Skip to main content

Software Development Kit to interact with Globant Enterprise AI.

Project description

PyGEAI - SDK for Globant Enterprise AI

PyGEAI is a Software Development Kit (SDK) for interacting with Globant Enterprise AI. It comprises libraries, tools, code samples, and documentation to simplify your experience with the platform.

Repository

Find the PyGEAI source code and documentation in the following GitHub repository:

GitHub repository

Configuration

Before using the SDK, you need to define GEAI_API_KEY ($SAIA_APITOKEN) and GEAI_API_BASE_URL ($BASE_URL). You can achieve this in three ways:

  • Environment variables: Set GEAI_API_KEY and GEAI_API_BASE_URL as environment variables in your operating system.
  • Credentials file: Create a file named credentials in the .geai directory within your user home directory ($USER_HOME/.geai/credentials) and define GEAI_API_KEY and GEAI_API_BASE_URL within this file.
  • Client instantiation: Specify the api_key and base_url parameters directly when creating an instance of a client class.

Note: If you plan to use the Evaluation Module, you must also define GEAI_API_EVAL_URL

Modules

The SDK consists of several modules, all accessible through a meta-package:

  • pygeai: This meta-package encapsulates all components of the SDK.
  • pygeai-cli: This package provides a command-line tool for interacting with the SDK.
  • pygeai-chat: This package offers facilities to chat with assistants/agents created in Globant Enterprise AI.
  • pygeai-dbg: This package includes a debugger to troubleshoot potential SDK issues and gain detailed insights into its operations [in development].
  • pygeai-core: This package handles interactions with the fundamental components of Globant Enterprise AI, including users, groups, permissions, API keys, organizations, and Projects.
  • pygeai-admin: This package enables interactions with the Globant Enterprise AI instance.
  • pygeai-lab: This package facilitates interactions with AI LAB.
  • pygeai-evaluation: This package provides functionality from the evaluation module.
  • pygeai-gam: This package allows interaction with [GAM] (https://wiki.genexus.com/commwiki/wiki?24746,Table+of+contents%3AGeneXus+Access+Manager+%28GAM%29,).
  • pygeai-assistant: This package handles interactions with various Assistants, including Data Analyst Assistants, RAG Assistants, Chat with Data Assistants, Chat with API Assistants, and Chat Assistants.
  • pygeai-organization: This package facilitates interactions with Organizations in Globant Enterprise AI.
  • pygeai-flows: This package enables interactions with Flows [in development].

Usage

Install PyGEAI

Use pip to install the package from PyPI:

(venv) ~$ pip install pygeai

To install pre-release versions, you can run:

(venv) ~$ pip install --pre pygeai

Verify installation

To check the installed PyGEAI version, run:

(venv) ~$ geai v

View help

To access the general help menu:

(venv) ~$ geai h

To view help for a specific command:

(venv) ~$ geai <command> h

Man Pages Documentation

The package includes Unix manual pages (man pages) for detailed command-line documentation. To access the man pages:

man geai

Setting up Man Pages Access

If you're using a virtual environment, you'll need to configure your system to find the man pages. Add the following to your shell configuration file (.bashrc, .zshrc, etc.):

# For macOS
if [ -n "$VIRTUAL_ENV" ]; then
    export MANPATH="$VIRTUAL_ENV/share/man:$MANPATH"
fi

# For Linux
if [ -n "$VIRTUAL_ENV" ]; then
    export MANPATH="$VIRTUAL_ENV/man:$MANPATH"
fi

After adding this configuration:

  1. Reload your shell configuration: source ~/.bashrc or source ~/.zshrc
  2. The man pages will be available when your virtual environment is active

Bugs and suggestions

To report any bug, request features or make any suggestions, the following email is available:

geai-sdk@globant.com

Authors

Copyright 2025, Globant. All rights reserved

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pygeai-0.2.1.tar.gz (236.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pygeai-0.2.1-py3-none-any.whl (339.0 kB view details)

Uploaded Python 3

File details

Details for the file pygeai-0.2.1.tar.gz.

File metadata

  • Download URL: pygeai-0.2.1.tar.gz
  • Upload date:
  • Size: 236.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.3

File hashes

Hashes for pygeai-0.2.1.tar.gz
Algorithm Hash digest
SHA256 fd5a3a7b6a899d2a3f315de491b316e40a5e2f8729b0ed4621ab20de8d98e0dc
MD5 75da9b831bb0ffabf5a1efd4f4d3cc1b
BLAKE2b-256 07d3dcfcf53607c78b7b7cc8ef938068784a2640a03788eb7af2f90d40fce0c2

See more details on using hashes here.

File details

Details for the file pygeai-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: pygeai-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 339.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.3

File hashes

Hashes for pygeai-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d6b1b504e5305bf642537deacbd9addacdd406da282f409011f7c695f07ff0e0
MD5 d39b1ce49a09ded361367cc81aee5fed
BLAKE2b-256 5ead39d4f883af460d1a4945a7fd6b161563a5abb33c82a5824c899341ac8f33

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page