Large-Language Model (LLM) part of Talk2PowerSystem

Table of Contents

• Overview
• Features
• Project Structure
• Installation
  • Prerequisites
  • Setup
• Run tests
  • Unit tests
  • Acceptance tests
• Versioning
• License

Overview

Large-Language Model (LLM) part of Talk2PowerSystem (Talk2PowerSystem_LLM) is a core component of the Talk2PowerSystem project, providing all the necessary coding and scripting to support the integration and operation of a Large-Language Model (LLM). This project focuses on enabling robust LLM functionalities, including data preprocessing, model training, inference, and seamless integration with other parts of the Talk2PowerSystem ecosystem.

Features

• Data Preprocessing: Scripts to clean, normalize, and format data for LLM training.

• Model Training: Pipelines and utilities for fine-tuning and training LLM models.

• Inference Engine: Code for running real-time queries and generating model predictions.

• System Integration: Tools and interfaces to connect the LLM with other components of the Talk2PowerSystem project.

• Testing and Evaluation: Automated tests and performance evaluation scripts to ensure model reliability and accuracy.

Project Structure

The repository is organized as follows:

• src/ - Main source code including training, inference, and integration scripts.

• data/ - Data sets and preprocessing scripts.

• docs/ - Documentation, guides, and technical notes.

• tests/ - Unit and integration tests for various modules.

• config/ - Configuration files for model parameters and environment settings.

• evaluation_results/ - Directory, which holds the evaluation results of the system.

• helm-chart/ - Directory, which holds resources for easier deployment on Kubernetes environments.

Installation

Prerequisites

• You should install conda. miniconda will suffice.

Setup

To set up the project locally, follow these steps:

1. Clone the repository:

   git clone https://github.com/statnett/Talk2PowerSystem_LLM.git

2. Create a conda environment and install dependencies

   conda create --name Talk2PowerSystemLLM --file conda-linux-64.lock
   conda activate Talk2PowerSystemLLM
   poetry install

Run tests

Unit tests

conda activate Talk2PowerSystemLLM
poetry install --with test
poetry run pytest --cov=talk2powersystemllm --cov-report=term-missing tests/unit_tests/

Acceptance tests

bash ./docker/generate-manifest.sh
docker buildx build --file docker/Dockerfile --tag talk2powersystem .
docker buildx build --file tests/acceptance_tests/docker-compose/DockerfileAcceptanceTests --tag talk2powersystem-acceptance-tests .
docker buildx build --file tests/acceptance_tests/docker-compose/DockerfileGraphDB --tag graphdb .
docker compose -f tests/acceptance_tests/docker-compose/docker-compose.yaml run --rm talk2powersystem-acceptance-tests poetry run pytest tests/acceptance_tests/
docker compose -f tests/acceptance_tests/docker-compose/docker-compose.yaml down -v --remove-orphans

Versioning

The chat bot releases follow the Semantic Versioning Standard. However, poetry follows the PEP 440 Standard, so in order to create a pre-release we need to do update the version manually. The official releases versions are in the form of major.minor.patch. The pre-releases versions are in the form of major.minor.patch-rc<N>. The development versions are in the form of major.minor.patch-dev0.

Steps to create an official release (from the main branch):

1. conda activate Talk2PowerSystemLLM

2. poetry version <major|minor|patch>.

3. git add pyproject.toml

4. git commit -m "Bumping version from <previous-version> to <current-version>"

5. git push -u origin main

6. Create a release from the GitHub interface. The tag and the release title must match the version from poetry!

7. Edit the version in pyproject.toml - increase the patch and add -dev0 after it. For example, if the version is 2.0.0, the next version must be 2.0.1-dev0.

8. git add pyproject.toml

9. git commit -m "Bumping version from <previous-version> to <current-version>"

10. git push -u origin main

Steps to create a pre-release (from the main branch):

1. conda activate Talk2PowerSystemLLM

2. Edit the version in pyproject.toml - If the current version is a pre-release version, then you must increase the release candidate number. For example, if the current version is 1.2.0-rc1, the next version must be 1.2.0-rc2. If the current version is a development version, then the next pre-release version must follow the semantic versioning convention on how to increment the major, minor and patch parts of the version and add -rc1 at the end. For example, if the current version is 1.1.0-dev0 and the next release will be a major one, the next version must be 2.0.0-rc1.

3. git add pyproject.toml

4. git commit -m "Bumping version from <previous-version> to <current-version>"

5. git push -u origin main

6. Create a release from the GitHub interface. The tag and the release title must match the version from poetry!

We release changes on demand. First, we create pre-releases, then we deploy them, and test the changes. Until the changes don’t meet the acceptance criteria, new pre-releases are created with fixes. If the changes meet the acceptance criteria, an official release is created, which is deployed.

License

Talk2PowerSystem_LLM is licensed under the Apache License 2.0. For more information, see the LICENSE file.