mirror of
https://github.com/escalante29/healthy-fit.git
synced 2026-03-21 13:28:46 +01:00
184c8330a7
Introduces DSPy-based nutrition and plan generation modules, including image analysis for nutritional info and personalized diet/exercise plans. Adds new API endpoints for health metrics/goals, nutrition image analysis, and plan management. Updates models, schemas, and backend structure to support these features, and includes initial training data and configuration for prompt optimization.
42 lines
1.3 KiB
Python
42 lines
1.3 KiB
Python
from dspy.teleprompt import BootstrapFewShot
|
|
|
|
from app.ai.nutrition import nutrition_module
|
|
from app.core.ai_config import configure_dspy
|
|
from scripts.nutrition_data import train_examples
|
|
|
|
# 0. Configure DSPy
|
|
configure_dspy()
|
|
|
|
# 1. Define Validated Examples (The "Train Set")
|
|
# ... (rest of the file) ...
|
|
|
|
|
|
# 2. Define a Metric
|
|
def validate_nutrition(example, pred, trace=None):
|
|
# Check if the predicted calories are within 15% of the actual calories
|
|
actual_cals = example.nutritional_info.calories
|
|
pred_cals = pred.nutritional_info.calories
|
|
|
|
threshold = 0.15
|
|
lower = actual_cals * (1 - threshold)
|
|
upper = actual_cals * (1 + threshold)
|
|
|
|
return lower <= pred_cals <= upper
|
|
|
|
|
|
# 3. Setup the Optimizer
|
|
teleprompter = BootstrapFewShot(metric=validate_nutrition, max_bootstrapped_demos=8, max_labeled_demos=8)
|
|
|
|
# 4. Compile (Optimize) the Module
|
|
print("Optimizing... (this calls the LLM for each example)")
|
|
compiled_nutrition = teleprompter.compile(nutrition_module, trainset=train_examples)
|
|
|
|
# 5. Save validity
|
|
# Correct path relative to backend/ directory
|
|
compiled_nutrition.save("app/ai/nutrition_compiled.json")
|
|
print("Optimization complete! Saved to app/ai/nutrition_compiled.json")
|
|
|
|
# 6. Usage
|
|
# To use the optimized version in production, you would load it:
|
|
# nutrition_module.load("backend/app/ai/nutrition_compiled.json")
|