[!CAUTION]
LAiSER is currently in development mode, features could be experimental. Use with caution!
Leveraging Artificial Intelligence for Skill Extraction & Research (LAiSER)
Contents
LAiSER is a tool that helps learners, educators and employers share trusted and mutually intelligible information about skills.
About
LAiSER is an innovative tool that harnesses the power of artificial intelligence to simplify the extraction and analysis of skills. It is designed for learners, educators, and employers who want to gain reliable insights into skill sets, ensuring that the information shared is both trusted and mutually intelligible across various sectors.
By leveraging state-of-the-art AI models, LAiSER automates the process of identifying and classifying skills from diverse data sources. This not only saves time but also enhances accuracy, making it easier for users to discover emerging trends and in-demand skills.
The tool emphasizes standardization and transparency, offering a common framework that bridges the communication gap between different stakeholders. With LAiSER, educators can better align their teaching methods with industry requirements, and employers can more effectively identify the competencies required for their teams. The result is a more efficient and strategic approach to skill development, benefiting the entire ecosystem.
Requirements
- Python version >= Python 3.9.
- A GPU with atleast 15GB video memory is essential for running this tool on large datasets.
Setup and Installation
-
Install LAiSER using pip:
For GPU support (recommended if you have a CUDA-capable GPU):
pip install laiser[gpu]
For CPU-only environments:
pip install laiser[cpu]
By default, torch and vllm GPU dependencies are included. Only when using the [cpu] extra will these GPU dependencies be excluded.
NOTE: Python 3.9 or later, preferably 3.12, is expected to be installed on your system. If you don't have Python installed, you can download it from here.
You can check if your machine has a GPU available with:
python -c "import torch; print(torch.cuda.is_available())"
Usage
As of now LAiSER can be used a python package in Google Colab or a local machine with GPU access. The steps to setup the tool are as follows:
Google Colab Setup
LAiSER's Jupyter notebook is, currently, the fastest way to get started with the tool. You can access the notebook here.
-
Once the notebook is imported in google colaboratory, connect to a GPU-accelerated runtime(T4 GPU) and run the cells in the notebook.
-
Sample code to import and verify laiser module
Using the new refactored API (recommended):
from laiser.skill_extractor_refactored import SkillExtractorRefactored print('\n\nInitializing the Skill Extractor...') # Replace 'your_model_id' and 'your_hf_token' with your actual credentials. model_id = "your_model_id" # e.g., "microsoft/DialoGPT-medium" hf_token = "your_hf_token" use_gpu = True # Change to False if you are not using a GPU se = SkillExtractorRefactored(model_id=model_id, hf_token=hf_token, use_gpu=use_gpu) print('The Skill Extractor has been initialized successfully!\n') print("LAiSER package loaded successfully!")
Legacy API (backward compatibility):
from laiser.skill_extractor import Skill_Extractor print('\n\nInitializing the Skill Extractor...') # Replace 'your_model_id' and 'your_hf_token' with your actual credentials. AI_MODEL_ID = "your_model_id" # e.g., "bert-base-uncased" HF_TOKEN = "your_hf_token" use_gpu = True # Change to False if you are not using a GPU se = Skill_Extractor(AI_MODEL_ID=AI_MODEL_ID, HF_TOKEN=HF_TOKEN, use_gpu=use_gpu) print('The Skill Extractor has been initialized successfully!\n') print("LAiSER package loaded successfully!")
Funding
Authors
Partners
3 maintainers
Release files for dev-laiser 0.3.9.99
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| dev_laiser-0.3.9.99.tar.gz | 61.3 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| dev_laiser-0.3.9.99-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 122.6 MB
Release files / dev_laiser-0.3.9.99.tar.gz
| Download URL | dev_laiser-0.3.9.99.tar.gz |
|---|---|
| Size | 61.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
20c0cdba7b200e81675c6ec3007fe50bcd20bc4b3a5776251773a0a42b2c0d9d
|
|
BLAKE2b-256 checksum How to use checksums |
660bc25b0f0b63e4e3b2596eb2013926c6ec4feedd27a36066773532f8bdcf1c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.11
|
Release files / dev_laiser-0.3.9.99-py3-none-any.whl
| Download URL | dev_laiser-0.3.9.99-py3-none-any.whl |
|---|---|
| Size | 61.3 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
64f96a6b0db5f86bc58e7d753e167c4df0573ccfa6746f7efacee0bd0289bdc4
|
|
BLAKE2b-256 checksum How to use checksums |
7390f8af21dd76decb8db144f70fb51bd7fcac313320fcc46c99f8621fe37cfe
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.11
|
