Skip to main content

Low abstraction agentic LLM framework.

Project description

logo

About LLMBrix

  • in early alpha development do not use productively
  • low abstraction LLM framework
  • simple toolkit to create AI apps

Install

pip install llmbrix --pre

Use

See examples in examples/ dir.

Development notes

Install package

pip install -e '.[dev]'

Configure pre-commit hook

pip install pre-commit
pre-commit install

Run tests

pytest

Env setup

OpenAI API key

This framework currently supports only OpenAI completion API as an LLM backend. To enable it you have to configure env variable with your API access token (see https://platform.openai.com/docs/quickstart for more details).

export OPENAI_API_KEY="<YOUR API TOKEN>"

Other

Release test install

pip install --index-url https://test.pypi.org/simple/ \
            --extra-index-url https://pypi.org/simple \
            llmbrix --pre

Project details


Download files

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

Source Distribution

llmbrix-0.1.0a6.tar.gz (226.4 kB view details)

Uploaded Source

Built Distribution

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

llmbrix-0.1.0a6-py3-none-any.whl (20.9 kB view details)

Uploaded Python 3

File details

Details for the file llmbrix-0.1.0a6.tar.gz.

File metadata

  • Download URL: llmbrix-0.1.0a6.tar.gz
  • Upload date:
  • Size: 226.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.9

File hashes

Hashes for llmbrix-0.1.0a6.tar.gz
Algorithm Hash digest
SHA256 0245797e744e92f513828f4874d409f0b016267313f66c2bbd0b14945459180b
MD5 9727929ce42aad82f758e96de9337e1c
BLAKE2b-256 e63a2ced6e5643d0856deb3eba6829199039b557ff1e779068a7fc7c03983bef

See more details on using hashes here.

File details

Details for the file llmbrix-0.1.0a6-py3-none-any.whl.

File metadata

  • Download URL: llmbrix-0.1.0a6-py3-none-any.whl
  • Upload date:
  • Size: 20.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.9

File hashes

Hashes for llmbrix-0.1.0a6-py3-none-any.whl
Algorithm Hash digest
SHA256 75607f1c0b30e29638c9ca8b650f4f94fee9e920317b751b3b06f943126bb92e
MD5 0f59c704ceb0f8a90f6571d5dc2569ce
BLAKE2b-256 3a76e2332a1b788e49c2a98e181572f6ff1d9f28613f48474d14c289c0ba0b8f

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