The project aims to train students to develop advanced solutions in natural language processing (NLP) and generative artificial intelligence (AI). These solutions aim to solve complex problems in organizations where it is crucial that computer systems understand, interpret, and manage human language naturally and effectively.
APPLICATION EXAMPLES:
- Customer Service and Support (Chatbots and Virtual Assistants): Development of automatic response systems that can understand and respond to customer queries in natural language (text), providing efficient customer service and reducing waiting times.
- CV Analysis and Talent Matching: Automated tools to analyze CVs, evaluate skills and experience in textual format, and suggest candidates for job vacancies and facilitate the generation of personalized CVs, optimizing the recruitment process.
Mandatory infrastructure resources:
- Python: Versatile, high-level programming language.
- TensorFlow: Open source deep learning framework.
- PyTorch: Deep learning framework with a focus on flexibility.
- NumPy: Essential library for numerical computation in Python.
- Scikit-learn: Machine learning library in Python.
- GPUs: Graphics processing unit for computational acceleration.
- Clusters: Sets of interconnected computers for parallel processing.
- Cloud: Scalable computing platforms based in the cloud.
- Google Colab Pro Plus: cloud and collaborative development environment.
- Git: Repository and version control tool.
- Flask: API development tool in Python.
- Ngrok: Tunneling tool for agile experimentation with endpoints (e.g. tunneling to quickly make an API running locally available).
- Hugging Face: Open LLM model platform available with API access.
- Langchain: Agent development tool based on LLM models.
- Ollama: Tool for local execution of open LLM models.
