@ljoukov/llm 7.0.2 → 7.0.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +11 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -491,6 +491,17 @@ const { value } = await generateJson({
|
|
|
491
491
|
console.log(value.ok, value.message);
|
|
492
492
|
```
|
|
493
493
|
|
|
494
|
+
For calls that should use a smaller reasoning budget, pass the cross-model `thinkingLevel` option:
|
|
495
|
+
|
|
496
|
+
```ts
|
|
497
|
+
const { value } = await generateJson({
|
|
498
|
+
model: "gemini-flash-latest",
|
|
499
|
+
input: "Return a JSON object with ok=true and message='hello'.",
|
|
500
|
+
schema,
|
|
501
|
+
thinkingLevel: "low",
|
|
502
|
+
});
|
|
503
|
+
```
|
|
504
|
+
|
|
494
505
|
### Streaming JSON outputs
|
|
495
506
|
|
|
496
507
|
Use `streamJson()` to stream thought deltas and get best-effort partial JSON snapshots while the model is still
|
package/package.json
CHANGED