Add RAG Q&A system evaluation use case example

[yttrium400]

Pull Request Template

Type of Change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Description

This PR adds a comprehensive use case example demonstrating how to evaluate a RAG-based question-answering system using UpTrain.

The notebook provides a complete, end-to-end workflow showing developers how to:

• Evaluate context quality (relevance and conciseness)
• Assess response quality (completeness, relevance, conciseness, consistency)
• Verify factual accuracy to catch hallucinations
• Implement safety checks (prompt injection and jailbreak detection)
• Analyze results and identify issues

The example uses a realistic scenario: a Python programming Q&A system that retrieves documentation and generates responses. It includes intentionally problematic examples (e.g., irrelevant context, hallucinated responses) to demonstrate how UpTrain's evaluations catch these issues.

Fixes #522

Checklist

• I have read the CONTRIBUTING document.
• My code follows the code style (BLACK) of this project.
• I have added tests to cover my changes.
• All new and existing tests passed.
• I have updated the documentation accordingly.
• I have added an appropriate CHANGELOG entry.

Author's Note

This is my first contribution to UpTrain! I created this use case example to help newcomers understand how to evaluate RAG systems comprehensively. The notebook:

Files added:

• examples/use_cases/rag_qa_system_evaluation.ipynb - Complete RAG evaluation workflow
• examples/use_cases/README.md - Documentation for the use_cases directory

Key features:

• Real-world scenario with Python Q&A system
• Sample data with both good and problematic examples
• Multiple evaluation types (9 different checks demonstrated)
• Analysis section showing how to identify issues
• Clear structure following existing UpTrain examples

Note on testing:
The notebook doesn't include automated tests as it's an example/tutorial. It follows the pattern of other notebooks in the examples/ directory which are meant to be run interactively.

Note on CHANGELOG:
I noticed the repository doesn't have a CHANGELOG file, so I haven't added an entry there.

Looking forward to feedback!