A local-first AI triage desk: sorting a one-person trade's jobs with Gemma 3
说明与用途
单人贸易因忙碌而错失工作。作者构建了一个终端前台,使用本地Gemma 3模型(通过Ollama)对消息进行分类、收集缺失信息,并将工作存储在SQLite中,完全控制且不泄露数据。
问题
A one‑person trade loses work because enquiries arrive while they are busy and nobody answers them. Using a metered, cloud‑hosted LLM to triage is costly, exposes customer data, and gives the vendor control over the model.
结果
The system processes a sample enquiry in a single command, asking for the missing address and desired time, then stores the job as pending. The owner can later approve it, after which the system sends a deterministic confirmation to the caller.
工作流
- 1. Caller types a message into the terminal.
- 2. The terminal sends the message and a JSON schema to the local Gemma 3 model via Ollama.
- 3. The model returns a JSON extraction (intent, required fields, etc.).
- 4. Deterministic code validates the JSON and decides whether to ask for more info, hand off to a human, or confirm the job.
- 5. If a field is missing, the code asks the caller for that single detail.
- 6. Once all required fields are present, the code confirms the job and stores it in SQLite.
- 7. The owner reviews the job list and approves or dismisses jobs via terminal commands.
证据
A one-person trade loses work for a dull reason: enquiries arrive while their hands are full, and nobody answers them.
So I built the opposite: a front desk whose triage runs on an open-weight model you host yourself, and which lives in the terminal.
Piping the lines in makes it reproducible in one command: printf ... | node src/cli.js
The model asks for exactly one thing at a time, and the confirmation is our text, not the model's — it never confirms a time or names a price.
- 记录日期: 2026-10-13T10:56:03.991Z