Implement FastAPI endpoint with fitness input validation and AI response generation

[Copilot]

This PR implements a complete FastAPI application that processes and validates fitness-related user inputs with a two-step AI validation and response generation pipeline.

Overview

The implementation addresses the requirement for a FastAPI endpoint that:

1. Validates whether user input is fitness-related using AI
2. Generates personalized responses based on user information if validation passes
3. Returns appropriate error responses for non-fitness inputs

Key Features

Structured Input Model

The endpoint accepts comprehensive user data:

• user_name: User's name
• user_goals: List of fitness goals (e.g., ["lose weight", "build muscle"])
• user_body_info: Dictionary of body metrics (e.g., {weight: 76.8, height: 180, age: 30})
• user_input: Text input to validate and process

Two-Step Processing Pipeline

Step 1: Fitness Validation
Uses OpenAI's structured output feature with GPT-4o to determine if the input is fitness-related:

completion = client.beta.chat.completions.parse(
    model="gpt-4o-2024-08-06",
    messages=[...],
    response_format=FitnessValidationResponse,  # Structured output with boolean + score
)

Step 2: Conditional Processing

• If validation fails (score < 0.5): Returns HTTP 400 with error details
• If validation succeeds: Generates personalized AI response using all user information

Example Usage

curl -X POST "http://localhost:8000/process-fitness-input" \
  -H "Content-Type: application/json" \
  -d '{
    "user_name": "John Doe",
    "user_goals": ["lose weight", "build muscle"],
    "user_body_info": {"weight": 76.8, "height": 180},
    "user_input": "I want to start a workout routine"
  }'

Success Response (200):

{
  "response": "Based on your goals of losing weight and building muscle...",
  "fitness_score": 0.95
}

Error Response (400):

{
  "detail": {
    "error": "Input is not fitness-related",
    "details": "The provided input does not appear to be related to fitness, health, or wellness. Confidence score: 0.25"
  }
}

Files Added

• main.py: FastAPI application with validation and response generation logic
• models.py: Pydantic models for type-safe request/response handling
• requirements.txt: Project dependencies (FastAPI, OpenAI, Pydantic, etc.)
• test_app.py: Automated tests for validation
• example_usage.py: Usage examples and demonstrations
• IMPLEMENTATION.md: Detailed implementation documentation
• .env.example: Environment variable template for OpenAI API key
• .gitignore: Python project gitignore configuration

Testing

All tests pass successfully:

• ✅ Pydantic models instantiate correctly
• ✅ FastAPI app structure is valid
• ✅ All expected routes exist (/, /health, /process-fitness-input)
• ✅ Function signatures are correct
• ✅ Server starts and responds to requests

Setup Instructions

1. Install dependencies: pip install -r requirements.txt
2. Configure OpenAI API key: cp .env.example .env and add your key
3. Start the server: python main.py or uvicorn main:app --reload
4. Access API documentation at http://localhost:8000/docs

The implementation provides a production-ready FastAPI application with comprehensive error handling, type safety via Pydantic models, and automatic OpenAPI documentation generation.

Original prompt

fast api endpointi var

• user adı
• user hedefleri ama liste şeklinde
• user vücut bilgileri (dict olarak, örneğin {weight: 76.8,..}
• user input'u

1. adım: user input'u kullanılarak, modele bu input'un fitness ile ilgili olup olmadığı sorulacak. Bu noktada içinde yalnızca boolean tarzı bi özellik olan veya score tarzı

2. adım: değere göre kontrol yapılacak
   başarısızsa, hatalı response
   başarılı ise kullanıcı bilgileri prompta dahil edilerek AI'a istek gönderilecek. AI'dan gelen döndürülecek

---

💬 Share your feedback on Copilot coding agent for the chance to win a $200 gift card! Click here to start the survey.