chore(sample-app): add medical doctor Q&A example with Traceloop instrumentation

[nirga]

Summary

This PR adds a comprehensive medical doctor Q&A example to the sample-app that demonstrates OpenLLMetry/Traceloop instrumentation with OpenAI's GPT models.

Features Added

• Medical Q&A Application (medical_qa_example.py):

  • Single question mode for interactive consultations
  • Batch mode processing 20 predefined medical questions
  • Professional medical persona with appropriate disclaimers and safety warnings
  • Comprehensive error handling and result saving

• Traceloop Instrumentation:

  • @workflow decorators for main consultation flows (single and batch modes)
  • Automatic OpenAI API call instrumentation with request/response tracing
  • Token usage metrics and performance monitoring
  • Error tracking and observability

• Medical Safety Features:

  • Evidence-based medical advice with professional disclaimers
  • Recommendations to consult healthcare providers for serious symptoms
  • Clear warnings for emergency situations requiring immediate attention
  • Ethical guidelines avoiding specific diagnoses without examination

• Documentation:

  • Comprehensive README_medical_qa.md with setup and usage instructions
  • 20 sample medical questions covering common health topics
  • Example results showing proper medical responses with disclaimers
  • Updated main sample-app README

Sample Questions Covered

• Symptoms and conditions (flu, diabetes, heart attack signs, concussion)
• Preventive care (vaccines, physical exams, immune system boosting)
• Emergency situations (chest pain, dangerous fever levels)
• General health guidance (sleep, hydration, stress management)

Technical Implementation

• Clean Architecture: Functional approach with proper separation of concerns
• Code Quality: Passes all flake8 linting checks
• Flexibility: Supports both environment variables and command-line API key input
• Extensibility: Easy to add new medical questions or modify responses

Usage Examples

# Single question mode
poetry run python sample_app/medical_qa_example.py --mode single --question "What are flu symptoms?"

# Batch processing with result saving
poetry run python sample_app/medical_qa_example.py --mode batch --save

Safety Notice

⚠️ This is a demonstration example for technical purposes. The medical responses should not replace professional medical advice and include appropriate disclaimers.

Test Plan

• [x] Verify script runs without errors in both single and batch modes
• [x] Confirm proper Traceloop instrumentation and span generation
• [x] Validate medical responses include appropriate disclaimers
• [x] Test error handling with invalid API keys
• [x] Check code passes flake8 linting standards
• [x] Verify documentation is comprehensive and accurate

🤖 Generated with Claude Code

---

[!IMPORTANT] Adds a medical Q&A example to the sample app with Traceloop instrumentation, featuring single and batch modes, comprehensive documentation, and safety disclaimers.

• Features:
  • Adds medical_qa_example.py for a medical Q&A chatbot with single and batch modes.
  • Includes 20 predefined medical questions for batch processing.
  • Implements Traceloop instrumentation for OpenAI API calls with @workflow decorators.
• Documentation:
  • Adds README_medical_qa.md with setup and usage instructions.
  • Updates README.md to include the new medical Q&A example.
• Safety:
  • Provides medical disclaimers and advises consulting healthcare providers for serious symptoms.
• Technical:
  • Uses OpenAI's GPT models for generating responses.
  • Supports environment variables and command-line input for API keys.
  • Passes flake8 linting checks.

^{This description was created by for c720b403b20f2718b2626d383768719e71702614. You can customize this summary. It will automatically update as commits are pushed.}

Summary by CodeRabbit

• New Features

  • Added a Medical Doctor Q&A sample app with interactive single-question and batch modes, optional result saving, and built-in observability via OpenTelemetry/Traceloop.

• Documentation

  • Revamped sample app README with examples, Poetry-based usage, and pointers to additional frameworks/tools.
  • Added a dedicated Medical Q&A guide covering setup, usage, safety notes, and tracing overview.

• Chores

  • Added required dependencies for the sample.
  • Included a static dataset of sample medical Q&A results.