Course Outcomes:
1. Explain the evolution of NLP to large language models, their architecture, and the role of prompt engineering in AI/ML applications.
2. Design and evaluate effective prompts using various prompting types, patterns, and debugging techniques.
3. Apply advanced prompting methods, including Chain-of-Thought, ReAct, and multimodal prompting, using tools such as LangChain and OpenAI SDK.
4. Develop domain-specific prompts for tasks such as coding assistance, conversational agents, and data analysis, including low-resource language applications.
5. Assess prompt safety, bias, and ethical considerations, and implement best practices for secure and responsible LLM usage.
Course Outcomes:
1. Understand the importance of data engineering and its workflow in managing and integrating data from various sources.
2. Apply advanced data manipulation techniques using Excel functions and tools for efficient data processing.
3. Utilize Power BI to connect, transform, and model data from diverse sources into meaningful relationships
4. Employ Tableau to prepare and transform data through connections, blending, and calculated fields.
5. Integrate and automate data pipelines across tools to streamline data workflows and promote collaboration.