.github/time/labs/aicharts/deploy.py

@@ -34,7 +34,7 @@ def deploy() -> dict:
         sys.exit("CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID are needed")
     code = parts()
     rev = hashlib.sha256(b"".join(d for _, _, d in code)).hexdigest()[:12]
-    vars_ = {"REV": rev, "AI_MODEL": cf.env("AICHARTS_AI_MODEL", cf.AI_MODEL), "AI_DAILY": cf.env("AICHARTS_AI_DAILY", "300"),
+    vars_ = {"REV": rev, "AI_MODEL": cf.env("AICHARTS_AI_MODEL", "@cf/meta/llama-3.3-70b-instruct-fp8-fast"), "AI_DAILY": cf.env("AICHARTS_AI_DAILY", "300"),
              "SAVE_DAILY": cf.env("AICHARTS_SAVE_DAILY", "1000")}
     db = cf.database("aicharts")  # named time-aicharts, like the script
     meta = {"main_module": "main.js", "compatibility_date": cf.COMPAT,

.github/time/labs/aicharts/worker.js

@@ -162,7 +162,7 @@ export function normalizeSpec(spec) {
 // Plain prompt first: the prompt's grammar and example steer small models better than a constrained decoder does (a
 // one-size schema for every step made them drop agg and by). JSON mode only when no object came back at all.
 async function model(env, messages) {
-  const input = { messages, max_tokens: 700, temperature: 0.1 };
+  const input = { messages, max_tokens: 900, temperature: 0.1 };
   const text = (out) => out?.response ?? out?.choices?.[0]?.message?.content ?? "";
   let raw = text(await env.AI.run(env.AI_MODEL, input));
   if (!firstObject(raw)) {