ai 5.0.0-canary.20 → 5.0.0-canary.21
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/CHANGELOG.md +51 -0
- package/dist/index.d.mts +467 -512
- package/dist/index.d.ts +467 -512
- package/dist/index.js +989 -1411
- package/dist/index.js.map +1 -1
- package/dist/index.mjs +947 -1368
- package/dist/index.mjs.map +1 -1
- package/dist/internal/index.d.mts +7 -13
- package/dist/internal/index.d.ts +7 -13
- package/dist/internal/index.js +126 -126
- package/dist/internal/index.js.map +1 -1
- package/dist/internal/index.mjs +119 -119
- package/dist/internal/index.mjs.map +1 -1
- package/package.json +2 -2
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,56 @@
|
|
|
1
1
|
# ai
|
|
2
2
|
|
|
3
|
+
## 5.0.0-canary.21
|
|
4
|
+
|
|
5
|
+
### Major Changes
|
|
6
|
+
|
|
7
|
+
- d964901: - remove setting temperature to `0` by default
|
|
8
|
+
- remove `null` option from `DefaultSettingsMiddleware`
|
|
9
|
+
- remove setting defaults for `temperature` and `stopSequences` in `ai` to enable middleware changes
|
|
10
|
+
- 0560977: chore (ai): improve consistency of generate text result, stream text result, and step result
|
|
11
|
+
- 516be5b: ### Move Image Model Settings into generate options
|
|
12
|
+
|
|
13
|
+
Image Models no longer have settings. Instead, `maxImagesPerCall` can be passed directly to `generateImage()`. All other image settings can be passed to `providerOptions[provider]`.
|
|
14
|
+
|
|
15
|
+
Before
|
|
16
|
+
|
|
17
|
+
```js
|
|
18
|
+
await generateImage({
|
|
19
|
+
model: luma.image('photon-flash-1', {
|
|
20
|
+
maxImagesPerCall: 5,
|
|
21
|
+
pollIntervalMillis: 500,
|
|
22
|
+
}),
|
|
23
|
+
prompt,
|
|
24
|
+
n: 10,
|
|
25
|
+
});
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
After
|
|
29
|
+
|
|
30
|
+
```js
|
|
31
|
+
await generateImage({
|
|
32
|
+
model: luma.image('photon-flash-1'),
|
|
33
|
+
prompt,
|
|
34
|
+
n: 10,
|
|
35
|
+
maxImagesPerCall: 5,
|
|
36
|
+
providerOptions: {
|
|
37
|
+
luma: { pollIntervalMillis: 5 },
|
|
38
|
+
},
|
|
39
|
+
});
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
Pull Request: https://github.com/vercel/ai/pull/6180
|
|
43
|
+
|
|
44
|
+
- bfbfc4c: feat (ai): streamText/generateText: totalUsage contains usage for all steps. usage is for a single step.
|
|
45
|
+
- ea7a7c9: feat (ui): UI message metadata
|
|
46
|
+
- 1409e13: chore (ai): remove experimental continueSteps
|
|
47
|
+
|
|
48
|
+
### Patch Changes
|
|
49
|
+
|
|
50
|
+
- 66af894: fix (ai): respect content order in toResponseMessages
|
|
51
|
+
- Updated dependencies [ea7a7c9]
|
|
52
|
+
- @ai-sdk/provider-utils@3.0.0-canary.17
|
|
53
|
+
|
|
3
54
|
## 5.0.0-canary.20
|
|
4
55
|
|
|
5
56
|
### Major Changes
|