Dabba: Turning WhatsApp Tiffin Orders into Tomorrow’s Cooking Plan

说明与用途

Dabba 自动将 WhatsApp 消息转换为结构化订单列表和烹饪计划，降低浪费并提升客户满意度。

问题

Small tiffin kitchens manually parse WhatsApp group messages to decide tomorrow’s cooking plan, risking waste or loss of customers.

结果

Dabba achieved 100% valid JSON parsing on 200 held‑out messages, 98% overall accuracy, and generated prep lists in ~30 s, outperforming zero‑shot baselines.

工作流

• Paste evening WhatsApp messages
• Parse each message into a structured order
• Resolve relative dates (kal, parso, Monday)
• Apply kitchen memory for customer‑specific phrases
• Forecast final demand per dish
• Display portions to cook with confidence ranges

证据

Dabba converts a WhatsApp conversation into a structured order list and a practical kitchen prep plan.

来源

The training used three epochs and 129 steps. The total training cost was under two dollars.

来源

The fine‑tuned 4B model performed much better on the actual task because it had learned the structure of these messages.

来源

Dabba stores a simple memory in Backboard: POST /assistants/{id}/memories { "content": "Harsh Khan: usual dish paneer_thali, prefs no_onion." }

来源