gllm-inference-binary 0.5.64

A library containing components related to model inferences in Gen AI applications.

GLLM Inference

Description

A library containing components related to model inferences in Gen AI applications.

Installation

Prerequisites

1. Python 3.11+ - Install here
2. Pip (if using Pip) - Install here
3. Poetry (automatically installed via Makefile) - Install here
4. Git (if using Git) - Install here
5. gcloud CLI (for authentication) - Install here
6. For git installation, access to the GDP Labs SDK github repository

1. Installation from Artifact Registry

Choose one of the following methods to install the package:

Using pip

pip install gllm-inference-binary

Using Poetry

poetry add gllm-inference-binary

2. Development Installation (Git)

For development purposes, you can install directly from the Git repository:

poetry add "git+ssh://[e-mail]/GDP-ADMIN/gen-ai-internal.git#subdirectory=libs/gllm-inference"

Available extras:

• anthropic: Install Anthropic models dependencies
• google-genai: Install Google Generative AI models dependencies
• google-vertexai: Install Google Vertex AI models dependencies
• huggingface: Install HuggingFace models dependencies
• openai: Install OpenAI models dependencies
• twelvelabs: Install TwelveLabs models dependencies

Local Development Setup

Quick Setup (Recommended)

For local development with editable gllm packages, use the provided Makefile:

# Complete setup: installs Poetry, configures auth, installs packages, sets up pre-commit
make setup

The following are the available Makefile targets:

1. make setup - Complete development setup (recommended for new developers)
2. make install-poetry - Install or upgrade Poetry to the latest version
3. make auth - Configure authentication for internal repositories
4. make install - Install all dependencies
5. make install-pre-commit - Set up pre-commit hooks
6. make update - Update dependencies

Manual Development Setup (Legacy)

If you prefer to manage dependencies manually:

1. Go to root folder of gllm-inference module, e.g. cd libs/gllm-inference.
2. Run poetry shell to create a virtual environment.
3. Run poetry lock to create a lock file if you haven't done it yet.
4. Run poetry install to install the gllm-inference requirements for the first time.
5. Run poetry update if you update any dependency module version at pyproject.toml.

Contributing

Please refer to this Python Style Guide to get information about code style, documentation standard, and SCA that you need to use when contributing to this project

Getting Started with Development

1. Clone the repository and navigate to the gllm-inference directory
2. Run make setup to set up your development environment
3. Run which python to get the path to be referenced at Visual Studio Code interpreter path (Ctrl+Shift+P or Cmd+Shift+P)
4. Try running the unit test to see if it's working:

poetry run pytest -s tests/unit_tests/

5. When you want to update the dependencies, run make update