Analyze food descriptions or photos, estimate nutritional content, and provide dietary advice.
Use Cases
- The user says "About how many calories is this meal?" or "Help me analyze what I ate today."
- The user takes a photo of food and wants to know its nutrition.
- The user is making a diet plan or managing fat loss/muscle gain.
Analysis Methods
Text Description Analysis
The user describes the food, and the LLM estimates based on nutritional knowledge:
输入: "一碗白米饭 + 红烧排骨三块 + 炒青菜一盘"
Output: ┌──────────┬───────┬────────┬────────┬────────┐ │ Food │ Calories │ Protein │ Carbs │ Fat │ ├──────────┼───────┼────────┼────────┼────────┤ │ White rice │ 230 cal │ 4g │ 50g │ 0.5g │ │ Braised pork ribs │ 350 cal │ 25g │ 8g │ 24g │ │ Stir-fried greens │ 80 cal │ 3g │ 5g │ 5g │ ├──────────┼───────┼────────┼────────┼────────┤ │ Total │ 660 cal │ 32g │ 63g │ 29.5g │ └──────────┴───────┴────────┴────────┴────────┘
Assessment: Calories are moderate, protein meets the target, carbs are on the high side. Suggestion: Pair with more vegetables and reduce the amount of rice to half a bowl.
### 图片分析（需多模态模型支持）
如果 LLM 支持视觉输入（如 Claude vision / GPT-4V），可直接分析食物照片。
### 每日饮食追踪
```bash
# 存储饮食记录
mkdir -p ~/.xiaodazi/nutrition
# 当日记录
cat >> ~/.xiaodazi/nutrition/$(date +%Y-%m-%d).json << 'EOF'
{"meal": "午餐", "time": "12:30", "foods": [...], "total_calories": 660}
EOF
# 查看当日汇总
cat ~/.xiaodazi/nutrition/$(date +%Y-%m-%d).json
Nutrition Database API (Optional)
# USDA FoodData Central（免费，无需 Key）
curl -s "https://api.nal.usda.gov/fdc/v1/foods/search?query=chicken+breast&api_key=DEMO_KEY&pageSize=3" | python3 -c "
import json, sys
data = json.load(sys.stdin)
for food in data.get('foods', [])[:3]:
name = food.get('description', '')
nutrients = {n['nutrientName']: n['value'] for n in food.get('foodNutrients', [])[:10]}
print(f'{name}:')
for k, v in list(nutrients.items())[:5]:
print(f' {k}: {v}')
"
Output Specifications
- Display the nutrition table as a Markdown table.
- Values are approximate; note "For reference only, not medical advice."
- Provide brief dietary advice (1-2 sentences).
- Support food names in Chinese and English.