### Project Setup and Execution Commands

Source: https://context7.com/crewaiinc/crewai-examples/llms.txt

Provides commands for cloning the CrewAI examples repository, installing dependencies using UV or Poetry, configuring environment variables, and running the marketing posts application.

```bash
# Clone and navigate to example
git clone https://github.com/crewAIInc/crewAI-examples.git
cd crewAI-examples/crews/marketing_strategy

# Install dependencies with UV (recommended)
uv sync

# Or with Poetry
poetry lock && poetry install

# Configure environment variables
cp .env.example .env
# Edit .env with your API keys:
# OPENAI_API_KEY=your_openai_key
# SERPER_API_KEY=your_serper_key

# Run the crew
poetry run marketing_posts
# Or with UV
uv run python src/marketing_posts/main.py

# For Flows, use crewai CLI
cd flows/self_evaluation_loop_flow
crewai install
crewai flow kickoff

# Generate flow visualization
crewai flow plot
```

--------------------------------

### Install Dependencies with UV

Source: https://github.com/crewaiinc/crewai-examples/blob/main/README.md

Install all project dependencies and set up the virtual environment using the UV package manager. This command ensures all necessary libraries are available for the example to run.

```bash
uv sync  # Installs all dependencies and creates virtual environment
```

--------------------------------

### Install Weaviate Client

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/industry-agents/industry-specialized-agents.ipynb

Installs the specified version of the weaviate-client library. Use this to ensure compatibility with the example.

```python
!pip install --quiet weaviate-client==4.15.4
```

--------------------------------

### Navigate to Specific Example Directory

Source: https://github.com/crewaiinc/crewai-examples/blob/main/README.md

After cloning the repository, navigate into the directory of the specific example you wish to explore. Replace 'crews/marketing_strategy' with the path to your chosen example.

```bash
cd crews/marketing_strategy  # or any other example
```

--------------------------------

### Setup NVIDIA API Key

Source: https://github.com/crewaiinc/crewai-examples/blob/main/integrations/nvidia_models/marketing_strategy/marketing_posts.ipynb

Sets up the NVIDIA API key from environment variables or prompts the user for input. Asserts that the key starts with 'nvapi-'.

```python
import getpass
import os

# del os.environ['NVIDIA_API_KEY']  ## delete key and reset
if os.environ.get("NVIDIA_API_KEY", "").startswith("nvapi-"):
    print("Valid NVIDIA_API_KEY already in environment. Delete to reset")
else:
    nvapi_key = getpass.getpass("NVAPI Key (starts with nvapi-): ")
    assert nvapi_key.startswith(
        "nvapi-"
    ), f"{nvapi_key[:5]}... is not a valid key"
    os.environ["NVIDIA_API_KEY"] = nvapi_key
```

--------------------------------

### Setup RAG Chain with LCEL

Source: https://github.com/crewaiinc/crewai-examples/blob/main/notebooks/Coding Assistant/coding_assistant_eval.ipynb

This example outlines the setup for a Retrieval-Augmented Generation (RAG) chain using LCEL. It involves defining retrievers, prompts, and LLMs to fetch relevant documents and generate answers.

```python
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.vectorstores import Chroma
from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain_core.runnables import RunnablePassthrough
from langchain_core.prompts import ChatPromptTemplate
from langchain.text_splitter import RecursiveCharacterTextSplitter

# 1. Load documents
loader = WebBaseLoader("https://docs.smith.langchain.com")
docs = loader.load()

# 2. Split documents
text_splitter = RecursiveCharacterTextSplitter()
chunks = text_splitter.split_documents(docs)

# 3. Create embeddings and vector store
vectorstore = Chroma.from_documents(chunks, OpenAIEmbeddings())
retriever = vectorstore.as_retriever()

# 4. Setup LLM and prompt
llm = ChatOpenAI(model="gpt-3.5-turbo")
prompt = ChatPromptTemplate.from_template("""
Answer the question based only on the following context:
{context}

Question: {question}
"""")

# 5. Define the RAG chain
def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)

rag_chain = (
    {
        "context": retriever | format_docs,
        "question": RunnablePassthrough(),
    }
    | prompt
    | llm
    | StrOutputKey("answer") # Assuming StrOutputKey is defined or using .content
)

# Example usage:
# print(rag_chain.invoke("What is LangSmith?"))
```

--------------------------------

### Install Marketing Posts Package

Source: https://github.com/crewaiinc/crewai-examples/blob/main/integrations/nvidia_models/marketing_strategy/marketing_posts.ipynb

Installs the necessary package for generating marketing posts.

```python
%pip install --upgrade --quiet marketing_posts
```

--------------------------------

### Install Dependencies with Make

Source: https://github.com/crewaiinc/crewai-examples/blob/main/integrations/nvidia_models/intro/README.md

Run this command to install the necessary dependencies for the project. Ensure you have a Makefile configured.

```bash
make install
```

--------------------------------

### Install Groq

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Install the Groq Python package using pip. Ensure your Python environment is set up.

```bash
pip install groq
```

--------------------------------

### Install Dependencies with Poetry

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/match_profile_to_positions/README.md

Install project dependencies using Poetry. Ensure you have Poetry installed and run this command in your project's root directory.

```bash
poetry lock && poetry install
```

--------------------------------

### Clone CrewAI Examples Repository

Source: https://github.com/crewaiinc/crewai-examples/blob/main/README.md

Use this bash command to clone the CrewAI examples repository to your local machine. This is the first step to accessing and running the provided examples.

```bash
git clone https://github.com/crewAIInc/crewAI-examples.git
cd crewAI-examples
```

--------------------------------

### Install Git on Linux (Ubuntu)

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Install Git on Ubuntu systems using the apt package manager.

```sh
sudo apt install git
```

--------------------------------

### CrewAI Agent Started Log

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/industry-agents/industry-specialized-agents.ipynb

Example log output showing an agent starting a task, including the agent's role and the specific task assigned. This log is part of the verbose output during CrewAI execution.

```text
Result:\n╭─╮╭─╮────────────────────────────────────────────── 🤖 Agent Started ───────────────────────────────────────────────╭─╮\n│ │                                                                                                                 │\n│   Agent: Industry researcher focused on biomedical trends and their applications in AI                           │\n│                                                                                                                 │\n│   Task:                                                                                                         │\n│         Conduct a thorough research about MUVERA                                                               │\n│         Make sure you find any interesting and relevant information using the web and Weaviate blogs.          │\n│                                                                                                                │\n│                                                                                                                 │\n╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
```

--------------------------------

### Install and Configure CrewAI

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Installs the CrewAI library and sets up initial configuration for agent roles, capabilities, and goals. Ensure you have Python and pip installed.

```python
# Install CrewAI
!pip install crewai

# Configure Settings
crewai_config = {
    'agent_roles': ['Data Analyst', 'Manager'],
    'agent_capabilities': ['data_analysis', 'task_management'],
    'goals': ['generate_insights', 'optimize_team_performance']
}

# Initialize Agents
data_analyst_agent = CrewAIAgent(role='Data Analyst')
manager_agent = CrewAIAgent(role='Manager')
```

--------------------------------

### Install Project Dependencies with UV

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/meta_quest_knowledge/README.md

Navigate to your project directory and use UV to install the project's dependencies. This command can also lock dependencies.

```bash
crewai install
```

--------------------------------

### Install UV Package Manager

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/meta_quest_knowledge/README.md

Install the UV package manager, which is recommended for dependency management in this project. Ensure you have Python 3.10 to 3.13 installed.

```bash
pip install uv
```

--------------------------------

### Initialize CrewAI and Groq

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Initialize CrewAI and Groq with their respective API keys. This setup is necessary before using their services.

```python
import crewai
import groq

crewai.init(api_key='YOUR_CREWAI_API_KEY')
groq.init(api_key='YOUR_GROQ_API_KEY')
```

--------------------------------

### Install Python, venv, and pip on Linux (Ubuntu)

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Update package lists and install Python, the virtual environment module, and pip on Ubuntu systems.

```sh
sudo apt update
sudo apt install python3 python3-venv python3-pip
```

--------------------------------

### Stock Analysis Crew Setup

Source: https://context7.com/crewaiinc/crewai-examples/llms.txt

Initializes a CrewAI setup for financial analysis, integrating custom SEC filing tools. It loads environment variables and configures an LLM using Ollama.

```python
from crewai import Agent, Crew, Process, Task
from crewai.project import CrewBase, agent, crew, task
from crewai_tools import WebsiteSearchTool, ScrapeWebsiteTool
from tools.calculator_tool import CalculatorTool
from tools.sec_tools import SEC10KTool, SEC10QTool
from dotenv import load_dotenv
from langchain.llms import Ollama

load_dotenv()
```

--------------------------------

### Run CrewAI Application (Windows)

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Starts the CrewAI application after installation and dependency setup.

```sh
python run.py
```

--------------------------------

### Copy and Configure Environment File

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/instagram_post/README.md

Copy the example environment file and set up necessary environment variables for tools like Browseless and Serper.

```bash
cp .env.example .env
```

--------------------------------

### Install CrewAI

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/industry-agents/industry-specialized-agents.ipynb

Installs the specified version of the crewai library. Ensure this version is used for the example to function correctly.

```python
!pip install --quiet crewai==0.134.0
```

--------------------------------

### Customer Support Agent Setup

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Initialize a Support Agent with a role, add query handling capability, and set a goal to resolve customer issues.

```python
support_agent = CrewAIAgent(role='Support Agent')
support_agent.add_capability('query_handling')
support_agent.set_goal('resolve_customer_issues')
```

--------------------------------

### Configure and Run Stock Analysis Script

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/stock_analysis/README.md

Instructions for setting up environment variables, installing dependencies, and executing the main Python script for stock analysis.

```bash
poetry install --no-root
```

```bash
poetry run python3 main.py
```

```bash
python main.py
```

--------------------------------

### Define a Task for an Agent

Source: https://github.com/crewaiinc/crewai-examples/blob/main/notebooks/Coding Assistant/coding_assistant_eval.ipynb

This example defines a task for an agent, specifying the description, expected output, and the agent assigned to it. The 'expected_output' helps guide the agent's response.

```python
from crewai import Task

# Define a task for the researcher agent
research_task = Task(
    description='Identify the top 5 emerging trends in AI and machine learning in 2024.',
    expected_output='A list of the top 5 emerging trends with a brief explanation for each.',
    agent=researcher
)
```

--------------------------------

### LCEL Chain Output as String

Source: https://github.com/crewaiinc/crewai-examples/blob/main/notebooks/Coding Assistant/coding_assistant_eval.ipynb

This example demonstrates how to ensure the output of an LCEL chain is a string. By default, LLM outputs are often Pydantic objects or similar; this shows how to get a plain string.

```python
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI

# Setup LLM and prompt
llm = ChatOpenAI(model="gpt-3.5-turbo")
prompt = ChatPromptTemplate.from_template("Write a short sentence about {topic}.")

# Create the chain
chain = prompt | llm

# Invoke the chain and get the string output
# The .invoke() method on a chain with an LLM typically returns a AIMessage object.
# To get the string content, you access the 'content' attribute.
result_message = chain.invoke({"topic": "the sun"})
result_string = result_message.content

print(f"Output as string: {result_string}")
```

--------------------------------

### Install CrewAI

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Install the latest version of CrewAI using pip. Ensure you have Python and pip installed.

```bash
pip install crewai
```

--------------------------------

### Manager Agent Setup

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Initialize a Manager Agent with a role, add performance tracking capability, and set a goal to improve support efficiency.

```python
manager_agent = CrewAIAgent(role='Manager')
manager_agent.add_capability('performance_tracking')
manager_agent.set_goal('improve_support_efficiency')
```

--------------------------------

### Configure Environment Variables

Source: https://github.com/crewaiinc/crewai-examples/blob/main/integrations/azure_model/README.md

Copy the example environment file and set your Azure OpenAI model, endpoint URL, and API key.

```bash
.env.example
```

--------------------------------

### Run the Book Writing Flow

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/write_a_book_with_flows/README.md

Execute the book writing flow from your project's root folder to start the AI agent orchestration.

```bash
crewai flow kickoff
```

--------------------------------

### Clone CrewAI Repository and Install Dependencies (Windows)

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Clones the CrewAI GitHub repository and installs necessary Python packages. This step requires Git to be installed.

```sh
git clone https://github.com/crewAIInc/crewAI.git
cd crewAI
```

```sh
pip install -r requirements.txt
```

--------------------------------

### Langgraph Workflow Setup

Source: https://github.com/crewaiinc/crewai-examples/blob/main/notebooks/Coding Assistant/coding_assistant_eval.ipynb

This snippet demonstrates how to set up a Langgraph workflow by defining the state, creating a StateGraph, and adding nodes for 'generate', 'check_code', and 'reflect'.

```python
from langgraph.graph import END, StateGraph, START

workflow = StateGraph(GraphState)

# Define the nodes
workflow.add_node("generate", generate)  # generation solution
workflow.add_node("check_code", code_check)  # check code
workflow.add_node("reflect", reflect)  # reflect
```

--------------------------------

### Install CrewAI

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/email_auto_responder_flow/README.md

Install the CrewAI library using pip. Ensure you have Python 3.10 or higher.

```bash
pip install crewai==0.130.0
```

--------------------------------

### Start CrewAI Agent

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Initiate the agent's processing tasks by calling the `start()` method.

```python
agent.start()
```

--------------------------------

### Data Analyst Agent Setup

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Initialize a Data Analyst Agent with a role, add data analysis capability, and set a goal to generate insights.

```python
data_analyst_agent = CrewAIAgent(role='Data Analyst')
data_analyst_agent.add_capability('data_analysis')
data_analyst_agent.set_goal('generate_insights')
```

--------------------------------

### YAML Agent Configuration Example

Source: https://context7.com/crewaiinc/crewai-examples/llms.txt

Shows how agents are defined in YAML files using role, goal, and backstory properties. This allows for easy customization without modifying Python code.

```yaml
role: Lead Market Analyst
goal: Identify emerging market trends and provide data-driven insights.
backstory: You are an expert market analyst with a keen eye for detail and a deep understanding of consumer behavior.
verbose: true
allow_delegation: false
```

--------------------------------

### Install CrewAI

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Install the CrewAI library using pip. Use the '[tools]' extra for additional functionalities.

```sh
pip install crewai
```

```sh
pip install 'crewai[tools]'
```

--------------------------------

### Example CrewAI Configuration File

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Define custom tool settings, database URIs, API keys, and user preferences in a `config.py` file.

```python
# config.py
DATABASE_URI = 'your_database_uri'
API_KEY = 'your_api_key'
USER_PREFERENCES = {
    'theme': 'dark',
    'notifications': True,
}
```

--------------------------------

### Install CrewAI Dependencies

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Install all required Python packages for CrewAI using the provided requirements file.

```sh
pip install -r requirements.txt
```

--------------------------------

### Initialize CrewAI Agent with Configuration

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Create an instance of the CrewAI class, passing configuration parameters like database URI, API key, and user preferences imported from `config.py`.

```python
from crewai import CrewAI
from config import DATABASE_URI, API_KEY, USER_PREFERENCES

agent = CrewAI(database_uri=DATABASE_URI, api_key=API_KEY, user_preferences=USER_PREFERENCES)
```

--------------------------------

### Install Git with Homebrew

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Install Git on macOS using Homebrew. Git is necessary for cloning the CrewAI repository.

```sh
brew install git
```

--------------------------------

### Initialize Serper Search Tool

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/industry-agents/industry-specialized-agents.ipynb

Initializes the SerperDevTool for web searching. This tool requires a SERPER_API_KEY to be set in the environment variables.

```python
search_tool = SerperDevTool()
```

--------------------------------

### Install Python with Homebrew

Source: https://github.com/crewaiinc/crewai-examples/blob/main/flows/lead-score-flow/Automating_Tasks_with_CrewAI.md

Use Homebrew to install the latest version of Python on macOS. This is recommended over the pre-installed version.

```sh
brew install python
```

--------------------------------

### Install Dependencies with Poetry

Source: https://github.com/crewaiinc/crewai-examples/blob/main/crews/instagram_post/README.md

Install project dependencies using Poetry. Ensure you have CrewAI version 0.130.0 or later.

```bash
poetry install --no-root
```