Skip to main content

Oblix - Python SDK for AI model orchestration

Project description

Visit documentation.oblix.ai for full documentation

Introduction

Welcome to Oblix! This section will guide you through the process of installing the SDK, setting up your environment, and creating your first Oblix application.

What is Oblix?

Oblix is a comprehensive SDK for intelligent orchestration of AI models between edge and cloud environments. The SDK provides:

  • Unified interface for multiple AI model providers (OpenAI, Claude, Ollama)
  • Intelligent orchestration that seamlessly switches between edge and cloud models
  • System resource monitoring and connectivity awareness through specialized agents
  • Persistent chat session management
  • Agent system for extensible monitoring and orchestration decision making

Installation

Oblix is available for both macOS and Windows and can be installed using pip:

pip install oblix

For a specific Python version, you can use:

python3.11 -m pip install oblix

Oblix supports Python versions 3.9, 3.10, 3.11, 3.12, and 3.13.

Windows-Specific Installation

On Windows, the following dependencies will be automatically installed for system resource monitoring:

  • pywin32: For Windows system API access
  • wmi: For hardware monitoring
  • pynvml: For NVIDIA GPU monitoring

No additional steps are required for Windows installation - these dependencies are automatically installed when you run pip install oblix.

Prerequisites

Before using Oblix, you'll need:

  • macOS or Windows operating system
  • Provider API Keys for any cloud models you want to use
  • Ollama installed if you want to use local edge models

Platform Support

Oblix supports the following platforms:

  • macOS (Intel and Apple Silicon)
  • Windows (x86/x64)

Quickstart

For quickstart guide and detailed examples, visit documentation.oblix.ai

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

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

oblix-0.1.3-cp312-none-any.whl (855.3 kB view details)

Uploaded CPython 3.12

oblix-0.1.3-cp311-none-any.whl (855.3 kB view details)

Uploaded CPython 3.11

oblix-0.1.3-cp310-none-any.whl (855.3 kB view details)

Uploaded CPython 3.10

oblix-0.1.3-cp39-none-any.whl (855.3 kB view details)

Uploaded CPython 3.9

File details

Details for the file oblix-0.1.3-cp312-none-any.whl.

File metadata

  • Download URL: oblix-0.1.3-cp312-none-any.whl
  • Upload date:
  • Size: 855.3 kB
  • Tags: CPython 3.12
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.7

File hashes

Hashes for oblix-0.1.3-cp312-none-any.whl
Algorithm Hash digest
SHA256 b18fda83ccb7b8df4b3dc14ea89fe52aaae170b72074100d79a5f52121054c74
MD5 68f62e7d7d10a10066aa604bb9c8dbfd
BLAKE2b-256 211e9108eb77d3dc3de5356e837e446d490c5575cf82bff6c33cfd265c2b3eea

See more details on using hashes here.

File details

Details for the file oblix-0.1.3-cp311-none-any.whl.

File metadata

  • Download URL: oblix-0.1.3-cp311-none-any.whl
  • Upload date:
  • Size: 855.3 kB
  • Tags: CPython 3.11
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.7

File hashes

Hashes for oblix-0.1.3-cp311-none-any.whl
Algorithm Hash digest
SHA256 c304453028233972d54e2042d87982c162193c6dc8853f482cc53773cb2bee8d
MD5 6c8d7f104dfd6a1b20486ef3a99f4a34
BLAKE2b-256 281b4da8dcfbb187992a3301eca5eb120b8fb7209773fa67020ad2614df21cb8

See more details on using hashes here.

File details

Details for the file oblix-0.1.3-cp310-none-any.whl.

File metadata

  • Download URL: oblix-0.1.3-cp310-none-any.whl
  • Upload date:
  • Size: 855.3 kB
  • Tags: CPython 3.10
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.7

File hashes

Hashes for oblix-0.1.3-cp310-none-any.whl
Algorithm Hash digest
SHA256 531377eaeed62d115c5f74d34332b67037ea701898c3d3805aa844ddc25b187b
MD5 960af35eed2e13bdc1d9b2f5f936f732
BLAKE2b-256 a651c42bfcaaf8408bf1c295a607ad0ad00ba42e1e133a18563300605fdda0b4

See more details on using hashes here.

File details

Details for the file oblix-0.1.3-cp39-none-any.whl.

File metadata

  • Download URL: oblix-0.1.3-cp39-none-any.whl
  • Upload date:
  • Size: 855.3 kB
  • Tags: CPython 3.9
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.7

File hashes

Hashes for oblix-0.1.3-cp39-none-any.whl
Algorithm Hash digest
SHA256 b5085c409b5660678bd14aeff74eb11ff9c5e77eea173277bcf37ec5b263ec55
MD5 9bddcda84f8cf780f1af3749d2612d60
BLAKE2b-256 a3c6c8d423148c0acfc19883245bed2f78653312251976b12b28696a8c53fed4

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