@ai-sdk/provider 1.1.3 → 2.0.0-alpha.10

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 CHANGED
@@ -1,22 +1,215 @@
1
1
  # @ai-sdk/provider
2
2
 
3
- ## 1.1.3
3
+ ## 2.0.0-alpha.10
4
4
 
5
5
  ### Patch Changes
6
6
 
7
- - beef951: feat: add speech with experimental_generateSpeech
7
+ - c4df419: release alpha.10
8
8
 
9
- ## 1.1.2
9
+ ## 2.0.0-alpha.9
10
10
 
11
11
  ### Patch Changes
12
12
 
13
- - 013faa8: core (ai): change transcription model mimeType to mediaType
13
+ - 811dff3: release alpha.9
14
14
 
15
- ## 1.1.1
15
+ ## 2.0.0-alpha.8
16
16
 
17
17
  ### Patch Changes
18
18
 
19
- - c21fa6d: feat: add transcription with experimental_transcribe
19
+ - 9222aeb: release alpha.8
20
+
21
+ ## 2.0.0-alpha.7
22
+
23
+ ### Patch Changes
24
+
25
+ - 5c56081: release alpha.7
26
+
27
+ ## 2.0.0-alpha.6
28
+
29
+ ### Patch Changes
30
+
31
+ - 0d2c085: chore (provider): tweak provider definition
32
+
33
+ ## 2.0.0-alpha.4
34
+
35
+ ### Patch Changes
36
+
37
+ - dc714f3: release alpha.4
38
+
39
+ ## 2.0.0-alpha.3
40
+
41
+ ### Patch Changes
42
+
43
+ - 6b98118: release alpha.3
44
+
45
+ ## 2.0.0-alpha.2
46
+
47
+ ### Patch Changes
48
+
49
+ - 26535e0: release alpha.2
50
+
51
+ ## 2.0.0-alpha.1
52
+
53
+ ### Patch Changes
54
+
55
+ - 3f2f00c: feat: `ImageModelV2#maxImagesPerCall` can be set to a function that returns a `number` or `undefined`, optionally as a promise
56
+
57
+ pull request: https://github.com/vercel/ai/pull/6343
58
+
59
+ ## 2.0.0-canary.14
60
+
61
+ ### Major Changes
62
+
63
+ - 7979f7f: feat (provider): support reasoning tokens, cached input tokens, total token in usage information
64
+
65
+ ### Patch Changes
66
+
67
+ - a8c8bd5: feat(embed-many): respect supportsParallelCalls & concurrency
68
+
69
+ ## 2.0.0-canary.13
70
+
71
+ ### Patch Changes
72
+
73
+ - 9bd5ab5: feat (provider): add providerMetadata to ImageModelV2 interface (#5977)
74
+
75
+ The `experimental_generateImage` method from the `ai` package now returnes revised prompts for OpenAI's image models.
76
+
77
+ ```js
78
+ const prompt = 'Santa Claus driving a Cadillac';
79
+
80
+ const { providerMetadata } = await experimental_generateImage({
81
+ model: openai.image('dall-e-3'),
82
+ prompt,
83
+ });
84
+
85
+ const revisedPrompt = providerMetadata.openai.images[0]?.revisedPrompt;
86
+
87
+ console.log({
88
+ prompt,
89
+ revisedPrompt,
90
+ });
91
+ ```
92
+
93
+ ## 2.0.0-canary.12
94
+
95
+ ### Patch Changes
96
+
97
+ - 7b3ae3f: chore (provider): change getSupportedUrls to supportedUrls (language model v2)
98
+
99
+ ## 2.0.0-canary.11
100
+
101
+ ### Major Changes
102
+
103
+ - e030615: chore (provider): remove prompt type from language model v2 spec
104
+
105
+ ### Patch Changes
106
+
107
+ - 9bf7291: chore(providers/openai): enable structuredOutputs by default & switch to provider option
108
+ - 4617fab: chore(embedding-models): remove remaining settings
109
+
110
+ ## 2.0.0-canary.10
111
+
112
+ ### Major Changes
113
+
114
+ - a3f768e: chore: restructure reasoning support
115
+
116
+ ### Patch Changes
117
+
118
+ - 9301f86: refactor (image-model): rename `ImageModelV1` to `ImageModelV2`
119
+
120
+ ## 2.0.0-canary.9
121
+
122
+ ### Major Changes
123
+
124
+ - e86be6f: chore: remove logprobs
125
+
126
+ ## 2.0.0-canary.8
127
+
128
+ ### Major Changes
129
+
130
+ - 95857aa: chore: restructure language model supported urls
131
+ - 7ea4132: chore: remove object generation mode
132
+
133
+ ## 2.0.0-canary.7
134
+
135
+ ### Major Changes
136
+
137
+ - b6b43c7: chore: move warnings into stream-start part (spec)
138
+ - 3795467: chore: return content array from doGenerate (spec)
139
+
140
+ ### Patch Changes
141
+
142
+ - 8aa9e20: feat: add speech with experimental_generateSpeech
143
+
144
+ ## 2.0.0-canary.6
145
+
146
+ ### Major Changes
147
+
148
+ - 14c9410: chore: refactor file towards source pattern (spec)
149
+ - d9c98f4: chore: refactor reasoning parts (spec)
150
+ - 0054544: chore: refactor source parts (spec)
151
+ - 9e9c809: chore: refactor tool call and tool call delta parts (spec)
152
+ - 32831c6: chore: refactor text parts (spec)
153
+ - d0f9495: chore: refactor file parts (spec)
154
+
155
+ ### Patch Changes
156
+
157
+ - 26735b5: chore(embedding-model): add v2 interface
158
+ - 443d8ec: feat(embedding-model-v2): add response body field
159
+ - c4a2fec: chore (provider): extract shared provider options and metadata (spec)
160
+ - fd65bc6: chore(embedding-model-v2): rename rawResponse to response
161
+ - 393138b: feat(embedding-model-v2): add providerOptions
162
+ - 7182d14: Remove `Experimental_LanguageModelV2Middleware` type
163
+
164
+ ## 2.0.0-canary.5
165
+
166
+ ### Major Changes
167
+
168
+ - 411e483: chore (provider): refactor usage (language model v2)
169
+ - ad80501: chore (provider): allow both binary and base64 file content (spec)
170
+ - 1766ede: chore: rename maxTokens to maxOutputTokens
171
+
172
+ ### Patch Changes
173
+
174
+ - 79457bd: chore (provider): extract LanguageModelV2File
175
+ - f10304b: feat(tool-calling): don't require the user to have to pass parameters
176
+
177
+ ## 2.0.0-canary.4
178
+
179
+ ### Major Changes
180
+
181
+ - 6f6bb89: chore (provider): cleanup request and rawRequest (language model v2)
182
+
183
+ ## 2.0.0-canary.3
184
+
185
+ ### Major Changes
186
+
187
+ - d1a1aa1: chore (provider): merge rawRequest into request (language model v2)
188
+
189
+ ## 2.0.0-canary.2
190
+
191
+ ### Major Changes
192
+
193
+ - abf9a79: chore: rename mimeType to mediaType
194
+ - 6dc848c: chore (provider): remove image parts
195
+
196
+ ### Patch Changes
197
+
198
+ - a166433: feat: add transcription with experimental_transcribe
199
+ - 0a87932: core (ai): change transcription model mimeType to mediaType
200
+
201
+ ## 2.0.0-canary.1
202
+
203
+ ### Major Changes
204
+
205
+ - c57e248: chore (provider): remove mode
206
+ - 33f4a6a: chore (provider): rename providerMetadata inputs to providerOptions
207
+
208
+ ## 2.0.0-canary.0
209
+
210
+ ### Major Changes
211
+
212
+ - d5f588f: AI SDK 5
20
213
 
21
214
  ## 1.1.0
22
215