab7b58c252c98630b5
+    status:
+      code: 200
+      message: OK
+- request:
+    body: !!binary |
+      Cs4CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpQIKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKOAgoQrqG+rs9H9Iyyqr2ZU1qS4RIIWspPh5zdoVMqDFRhc2sgQ3JlYXRlZDABOeiB
+      tw7crwgYQZgvuQ7crwgYSi4KCGNyZXdfa2V5EiIKIGYzNDZhOWFkNmQ3MzA2M2UwNjc3YjE3Y2U5
+      YzUwMTc3SjEKB2NyZXdfaWQSJgokNmM4OTQ3MzctMzViYy00YWQxLWIxNjYtYWU2Nzg4YTEwOGFm
+      Si4KCHRhc2tfa2V5EiIKIGIxN2IxODhkYmYxNGY5M2E5OGU1Yjk1YWFkMzY3NTc3SjEKB3Rhc2tf
+      aWQSJgokMmNlZDRlYTQtNWI3MC00YTA3LTkxMjktNDM0NmQ0NTljODYyegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '337'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Sun, 17 Nov 2024 07:10:22 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are {topic} Reporting
+      Analyst\n. You''re a meticulous analyst with a keen eye for detail. You''re
+      known for your ability to turn complex data into clear and concise reports,
+      making it easy for others to understand and act on the information you provide.\nYour
+      personal goal is: Create detailed reports based on {topic} data analysis and
+      research findings\n\nTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      Your final answer must be the great and the most complete as possible, it must
+      be outcome described.\n\nI MUST use these formats, my job depends on it!"},
+      {"role": "user", "content": "\nCurrent Task: Review the context you got and
+      expand each topic into a full section for a report. Make sure the report is
+      detailed and contains any and all relevant information.\n\n\nThis is the expect
+      criteria for your final answer: A fully fledge reports with the mains topics,
+      each with a full section of information. Formatted as markdown without ''```''\n\nyou
+      MUST return the actual complete content as the final answer, not a summary.\n\nThis
+      is the context you''re working with:\n1. **Breakthrough in Quantum Computing**:
+      By 2024, advancements in quantum computing have led to more reliable qubit processing,
+      paving the way for practical applications in cryptography, complex system simulations,
+      and optimization problems.\n\n2. **AI Integration in Healthcare**: Artificial
+      intelligence continues to transform healthcare, with AI algorithms now more
+      accurately diagnosing diseases, predicting patient outcomes, and personalizing
+      treatment plans than ever before.\n\n3. **Renewable Energy Innovations**: The
+      year 2024 has seen significant improvements in renewable energy technologies.
+      Next-generation solar panels and wind turbines are more efficient, leading to
+      widespread adoption and reduced reliance on fossil fuels.\n\n4. **5G Expansion
+      and 6G Development**: The global rollout of 5G technology reaches near completion,
+      and research into 6G has commenced. This development promises to introduce unprecedented
+      data transfer speeds and connectivity.\n\n5. **Advances in Biotechnology**:
+      Gene-editing technologies, such as CRISPR, have advanced to a stage where genetic
+      disorders can be effectively treated, sparking ethical debates and regulatory
+      considerations.\n\n6. **Space Exploration Milestones**: The space industry achieves
+      new milestones with the establishment of permanent lunar bases and the first
+      manned missions to Mars, driven by both government and private sector collaboration.\n\n7.
+      **Sustainable Agriculture Practices**: In response to climate change challenges,
+      sustainable agriculture practices, including vertical farming and precision
+      agriculture, are gaining traction globally, boosting food production and reducing
+      environmental impact.\n\n8. **Cybersecurity Enhancements**: With increasing
+      digital threats, 2024 sees robust advancements in cybersecurity technologies,
+      including AI-driven threat detection, and enhanced data encryption methodologies.\n\n9.
+      **Transportation Innovation**: Public transportation and electric vehicle technology
+      continue to evolve with the introduction of autonomous public transit systems
+      and improvements in EV battery longevity and charging infrastructures.\n\n10.
+      **Mental Health Awareness**: A global increase in mental health awareness leads
+      to increased funding for research and the integration of digital therapies and
+      apps that provide more accessible mental health support.\n\nThese bullet points
+      summarize significant areas of development and interest in the given topic in
+      2024, highlighting the profound impacts in various fields.\n\nBegin! This is
+      VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"],
+      "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '3935'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=08pKRcLhS1PDw0mYfL2jz19ac6M.T31GoiMuI5DlX6w-1731827382-1.0.1.1-UfOLu3AaIUuXP1sGzdV6oggJ1q7iMTC46t08FDhYVrKcW5YmD4CbifudOJiSgx8h0JLTwZdgk.aG05S0eAO_PQ;
+        _cfuvid=74kaPOoAcp8YRSA0XocQ1FFNksu9V0_KiWdQfo7wQuQ-1731827382509-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA3RXS28cxxG++1cU6OuSkBRJVnijFFumBQQKRcOH6FLTXTtTUU93q6pmlyNf8jfy
+        9/JLguqZfQnIhVhuv+r1PfbPHwCuOF7dwlUY0MJY0/Xd74/87tPHr/KwHV59CMF+e1nf/P7ht+Hx
+        17/a1cZPlO5fFOxw6iaUsSYyLnlZDkJo5Lc+/+kvz9+8+Onl89dtYSyRkh/rq12/LNcvnr14ef3s
+        zfWz1+vBoXAgvbqFf/4AAPBn++sh5khPV7fwbHP4ZiRV7Onq9rgJ4EpK8m+uUJXVMC/hrouhZKPc
+        on4cytQPdgv3kMseAmboeUeA0HvogFn3JACf8y+cMcFd+//2c/6cf4R3ZaxCA2X1Iw9UixiUDB9o
+        hkcKQy6p9BwwAeYInwJTNt5ygL/RjlKpI2VT4AyefbvyR3grhF9sEA/Ll/4xYbZpbG9NxrkH3/h2
+        bmc2oNxnvxKzAcYd5kDHW7+uR8Px6IA7go4oA4aBaUdxAxXFOEwJJc1+ygYCFEIoW/g6dWxQpQRS
+        9QuEEmPHiW2+gceBFbrzeAdUqLij2G7Z4wzbIu1zFQy2lKLWxAF9RpYnzoMkUcAgRRWUdiSYIJYR
+        OesN3GcIMlcrvWAd5o3fq3SZNWWdhIDy4N9FoNyO+Fsj2VCigg1oEMqUItTiY8CY0gxCu5Im38nf
+        CCIaglKYhG2GboYRv3j+bIBpLGrAYyXZcZkUrMCAoa2jGY3V9ObYt1PxMWkBegqUWneUxylhW1lQ
+        8wQ6q9GoG9gPHIY1SBPMui0yAuc4qQmTgk5hAC/2gDJioKnVVtucjWgk7P+pT1wgj/9sTlqycQr+
+        srfGeKR2MLS88q4k7yBnoKdKwktlfUM8je0N/DKJDSRjEdpAqcYjf1u6WqV0icZjJx0Eahx0A1vO
+        3phNu66jueTYcNdRpi0bbKWM67wcZ64WR+DZqBzLpCaEY+Ls20olae8vsfJYpex8gbZbboXwwqGB
+        BkykUIVa+9IMU0Yz5IxdopsVh3f3cJ+N+uVOr8avhMmGgEINgnfSsMyYgLNRSty3YnN7xHMIRcjj
+        xlMPj5cNp8tQfdMC5z3b4E9j6ouwDaO28ixo9WSmXIUCRcpGETCESTAccRsZ+1yU242RlVBJHagO
+        lLVsoJNUVIVhGjFDwLoA2qvTzYAZ0/zNn9qhWgOCkil8nTh8SfM6B0ahTW71gZfsA71j5S6Ro8FD
+        WW6nmTaQCGMbtgLUWKZNqRfHc2E9xk26Tj4rBOGFL5xBQsmRl94m/kJO04FkGVqUyGWH2ijsLOmP
+        QpGDOTPf3UPTG3Vig5pwbniEyrtimMDFwku4LUIB9ZCZ0zWUyUIZSTcQZGrd9oCqkOPcLz/rpJqg
+        Ud/mLEcQ0jJJIMCUysJ4N3AXl0ycdDZwd//ff/9HYaVUr1AlUV91FvLxNkebx5z1QGt6DK692s1g
+        yKlIY/izaJyffHeHShHa3EXecZwwQU+ZjMMGEm9JbU4rJinvWEr2RzFBE8onc6qdvMcu5w2Tp8ga
+        unwE/fQhLkVj3Trjl3wA1ANl2jvC4OdM0s9wn3PZrYj1PY4AGFG+KOAZHaPMMBNKq7scL6HlEjvK
+        rPf87/Rk157ailotPhMVs/e+Kz7QJ2k40MIM3jVvcMk7ktb9Np065cT94Jzoo5somHDwPnmu35dk
+        eWsNC2NZVGdfJMU9R2r6VVEwJUqbg2o1JdizXzdJx5lOCc2LWgvplGzh43XPqmHe4xbnIRNbAVFb
+        gcoWDpU4kigapPahPamVKB7pgc/aEUrybHlHaW5DINxN1rCNF5ajCcmB0/pUOkeTewRnwuKIUuUE
+        24mS3sAfHEmrEMZTgcp21fHzTjoBnEqbZpeDSilR9GnPxV1WOm++E8Xa2UWuuskWwe2l7JsKXAz2
+        iDl604+6d+0aTMaecybVw9S+eg8/P1XM6rH65tfvz91bG9zHgZYJ3bP52dYggkwo16shpmNxSkpl
+        Mk/71fuzZm+AXH480i2qkTRRkUy2tulEmosHS64vObcu+Uj6u83LNJw43UmGyD3bpefSjVc2TY2R
+        78tju1dHFIM22py3gmoyBZvEMfVASihOyo6C15dBY/JuuoJGkj3OGxi4uQX7TqmaoVpkkOQ8pYsk
+        zsXoBv4YKMN2WtxZY8S48QBYmzMJfq8V0Kk24007ykuFVnDF7/L+f3ZvtWDjlA++9GIWPcrtYnZO
+        TfIGd5gd2jZce6+WHwGRfLSa/m4nr+AFrpp48TiStM07FpsaYrDR/+K3qPGCvzolE7weuB+uI205
+        N+GA9dfL6n4490fLcsYpb7mcMYlvuM+rx+gulkb84n7yDNNuMaPzIWmlsJTL0U2ZrsnFy9M/L1DL
+        6t3D/aePDwcyuTDlLn/7o9aPJbaXloqsLGUcjr5144R2ZJ+mNP7kYVtkLRL9h8KZg4tEI0WYctve
+        fBx8co98YW9KpQxThUx7b6BgbcYZqrPUyQQdqEONBciGxi6RukYYobj1aI5zsThrXEvHOi6Ue85E
+        rsbfq/1CdOf1b1dfxJip+V5DoxanUO8/E4rMsBUcaV9cIJ2IYxRSPU21W950Kmxe41scwQa0BCYn
+        g1zEzfMabuT/AQAA//+MWbFu5DYQ7f0VhKsEWC9ygH1BSuPgIoWBQxJcFywoaSQxpkiFpORscf8e
+        vBlS4q7tIOUuJZKaGb5573FFNaZzqaLfZ90SQM/63EWfjaWYPBoPnpEHqHogkG5H3vurGgktc1O1
+        B+7ogts4MxSRHRNHRk/fg+9M2uEHaArvG8/ZxekAqtpryAXmMuBsoK1NZIwrZ1Iar7DbelulFrta
+        bDPhzk2VufnUIEGL9Dzd+KIhGkqvEMqDXylw21CRP1wPRUqA8ASzIlOR2uQBDylj17MPhDcPQoZN
+        TD5wjTtHnZpMjLxK8upZh6gCzYEit3A1ebfkNmVJz6wWOJPxOvAHxRqHody4VduF+0LcjQbjoqQD
+        m828dwh+cR3qKIeRYSovQSlZktxIIn6jTn212lE6qlIhSyxqST0OAeYBT/FVNH4uk8fJdDFlMZel
+        XDuC/riB2UlrDY48/nQDHbhcVCREtnRLmuZRs5xxKlar6mrVuay6Exm0N1LM5VhB6DBtoGX+XgqB
+        mvQ/ZmJ4W5Jhwp0zXHF3HJSoXslaltuMYUwFqh3wZAuKF8rN5WbHQoqBIfmij0m1wc/qbMh2rHUs
+        qck4DL3lKL33aQ4GWpuhbPvQnQBlu6P3vrtwKxrvs4oJvhC0DdZGsjMwmVaD8OsOAEBXi5tp1i3q
+        JgI34OGJNk1BF0Tb4pqdlQIgX84NJsy7eapZGddF3GhJGoHWjKnJuIX5JbH98B/GFtNe3bFgay+W
+        umhK3cJ6CEV1vJAaxqnHX++6AKKXd1AErXfS4Ik78h0bI4Hi7B1zOl9hLa98B9ugfYmHj+yVdbFg
+        4MUwe/rQliq73jAN35RtKD3A/0qKJgqDcA8OG5/+IsQj+AfrUeN2o2Gz0oBOMQu8zGBE4uR1SkJA
+        0ES2FXZW0SKOnS6MDRUBcVPS/gfeBRGTpfeQC0e+HK0ISEl+bmqcaak1BoSGRKtb7Tq0kl0LNj6N
+        al4aa1rZuEmbx8FfmgWbWmk0LSyfH56+xR8ZJkBm96OBPrAk7/yERvDBlOSC4S63hEaDaGbN3pyV
+        73vu9zs15/U3WZaCXskqUTybvcdVApGv8SDiMFBMRWeITqPSKY7qi3ftEgKhwg7q6VsdQzG7YJ8g
+        buay2hv2aM7KYoG1yNd21FJNV4T/UIiFwIcwLGXNZFLlrmU79G2ItdTVuoehxu2s+YopPGmIpVJA
+        z4I8YrOpx1cdWIkJaADzwH3SeK4beqEZ0ASYsagsw31AZTATCqR0mfLCkso6kxjzRen0i+NRkfmo
+        xkq36jlt5vUOZCCThRRcrTrPW2tK3tuYm3YW77plvleiVdk/1xNlnXORoDovUNIVOtdOkJTwUT3G
+        qzkbHYJh052FJQqSrwTExiE36IFynCVK8HA99Kmcyrwn4E7VP0SCykJonXf5EMOWvfBUAanBTLB4
+        8oZ4vzvRPWZ9HUm90PmKygm4rTpwifbSVEtBsCKNbMFe+q8rwTWX+qilbDbLhRgLWYacxR0EFwPI
+        7aVQyMdIGE3mFK/GWhVHPRNXjpCrY335FKhfosbdl1uszf9/326zrB/gn8c8vv0P+RfHE5LgHW6u
+        YvLzLY9+v1HqT741Wy4uwm7n4Kc5nZJ/IYcJP/9yL/Pd7vd0++innz5/ysMJtmg18vPDw+GdKU8d
+        wXmM1dXbbQsp0O3v7vd0eumMrwZuqg9/u6H35paPN274P9PvA21Lc6LuNGdHuP7o/bFAf3FXe/+x
+        LdC84Vs5UafeuIECkzSkpJ9P9w9t/3Dfkabbm+83/wIAAP//AwCS6QzxVR0AAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8e3de6697f976217-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 17 Nov 2024 07:10:27 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '10658'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999045'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 1ms
+      x-request-id:
+      - req_f0af67637da5bc0e6b11fc3e5db59f62
+    status:
+      code: 200
+      message: OK
+version: 1