### Install Arklex AI

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Installs the Arklex AI library with different feature sets. Users can choose a basic installation or include support for vector databases, e-commerce integrations, CRM integrations, or all features.

```bash
pip install arklex

pip install arklex[milvus]

pip install arklex[shopify]

pip install arklex[hubspot]

pip install arklex[all]
```

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

### Getting Started with Arklex AI

Source: https://github.com/arklexai/agent-first-organization/blob/main/project_improvements/DOCUMENTATION_IMPROVEMENTS.md

Provides a step-by-step guide to setting up the Arklex AI development environment. Includes prerequisites, installation steps, environment configuration, database setup, and starting the application.

```bash
git clone https://github.com/your-org/arklex-ai.git
cd arklex-ai
```

```bash
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
```

```bash
pip install -r requirements.txt
pip install -r requirements-dev.txt
```

```env
# Database
DATABASE_URL=postgresql://user:password@localhost:5432/arklex

# API Keys
OPENAI_API_KEY=your-openai-api-key
ANTHROPIC_API_KEY=your-anthropic-api-key

# Security
SECRET_KEY=your-secret-key

# Environment
ENVIRONMENT=development
DEBUG=true
```

```bash
# Create database
createdb arklex

# Run migrations
alembic upgrade head
```

```bash
# Development server
uvicorn arklex.main:app --reload --host 0.0.0.0 --port 8000

# Or with Docker
docker-compose up
```

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

### Contribution Guidelines - Getting Started

Source: https://github.com/arklexai/agent-first-organization/blob/main/project_improvements/DOCUMENTATION_IMPROVEMENTS.md

Provides essential steps for new contributors to set up their development environment, including forking the repository, cloning, installing dependencies, and setting up pre-commit hooks.

```bash
# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt
pip install -r requirements-dev.txt

# Set up pre-commit hooks
pre-commit install
```

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

### Verify Arklex AI Installation

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Confirms that the Arklex AI library has been successfully installed by importing it and printing a success message.

```python
python -c "import arklex; print('Arklex AI installed successfully!')"
```

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

### Install and Setup Arklex AI

Source: https://github.com/arklexai/agent-first-organization/blob/main/README.md

Instructions for installing the Arklex library via pip, setting up environment variables with API keys, cloning the repository, and installing the package in editable mode.

```bash
pip install arklex
```

```bash
echo "OPENAI_API_KEY=your_key_here" > .env
```

```bash
git clone https://github.com/arklexai/Agent-First-Organization.git
cd Agent-First-Organization
pip install -e .
```

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

### Reinstall with Dependencies

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Troubleshoots import errors by uninstalling and then reinstalling the `arklex` package with all its dependencies. This ensures all necessary components are correctly installed.

```bash
# Reinstall with all dependencies
pip uninstall arklex
pip install arklex[all]
```

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

### Install Arklex

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Quickstart.md

Installs the Arklex library using pip within the activated virtual environment. This command fetches and installs the latest stable version of Arklex.

```bash
pip install arklex
```

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

### Copy Example Agent Configuration

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Quickstart.md

Copies the existing customer service agent configuration directory to a new location, allowing for customization without altering the original example.

```bash
cp -r examples/customer_service examples/customer_service_copy
```

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

### Start API Server

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Initiates the agent as a web API service. This command starts a server that exposes the agent's functionalities through API endpoints, typically using a specified input directory for agent configuration.

```bash
python model_api.py --input-dir ./my_first_agent
```

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

### Running Arklex AI Documentation Locally

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/README.md

Navigates to the docs directory, installs dependencies, and starts the Docusaurus development server.

```bash
# Navigate to docs directory
cd docs

# Install dependencies
npm install

# Start development server
npm run start
```

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

### Test API Endpoints

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Demonstrates how to interact with the deployed agent API using `curl`. It includes examples for testing the health endpoint and sending a POST request to the chat endpoint with a JSON payload.

```bash
# Test health endpoint
curl http://localhost:8000/health

# Test chat endpoint
curl -X POST http://localhost:8000/chat \
  -H "Content-Type: application/json" \
  -d '{"query": "Hello, how are you?"}'
```

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

### Local Development Setup (Node.js)

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/README.md

Installs Node.js using nvm, verifies versions, and sets up the development environment for Arklex AI documentation.

```bash
# installs nvm (Node Version Manager)
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.0/install.sh | bash

# download and install Node.js (you may need to restart the terminal)
nvm install 22

# verifies the right Node.js version is in the environment
node -v # should print `v22.11.0`

# verifies the right npm version is in the environment
npm -v # should print `10.9.0`
```

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

### Start Model API Server

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Quickstart.md

Starts a local API server for the model, which defaults to using the OpenAI API with the 'gpt-4o-mini' model. This server is used for evaluation purposes.

```bash
python model_api.py --input-dir ./examples/customer_service_copy
```

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

### Run Example Customer Service Agent

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Quickstart.md

Executes the provided Python script to run a pre-built customer service agent. The '--input-dir' flag specifies the directory containing the agent's configuration and data.

```bash
python run.py --input-dir ./examples/customer_service
```

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

### Prepare Documents for RAG Agent

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Creates a 'documents' directory to store files (PDF, TXT, DOC) that will be used for Retrieval-Augmented Generation (RAG) by an Arklex AI agent.

```bash
mkdir -p documents
# Add your PDF, TXT, or DOC files to this directory
```

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

### Run Basic Agent Tests

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Executes a set of predefined test queries against the agent. This command requires the agent's configuration file, input directory, and a comma-separated string of test queries.

```bash
python eval.py \
  --config my_first_agent_config.json \
  --input-dir ./my_first_agent \
  --test_queries "Hello,What is AI?,How do you work?"
```

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

### Test Arklex AI Configuration

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Tests the Arklex AI configuration by initializing an Orchestrator with specified LLM provider, model, and API key, printing a success message upon successful initialization.

```python
import os
from arklex import Orchestrator

orchestrator = Orchestrator(
    llm_provider='openai',
    model='gpt-4o-mini',
    api_key=os.getenv('OPENAI_API_KEY')
)
print('Configuration test successful!')
```

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

### Run Arklex AI Agent

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Executes an Arklex AI agent with specified input directory, LLM provider, model, and a user query. It also provides commands for running an evaluation against a model API server.

```bash
python run.py \
  --input-dir ./my_first_agent \
  --llm_provider openai \
  --model gpt-4o-mini \
  --query "Hello! What can you help me with?"

# For evaluation and testing, you can also use the model API server:
# 1. Start the model API server (defaults to OpenAI with "gpt-4o-mini" model):
python model_api.py --input-dir ./examples/customer_service

# 2. Run evaluation (in a separate terminal):
python eval.py --model_api http://127.0.0.1:8000/eval/chat \
  --config "examples/customer_service/customer_service_config.json" \
  --documents_dir "examples/customer_service" \
  --model "claude-3-haiku-20240307" \
  --llm_provider "anthropic" \
  --task "all"
```

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

### Start Model API Server

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/CONFIGURATION.md

This command starts the model API server, which defaults to using the OpenAI provider with the 'gpt-4o-mini' model. It's used for evaluation and testing purposes.

```bash
python model_api.py --input-dir ./examples/customer_service
```

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

### Verify API Key

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Ensures the OpenAI API key is correctly set in the environment variables. This involves exporting the key and then echoing it to confirm its presence.

```bash
# Verify your API key is set correctly
export OPENAI_API_KEY="your-actual-key-here"
echo $OPENAI_API_KEY  # Should display your key
```

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

### Create Agent Configuration File

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Defines the structure for an agent's configuration, including its name, description, version, orchestrator settings (LLM provider, model, temperature, max tokens), worker configurations (RAG, database), and a list of tools.

```json
{
  "name": "My First Agent",
  "description": "A simple agent that can answer questions",
  "version": "1.0.0",
  "orchestrator": {
    "llm_provider": "openai",
    "model": "gpt-4o-mini",
    "temperature": 0.7,
    "max_tokens": 1000
  },
  "workers": {
    "rag_worker": {
      "enabled": false
    },
    "database_worker": {
      "enabled": false
    }
  },
  "tools": []
}
```

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

### Load and Process Orchestrator Configuration

Source: https://github.com/arklexai/agent-first-organization/blob/main/arklex/orchestrator/examples/README.md

Demonstrates how to load a JSON orchestrator configuration file and initialize the Arklex Orchestrator to start processing. This involves reading the configuration from a file and passing it to the Orchestrator constructor.

```python
from arklex.orchestrator import Orchestrator
import json

# Load example configuration
with open("ecommerce_assistant.json", "r") as f:
    config = json.load(f)

# Initialize orchestrator
orchestrator = Orchestrator(config)

# Start processing
orchestrator.process()
```

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

### Project Documentation Links

Source: https://github.com/arklexai/agent-first-organization/blob/main/README.md

Provides links to various documentation resources for the Agent-First Organization project, including full documentation, quick start, API reference, architecture, and deployment guides.

```markdown
- 📚 **[Full Documentation](https://arklexai.github.io/Agent-First-Organization/)
- 🚀 **[Quick Start](docs/QUICKSTART.md)
- 🛠️ **[API Reference](docs/API.md)
- 🏗️ **[Architecture](docs/ARCHITECTURE.md)
- 🚀 **[Deployment](docs/DEPLOYMENT.md)
```

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

### Generate and Run RAG Agent

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Commands to generate a RAG agent using a configuration file and then run the agent with a specific query. It requires specifying the configuration, output directory, LLM provider, and model.

```bash
# Generate the agent
python create.py \
  --config rag_agent_config.json \
  --output-dir ./rag_agent \
  --llm_provider openai \
  --model gpt-4o-mini

# Run with document query
python run.py \
  --input-dir ./rag_agent \
  --llm_provider openai \
  --model gpt-4o-mini \
  --query "What information do you have about machine learning?"
```

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

### Customize Agent Configuration (JSON Example)

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Quickstart.md

Illustrates a JSON configuration snippet for an Arklex agent, highlighting fields like 'domain', 'intro', 'task_docs', and 'rag_docs' that can be modified for custom agents. The 'source' can be a URL or a local file path, and 'num' specifies the number of documents to fetch.

```json
{
    "domain": "AI agents",
    "intro": "The Arklex AI's core technology is an advanced general-purpose AI Agent platform, which reduces hard-code engineering effort for developers and provides personalized experiences to end users.",
    "task_docs": [
        {
            "source": "https://www.arklex.ai/",
            "type": "url",
            "num": 20
        }
    ],
    "rag_docs": [
        {
            "source": "https://www.arklex.ai/",
            "type": "url",
            "num": 20
        }
    ],...
}
```

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

### Start Model API

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/tutorials/roleplay-agent.md

Command to start the API for the Agent, defaulting to OpenAI with the 'gpt-4o-mini' model.

```bash
python model_api.py --input-dir ./examples/roleplay
```

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

### Start Model API

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/tutorials/booking-service.md

Starts the API for the Agent, defaulting to OpenAI with the 'gpt-4o-mini' model. The API will be accessible on port 8000.

```bash
python model_api.py --input-dir ./examples/booking_system
```

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

### Run Tool-Enabled Agent

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Executes an agent that has been configured with external tools. The command specifies the input directory, LLM provider, model, and the user's query, which may involve invoking the integrated tools.

```bash
python run.py \
  --input-dir ./tool_agent \
  --llm_provider openai \
  --model gpt-4o-mini \
  --query "What's 15% of 250? Also, what's the latest news about AI?"
```

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

### Generate Agent Workflow

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Generates an agent's workflow using a configuration file, output directory, LLM provider, and model. This command is used to create the necessary files and structure for running an agent.

```bash
python create.py \
  --config my_first_agent_config.json \
  --output-dir ./my_first_agent \
  --llm_provider openai \
  --model gpt-4o-mini
```

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

### Install Arklex Package

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/intro.md

Installs the Arklex Python package using pip.

```bash
pip install arklex
```

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

### Set Up Python Virtual Environment

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Quickstart.md

Navigates into the cloned repository and creates a Python virtual environment named '.venv' for project dependencies.

```bash
cd Agent-First-Organization
python3 -m venv .venv
```

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

### Browser Worker JSON Configuration Example

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/CONFIGURATION.md

Example JSON configuration for the browser worker.

```json
{
  "browser_worker": {
    "enabled": false,
    "headless": true,
    "timeout": 30,
    "user_agent": "Mozilla/5.0 (compatible; ArklexBot/1.0)",
    "proxy": "http://proxy:8080",
    "viewport_width": 1920,
    "viewport_height": 1080,
    "max_concurrent_browsers": 3
  }
}
```

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

### Start Docusaurus Development Server

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Example/intro.md

Navigates to the newly created website directory and starts the local development server. The site will be available at http://localhost:3000/ and reloads automatically on changes.

```bash
cd my-website
npm run start
```

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

### RAG Worker JSON Configuration Example

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/CONFIGURATION.md

Example JSON configuration for the RAG worker.

```json
{
  "rag_worker": {
    "enabled": true,
    "vector_db": "milvus",
    "collection_name": "documents",
    "embedding_model": "text-embedding-ada-002",
    "top_k": 5,
    "similarity_threshold": 0.7,
    "cache_enabled": true,
    "cache_ttl": 3600,
    "batch_size": 10,
    "max_concurrent_requests": 5
  }
}
```

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

### Database Worker JSON Configuration Example

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/CONFIGURATION.md

Example JSON configuration for the database worker.

```json
{
  "database_worker": {
    "enabled": true,
    "connection_string": "mysql://user:pass@localhost:3306/arklex_db",
    "pool_size": 10,
    "max_overflow": 20,
    "echo": false,
    "ssl_mode": "require",
    "connection_timeout": 10,
    "query_timeout": 30
  }
}
```

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

### Resolve Package Installation Failures

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/TROUBLESHOOTING.md

Addresses errors encountered during `pip install arklex`, often due to missing system dependencies. Provides commands to install necessary build tools and libraries on Ubuntu/Debian, macOS, and Windows before installing the package.

```bash
# Install system dependencies first
# On Ubuntu/Debian:
sudo apt-get update
sudo apt-get install -y gcc g++ python3-dev

# On macOS:
xcode-select --install

# On Windows:
# Install Visual Studio Build Tools

# Then install arklex
pip install arklex

# If still failing, try with specific version
pip install arklex==1.0.0
```

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

### Run Example Agent

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/intro.md

Executes an example agent from the customer service directory using the Arklex framework. Requires setting the OpenAI API key.

```bash
python run.py --input-dir ./examples/customer_service
```

```bash
export OPENAI_API_KEY=sk-...
```

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

### Create and Run an Agent

Source: https://github.com/arklexai/agent-first-organization/blob/main/README.md

Guides on creating a new AI agent using a configuration file and running the agent with specified LLM provider and model.

```bash
python create.py \
  --config ./examples/customer_service/customer_service_config.json \
  --output-dir ./examples/customer_service \
  --llm_provider openai \
  --model gpt-4o
```

```bash
python run.py \
  --input-dir ./examples/customer_service \
  --llm_provider openai \
  --model gpt-4o
```

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

### Anthropic Orchestrator Configuration

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/CONFIGURATION.md

Example JSON configuration for the orchestrator when using Anthropic models.

```json
{
  "orchestrator": {
    "llm_provider": "anthropic",
    "model": "claude-3-5-sonnet-20241022",
    "temperature": 0.7,
    "max_tokens": 1000,
    "top_p": 1.0,
    "top_k": 40
  }
}
```

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

### OpenAI Orchestrator Configuration

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/CONFIGURATION.md

Example JSON configuration for the orchestrator when using OpenAI models.

```json
{
  "orchestrator": {
    "llm_provider": "openai",
    "model": "gpt-4o",
    "temperature": 0.7,
    "max_tokens": 1000,
    "top_p": 1.0,
    "frequency_penalty": 0.0,
    "presence_penalty": 0.0
  }
}
```

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

### Google Gemini Orchestrator Configuration

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/CONFIGURATION.md

Example JSON configuration for the orchestrator when using Google Gemini models.

```json
{
  "orchestrator": {
    "llm_provider": "gemini",
    "model": "gemini-1.5-pro",
    "temperature": 0.7,
    "max_tokens": 1000,
    "top_p": 1.0,
    "top_k": 40
  }
}
```

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

### Clone Arklex Repository

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Quickstart.md

Clones the official Arklex Agent-First Organization repository from GitHub to your local machine.

```bash
git clone https://github.com/arklexai/Agent-First-Organization.git
```

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

### Run Custom Agent

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Quickstart.md

Executes the newly created custom agent. The '--input-dir' flag points to the directory containing the custom agent's configuration and data.

```bash
python run.py --input-dir ./examples/customer_service_copy
```

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

### Health Check Endpoint Implementation

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/TROUBLESHOOTING.md

Example of a FastAPI health check endpoint that verifies service status by testing database connections and external API availability.

```Python
# Implement health checks
@app.get("/health")
async def health_check():
    try:
        # Test database connection
        # Test LLM API
        # Check memory usage
        return {"status": "healthy"}
    except Exception as e:
        return {"status": "unhealthy", "error": str(e)}
```

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

### Developer Experience Metrics

Source: https://github.com/arklexai/agent-first-organization/blob/main/project_improvements/DOCUMENTATION_IMPROVEMENTS.md

Metrics focused on improving the developer experience, including setup time, example execution, documentation search, and community contributions.

```APIDOC
Developer Experience Metrics:
  - Setup Time: Aim for less than 5 minutes for new developers.
  - Example Execution: Ensure all provided examples run successfully.
  - Documentation Search: Implement effective search functionality within the documentation.
  - Interactive Documentation: Provide interactive API documentation for easier exploration.
  - Video Tutorials: Create video tutorials for complex features.
  - Community Examples: Encourage and integrate community-contributed examples.
```

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

### Model API Server and Evaluation

Source: https://github.com/arklexai/agent-first-organization/blob/main/README.md

Instructions for starting the model API server and running evaluations against it, specifying the model API endpoint, configuration, documents, LLM provider, and task.

```bash
python model_api.py --input-dir ./examples/customer_service
```

```bash
python eval.py --model_api http://127.0.0.1:8000/eval/chat \
  --config "examples/customer_service/customer_service_config.json" \
  --documents_dir "examples/customer_service" \
  --model "claude-3-haiku-20240307" \
  --llm_provider "anthropic" \
  --task "all"
```

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

### Configure Multi-Agent Workflow

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/EXAMPLES.md

Defines the configuration for a Multi-Agent Workflow, detailing the setup for individual agents (research, analysis, writing) including their orchestrator settings and tool integrations.

```json
{
  "name": "Multi-Agent Workflow",
  "description": "Complex workflow with multiple specialized agents",
  "version": "1.0.0",
  "agents": {
    "research_agent": {
      "orchestrator": {
        "llm_provider": "openai",
        "model": "gpt-4o",
        "temperature": 0.3
      },
      "tools": ["web_search_tool", "document_processor_tool"]
    },
    "analysis_agent": {
      "orchestrator": {
        "llm_provider": "openai",
        "model": "gpt-4o",
        "temperature": 0.3
      },
      "tools": ["calculator_tool", "statistical_analysis_tool"]
    },
    "writing_agent": {
      "orchestrator": {
        "llm_provider": "openai",
        "model": "gpt-4o",
        "temperature": 0.7
      },
      "tools": ["document_processor_tool"]
    }
  }
}
```

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

### Implement Document Processor

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/EXAMPLES.md

Demonstrates the Python implementation for the Document Processor agent, including orchestrator setup, adding specialized tools, and running a document processing task.

```python
from arklex.tools import DocumentProcessorTool, OCRTool, TableExtractorTool

# Create orchestrator
orchestrator = Orchestrator(
    llm_provider="openai",
    model="gpt-4o",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Add document processing tools
orchestrator.add_tool(DocumentProcessorTool())
orchestrator.add_tool(OCRTool())
orchestrator.add_tool(TableExtractorTool())

# Process document
result = orchestrator.run(task_graph, query="Process this PDF document")
print(result.response)
```

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

### Arklex AI Tutorial Series Overview

Source: https://github.com/arklexai/agent-first-organization/blob/main/project_improvements/DOCUMENTATION_IMPROVEMENTS.md

An index of tutorial series for Arklex AI, categorized by difficulty level (Beginner, Intermediate, Advanced). Each tutorial includes a brief description, estimated duration, prerequisites, and a link to start.

```markdown
# Tutorial Series

## Beginner Tutorials

### 1. Building Your First Agent
Learn how to create a simple AI agent that can respond to user queries.

**Duration:** 30 minutes
**Prerequisites:** Basic Python knowledge

[Start Tutorial →](tutorials/first-agent.md)

### 2. Adding Tools to Your Agent
Learn how to extend your agent's capabilities with custom tools.

**Duration:** 45 minutes
**Prerequisites:** Completed "Building Your First Agent"

[Start Tutorial →](tutorials/adding-tools.md)

### 3. Creating Multi-Agent Workflows
Learn how to orchestrate multiple agents to solve complex problems.

**Duration:** 60 minutes
**Prerequisites:** Completed "Adding Tools to Your Agent"

[Start Tutorial →](tutorials/multi-agent-workflows.md)

## Intermediate Tutorials

### 4. Building RAG Systems
Learn how to build document retrieval and question-answering systems.

**Duration:** 90 minutes
**Prerequisites:** Basic understanding of vector databases

[Start Tutorial →](tutorials/rag-systems.md)

### 5. Integrating External APIs
Learn how to integrate with Shopify, HubSpot, and other services.

**Duration:** 75 minutes
**Prerequisites:** API integration experience

[Start Tutorial →](tutorials/external-integrations.md)

### 6. Custom Tool Development
Learn how to create custom tools for your agents.

**Duration:** 60 minutes
**Prerequisites:** Python development experience

[Start Tutorial →](tutorials/custom-tools.md)

## Advanced Tutorials

### 7. Performance Optimization
Learn how to optimize your agents for production use.

**Duration:** 120 minutes
**Prerequisites:** Understanding of performance concepts

[Start Tutorial →](tutorials/performance-optimization.md)

### 8. Security Best Practices
Learn how to secure your agents and integrations.

**Duration:** 90 minutes
**Prerequisites:** Security awareness

[Start Tutorial →](tutorials/security-best-practices.md)

### 9. Deployment and Scaling
Learn how to deploy your agents to production.

**Duration:** 150 minutes
**Prerequisites:** DevOps experience

[Start Tutorial →](tutorials/deployment-scaling.md)
```

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

### Logging Configuration Example

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/DEPLOYMENT.md

Placeholder for logging configuration details. This section would typically include how to configure log aggregation, formatting, and retention for the Arklex agent.

```python
# Logging configuration would go here.
# Example: Configure Python's logging module
# import logging
# logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
```

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

### Booking Assistant Example Config

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/tutorials/booking-service.md

An example JSON configuration file for a booking assistant chatbot designed for The Irish Repertory Theatre.

```json
{
    "role": "booking assistant",
    "user_objective": "The booking assistant helps users to book tickets for performances.",
    "builder_objective": "The booking assistant helps to request customer's contact information.",
    "domain": "performance company",
    "intro": "The Irish Repertory Theatre is a premier performance company that offers a wide range of theatrical productions.",
    "task_docs": [
        {
            "source": "https://irish-rep.org/",
            "desc": "Homepage of The Irish Repertory Theatre."
        }
    ],
    "workers": [
        {
            "id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
            "name": "BookingWorker",
            "path": "booking_worker.py"
        }
    ],
    "tools": [
        {
            "id": "a1b2c3d4-e5f6-7890-1234-567890abcdef",
            "name": "find_user_id_by_email",
            "path": "shopify/find_user_id_by_email.py",
            "fixed_args": {
                "token": "<access_token>",
                "shop_url": "<url>",
                "api_version": "<version>"
            }
        }
    ]
}
```

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

### Monitor Memory Usage

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/QUICKSTART.md

Provides commands to monitor system memory usage, which can help diagnose memory-related issues. `htop` or `top` are common command-line utilities for this purpose.

```bash
# Monitor memory usage
htop  # or top on macOS
```

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

### Release Steps

Source: https://github.com/arklexai/agent-first-organization/blob/main/project_improvements/DOCUMENTATION_IMPROVEMENTS.md

Commands for updating the project version, creating a Git tag, and deploying to PyPI.

```bash
# Update version
bump2version patch  # or minor/major

# Create release
git tag v1.2.3
git push origin v1.2.3

# Deploy to PyPI
python setup.py sdist bdist_wheel
twine upload dist/*
```

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

### SearchWorker Instantiation and Action Graph Setup

Source: https://github.com/arklexai/agent-first-organization/blob/main/docs/docs/Workers/SearchWorker.mdx

Demonstrates the initialization of the SearchWorker, including setting up the LangGraph StateGraph with nodes for search engine interaction and tool generation, and configuring the LLM.

```python
def __init__(self):
        super().__init__()
        self.action_graph = self._create_action_graph()
        self.llm = ChatOpenAI(model=MODEL["model_type_or_path"], timeout=30000)

def _create_action_graph(self):
    workflow = StateGraph(MessageState)
    # Add nodes for each worker
    search_engine = SearchEngine()
    workflow.add_node("search_engine", search_engine.search)
    workflow.add_node("tool_generator", ToolGenerator.context_generate)
    # Add edges
    workflow.add_edge(START, "search_engine")
    workflow.add_edge("search_engine", "tool_generator")
    return workflow
```