Installation Guide

This guide covers detailed installation steps for different types of applications in the Awesome LLM Apps repository.

System Requirements

Python

Version: 3.8 or higherRecommended: 3.10+

Memory

Minimum: 4GB RAMRecommended: 8GB+ for local models

Storage

Minimum: 2GB free spaceAdditional space needed for local models

Internet

Required for cloud APIsOptional for local-only setups

Installation Methods

Quick Install
Virtual Environment
Conda Environment

For most users, this is the fastest way to get started:

# Clone the repository
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps

# Navigate to your chosen project
cd starter_ai_agents/ai_travel_agent

# Install dependencies
pip install -r requirements.txt

# Run the application
streamlit run travel_agent.py

Recommended for development and avoiding package conflicts:

# Clone the repository
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps

# Create virtual environment
python -m venv venv

# Activate virtual environment
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Navigate to your project
cd starter_ai_agents/ai_travel_agent

# Install dependencies
pip install -r requirements.txt

# Run the application
streamlit run travel_agent.py

Always activate your virtual environment before running applications:

source venv/bin/activate  # Linux/Mac
venv\Scripts\activate     # Windows

If you use Anaconda or Miniconda:

# Clone the repository
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps

# Create conda environment
conda create -n llm-apps python=3.10
conda activate llm-apps

# Navigate to your project
cd starter_ai_agents/ai_travel_agent

# Install dependencies
pip install -r requirements.txt

# Run the application
streamlit run travel_agent.py

Project-Specific Installation

Starter AI Agents

Basic agents with minimal dependencies. Perfect for beginners.

Navigate to Agent Directory

cd starter_ai_agents/<agent-name>

Popular starter agents:

ai_travel_agent - Travel planning agent
ai_data_analysis_agent - Data analysis with AI
openai_research_agent - Multi-agent research system
ai_music_generator_agent - Music generation

Install Dependencies

Most starter agents use these core libraries:

pip install -r requirements.txt

Common dependencies:

streamlit
agno>=2.2.10
openai
python-dotenv

Configure API Keys

Set environment variables:

export OPENAI_API_KEY='sk-...'
export SERPAPI_KEY='your-serpapi-key'  # If using search

Run the Application

streamlit run <agent-name>.py

RAG (Retrieval Augmented Generation) Applications

RAG applications require additional dependencies for vector databases and embeddings.

Navigate to RAG Project

cd rag_tutorials/<project-name>

Examples:

ai_blog_search - Agentic RAG with LangGraph
corrective_rag - CRAG implementation
local_rag_agent - Local RAG with open-source models

Install Dependencies

RAG applications typically include:

pip install -r requirements.txt

Common RAG dependencies:

langchain
langgraph
langchain-community
langchain-google-genai
langchain-qdrant
langchain-text-splitters
tiktoken
beautifulsoup4
python-dotenv

Set Up Vector Database

Some RAG apps use Qdrant or ChromaDB:For Qdrant (cloud):

export QDRANT_URL='your-qdrant-url'
export QDRANT_API_KEY='your-qdrant-key'

For ChromaDB (local):

# No additional setup needed - runs locally

Run the Application

streamlit run app.py

MCP (Model Context Protocol) Agents

MCP agents require Docker and additional setup for protocol servers.

Install Docker

MCP agents use Docker containers for protocol servers.

macOS
Linux
Windows

Download from docker.com

# Verify installation
docker --version
docker ps

# Ubuntu/Debian
sudo apt-get update
sudo apt-get install docker.io
sudo systemctl start docker

# Verify installation
docker --version

Make sure Docker is running before starting MCP agents:

docker ps

Navigate to MCP Agent

cd mcp_ai_agents/<agent-name>

Available MCP agents:

github_mcp_agent - GitHub repository analysis
browser_mcp_agent - Browser automation
notion_mcp_agent - Notion integration

Install Python Dependencies

pip install -r requirements.txt

MCP-specific dependencies:

openai
streamlit
mcp
anthropic
python-dotenv

Configure API Keys

MCP agents typically need multiple API keys:For GitHub MCP Agent:

export OPENAI_API_KEY='your-openai-key'
export GITHUB_TOKEN='your-github-token'

Create a GitHub Personal Access Token at github.com/settings/tokens with repo scope.

Run the Agent

streamlit run github_agent.py

The agent will automatically manage Docker containers for MCP servers.

Advanced Multi-Agent Teams

Multi-agent systems may have additional dependencies for coordination and orchestration.

Navigate to Agent Team

cd advanced_ai_agents/multi_agent_apps/agent_teams/<team-name>

Examples:

ai_finance_agent_team - Financial analysis team
ai_legal_agent_team - Legal research team
multimodal_coding_agent_team - Code generation team

Install Framework Dependencies

Different teams use different frameworks:

pip install ag2
pip install pyautogen

Install All Dependencies

pip install -r requirements.txt

Run the Team

streamlit run <team-app>.py

Voice AI Agents

Voice agents require audio processing libraries.

System Audio Libraries

Install system-level audio dependencies:

macOS
Linux
Windows

brew install portaudio

# Ubuntu/Debian
sudo apt-get install portaudio19-dev python3-pyaudio

Install Python Packages

cd voice_ai_agents/<agent-name>
pip install -r requirements.txt

Common voice dependencies:

openai
streamlit
sounddevice
soundfile
numpy

Run Voice Agent

streamlit run voice_agent.py

Local Model Setup (Ollama)

Many applications support local models via Ollama for privacy and cost savings.

Install Ollama

Download and install from ollama.ai

macOS
Linux
Windows

brew install ollama

curl -fsSL https://ollama.ai/install.sh | sh

Pull Your Model

Download models you want to use:

ollama pull llama3.1
ollama pull mistral
ollama pull qwen2.5

Use smaller models for faster responses:

ollama pull llama3.1:7b   # 7B parameter model
ollama pull gemma2:2b     # 2B parameter model

Start Ollama Service

ollama serve

Verify it’s running:

curl http://localhost:11434/api/tags

Run Local Applications

Applications with local support typically have separate files:

streamlit run local_<app-name>.py

Example:

cd starter_ai_agents/ai_travel_agent
streamlit run local_travel_agent.py

Environment Variables

Manage your API keys securely using environment variables.

Using .env Files

Many projects include .env.example files:

# Copy the example file
cp .env.example .env

# Edit with your keys
nano .env

Example .env file:

OPENAI_API_KEY=sk-...
GOOGLE_API_KEY=AI...
ANTHROPIC_API_KEY=sk-ant-...
SERPAPI_KEY=...

System Environment Variables

Linux/macOS
Windows

Add to ~/.bashrc or ~/.zshrc:

export OPENAI_API_KEY='sk-...'
export GOOGLE_API_KEY='AI...'

Reload your shell:

source ~/.bashrc

Command Prompt:

setx OPENAI_API_KEY "sk-..."

PowerShell:

[Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "sk-...", "User")

Security Best Practices:

Never commit .env files to Git
Use different API keys for development and production
Rotate your API keys regularly
Add .env to your .gitignore file

Framework-Specific Setup

OpenAI Agents SDK

pip install openai-agents
pip install openai
pip install streamlit
pip install pydantic
pip install python-dotenv

Required environment variable:

export OPENAI_API_KEY='sk-...'

Google ADK (Agent Development Kit)

pip install google-genai-adk
pip install google-generativeai

Configuration:

# For Google AI Studio
export GOOGLE_GENAI_USE_VERTEXAI=False
export GOOGLE_API_KEY='AI...'

# For Vertex AI
export GOOGLE_GENAI_USE_VERTEXAI=True

LangChain & LangGraph

pip install langchain
pip install langgraph
pip install langchain-community
pip install langchain-openai
pip install langchain-google-genai
pip install langchain-anthropic

CrewAI

pip install crewai
pip install crewai-tools

Troubleshooting

Common Installation Issues

ModuleNotFoundError: No module named 'X'

Solution:

# Upgrade pip
pip install --upgrade pip

# Reinstall requirements
pip install -r requirements.txt --force-reinstall

Permission Denied on macOS/Linux

Solution:

# Don't use sudo with pip
# Instead, use --user flag
pip install --user -r requirements.txt

# Or use a virtual environment
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Docker connection refused

Solution:

# Ensure Docker is running
docker ps

# On macOS, start Docker Desktop
# On Linux
sudo systemctl start docker

Streamlit command not found

Solution:

# Ensure streamlit is installed
pip install streamlit

# If still not working, run via python
python -m streamlit run app.py

API rate limit errors

Solution:

Check your API usage and billing
Use smaller models or reduce request frequency
Consider using local models via Ollama

Verification

Verify your installation:

# Check Python version
python --version

# Check pip
pip --version

# Check installed packages
pip list | grep streamlit
pip list | grep openai

# Test Streamlit
streamlit hello

# Check Docker (if needed)
docker --version
docker ps

Updating Dependencies

Keep your installations up to date:

# Update all packages
pip install -r requirements.txt --upgrade

# Update specific package
pip install --upgrade streamlit

# Update Ollama
curl -fsSL https://ollama.ai/install.sh | sh

Next Steps

Quick Start

Run your first AI agent in minutes

AI Agents

Explore starter and advanced agents

RAG Tutorials

Build retrieval augmented generation apps

Configuration

Advanced configuration options

Additional Resources

For project-specific installation instructions, always refer to the README.md file in each project directory.

Get Started

AI Agents

RAG Applications

Advanced Concepts

Agent Skills

Framework Guides

System Requirements

Python

Memory

Storage

Internet

Installation Methods

Project-Specific Installation

Starter AI Agents

RAG (Retrieval Augmented Generation) Applications

MCP (Model Context Protocol) Agents

Advanced Multi-Agent Teams

Voice AI Agents

Local Model Setup (Ollama)

Environment Variables

Using .env Files

System Environment Variables

Framework-Specific Setup

OpenAI Agents SDK

Google ADK (Agent Development Kit)

LangChain & LangGraph

CrewAI

Troubleshooting

Common Installation Issues

Verification

Updating Dependencies

Next Steps

Quick Start

AI Agents

RAG Tutorials

Configuration

Additional Resources

Build docs developers (and LLMs) love

Get Started

AI Agents

RAG Applications

Advanced Concepts

Agent Skills

Framework Guides

​System Requirements

Python

Memory

Storage

Internet

​Installation Methods

​Project-Specific Installation

​Starter AI Agents

​RAG (Retrieval Augmented Generation) Applications

​MCP (Model Context Protocol) Agents

​Advanced Multi-Agent Teams

​Voice AI Agents

​Local Model Setup (Ollama)

​Environment Variables

​Using .env Files

​System Environment Variables

​Framework-Specific Setup

​OpenAI Agents SDK

​Google ADK (Agent Development Kit)

​LangChain & LangGraph

​CrewAI

​Troubleshooting

​Common Installation Issues

​Verification

​Updating Dependencies

​Next Steps

Quick Start

AI Agents

RAG Tutorials

Configuration

​Additional Resources

Build docs developers (and LLMs) love

System Requirements

Installation Methods

Project-Specific Installation

Starter AI Agents

RAG (Retrieval Augmented Generation) Applications

MCP (Model Context Protocol) Agents

Advanced Multi-Agent Teams

Voice AI Agents

Local Model Setup (Ollama)

Environment Variables

Using .env Files

System Environment Variables

Framework-Specific Setup

OpenAI Agents SDK

Google ADK (Agent Development Kit)

LangChain & LangGraph

CrewAI

Troubleshooting

Common Installation Issues

Verification

Updating Dependencies

Next Steps

Additional Resources