Skip to content

Installation Guide

This guide will help you install skforecast-ai, an AI-powered forecasting assistant built on top of skforecast. The default installation of skforecast-ai includes only the essential dependencies required for basic functionality. Additional optional dependencies can be installed for extended features such as LLM-based assistance.

Python PyPI

Basic installation

Skforecast-ai requires Python 3.10 or higher. It is available on PyPI and can be installed using pip.

To install the basic version of skforecast-ai with its core dependencies, run:

pip install skforecast-ai

Specific version:

pip install skforecast-ai==0.1.0

Latest (unstable):

pip install git+https://github.com/skforecast/skforecast-ai@main

The following dependencies are installed with the default installation:

  • pydantic>=2.10
  • pandas>=2.1
  • skforecast>=0.23
  • typer>=0.22
  • rich>=13.9
  • tomli>=2.0 (only for Python < 3.11)
  • statsmodels>=0.13, <0.15

Optional dependencies

To install the full version with all optional dependencies:

pip install skforecast-ai[full]

For specific use cases, you can install these dependencies as needed:

LLM

Enables the LLM-powered forecasting assistant features.

pip install skforecast-ai[llm]
  • pydantic-ai>=2, <3

Groq

Adds support for Groq models through pydantic-ai.

pip install skforecast-ai[groq]
  • pydantic-ai[groq]>=2, <3

Bedrock

Adds support for Amazon Bedrock models through pydantic-ai.

pip install skforecast-ai[bedrock]
  • pydantic-ai[bedrock]>=2, <3
  • boto3>=1.34

All providers

Installs every supported LLM provider (Groq and Bedrock).

pip install skforecast-ai[all]
  • pydantic-ai[bedrock,groq]>=2, <3
  • boto3>=1.34