I Built an Open-Weight Tarot Reader — Then Found My Backup Model Was Doing the Work

说明与用途

Pocket Oracle 通过 Gemma 和 Llama 模型链进行 AI 塔罗牌解读，但 Gemma 的短时限导致频繁回退到 Llama。通过延长 Gemma 的时间预算并明确显示使用的模型，应用程序变得更可靠、透明且成本更低。

问题

The primary AI model (Gemma 4 26B A4B) was timing out too quickly, causing the fallback model (Llama 3.3 70B) to handle most requests, leading to uncertainty about which model actually produced the readings.

结果

By extending Gemma’s timeout and making model usage explicit, Pocket Oracle now reliably uses the intended open‑weight model for most readings, improves transparency for users, and reduces unnecessary costs from fallback usage.

工作流

• 1. User selects language and draws cards. 2. Browser sends card names, spread, and question to Cloudflare Worker. 3. Worker validates input, looks up canonical card data, constructs a prompt. 4. Worker calls Gemma 4 26B A4B with a 60‑second timeout. 5. If Gemma times out or fails, Worker falls back to Llama 3.3 70B. 6. Worker validates JSON output, restores card identities, and returns the reading. 7. Browser renders the reading and shows which model produced it. 8. Optional narration: browser requests a short‑lived HMAC‑signed token from the Worker. 9. Worker posts to ElevenLabs to generate audio, then streams it back to the browser.

证据

Gemma now has up to 60 seconds per attempt, within a 100-second total Worker budget; the frontend has a 105-second request ceiling.

来源

Gemma completed five of six requests in this small test, with a 33.55-second median across all six.

来源

The frontend reports which model actually generated the displayed interpretation.

来源