smolagents-audit/docs/source/en/installation.md

Installation Options

The smolagents library can be installed using pip. Here are the different installation methods and options available.

Prerequisites

• Python 3.10 or newer
• Python package manager: pip or uv

Virtual Environment

It's strongly recommended to install smolagents within a Python virtual environment. Virtual environments isolate your project dependencies from other Python projects and your system Python installation, preventing version conflicts and making package management more reliable.

Using venv:

python -m venv .venv
source .venv/bin/activate

Using uv:

uv venv .venv
source .venv/bin/activate

Basic Installation

Install smolagents core library with:

```bash pip install smolagents ``` ```bash uv pip install smolagents ```

Installation with Extras

smolagents provides several optional dependencies (extras) that can be installed based on your needs. You can install these extras using the following syntax:

pip install "smolagents[extra1,extra2]"

```bash uv pip install "smolagents[extra1,extra2]" ```

Tools

These extras include various tools and integrations:

• toolkit: Install a default set of tools for common tasks.

  pip install "smolagents[toolkit]"
  

• mcp: Add support for the Model Context Protocol (MCP) to integrate with external tools and services.

  pip install "smolagents[mcp]"
  

- **toolkit**: Install a default set of tools for common tasks. ```bash uv pip install "smolagents[toolkit]" ``` - **mcp**: Add support for the Model Context Protocol (MCP) to integrate with external tools and services. ```bash uv pip install "smolagents[mcp]" ```

Model Integration

These extras enable integration with various AI models and frameworks:

• openai: Add support for OpenAI API models.

  pip install "smolagents[openai]"
  

• transformers: Enable Hugging Face Transformers models.

  pip install "smolagents[transformers]"
  

• vllm: Add VLLM support for efficient model inference.

  pip install "smolagents[vllm]"
  

• mlx-lm: Enable support for MLX-LM models.

  pip install "smolagents[mlx-lm]"
  

• litellm: Add LiteLLM support for lightweight model inference.

  pip install "smolagents[litellm]"
  

• bedrock: Enable support for AWS Bedrock models.

  pip install "smolagents[bedrock]"
  

- **openai**: Add support for OpenAI API models. ```bash uv pip install "smolagents[openai]" ``` - **transformers**: Enable Hugging Face Transformers models. ```bash uv pip install "smolagents[transformers]" ``` - **vllm**: Add VLLM support for efficient model inference. ```bash uv pip install "smolagents[vllm]" ``` - **mlx-lm**: Enable support for MLX-LM models. ```bash uv pip install "smolagents[mlx-lm]" ``` - **litellm**: Add LiteLLM support for lightweight model inference. ```bash uv pip install "smolagents[litellm]" ``` - **bedrock**: Enable support for AWS Bedrock models. ```bash uv pip install "smolagents[bedrock]" ```

Multimodal Capabilities

Extras for handling different types of media and input:

• vision: Add support for image processing and computer vision tasks.

  pip install "smolagents[vision]"
  

• audio: Enable audio processing capabilities.

  pip install "smolagents[audio]"
  

- **vision**: Add support for image processing and computer vision tasks. ```bash uv pip install "smolagents[vision]" ``` - **audio**: Enable audio processing capabilities. ```bash uv pip install "smolagents[audio]" ```

Remote Execution

Extras for executing code remotely:

• blaxel: Add support for Blaxel sandboxes - fast-launching VMs with hibernation (recommended).

  pip install "smolagents[blaxel]"
  

• e2b: Enable E2B support for remote execution.

  pip install "smolagents[e2b]"
  

• docker: Add support for executing code in Docker containers.

  pip install "smolagents[docker]"
  

- **blaxel**: Add support for Blaxel sandboxes - fast-launching VMs with hibernation (recommended). ```bash uv pip install "smolagents[blaxel]" ``` - **e2b**: Enable E2B support for remote execution. ```bash uv pip install "smolagents[e2b]" ``` - **docker**: Add support for executing code in Docker containers. ```bash uv pip install "smolagents[docker]" ```

Telemetry and User Interface

Extras for telemetry, monitoring and user interface components:

• telemetry: Add support for monitoring and tracing.

  pip install "smolagents[telemetry]"
  

• gradio: Add support for interactive Gradio UI components.

  pip install "smolagents[gradio]"
  

- **telemetry**: Add support for monitoring and tracing. ```bash uv pip install "smolagents[telemetry]" ``` - **gradio**: Add support for interactive Gradio UI components. ```bash uv pip install "smolagents[gradio]" ```

Complete Installation

To install all available extras, you can use:

pip install "smolagents[all]"

```bash uv pip install "smolagents[all]" ```

Verifying Installation

After installation, you can verify that smolagents is installed correctly by running:

import smolagents
print(smolagents.__version__)

Next Steps

Once you have successfully installed smolagents, you can:

• Follow the guided tour to learn the basics.
• Explore the how-to guides for practical examples.
• Read the conceptual guides for high-level explanations.
• Check out the tutorials for in-depth tutorials on building agents.
• Explore the API reference for detailed information on classes and functions.