ai 5.0.245 → 5.0.248

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
@@ -1,5 +1,33 @@
1
1
  # ai
2
2
 
3
+ ## 5.0.248
4
+
5
+ ### Patch Changes
6
+
7
+ - 77d33c0: Split OpenAI and Azure OpenAI embedding requests by a conservative UTF-8 byte budget derived from their aggregate token limit, in addition to input count limits.
8
+ - Updated dependencies [77d33c0]
9
+ - Updated dependencies [e0d7904]
10
+ - @ai-sdk/provider-utils@3.0.35
11
+ - @ai-sdk/gateway@2.0.143
12
+
13
+ ## 5.0.247
14
+
15
+ ### Patch Changes
16
+
17
+ - Updated dependencies [326a47b]
18
+ - @ai-sdk/gateway@2.0.142
19
+
20
+ ## 5.0.246
21
+
22
+ ### Patch Changes
23
+
24
+ - d1aa120: Include telemetry metadata on tool call spans.
25
+ - Updated dependencies [2fff9f1]
26
+ - Updated dependencies [f364ea0]
27
+ - Updated dependencies [8c37324]
28
+ - @ai-sdk/provider-utils@3.0.34
29
+ - @ai-sdk/gateway@2.0.141
30
+
3
31
  ## 5.0.245
4
32
 
5
33
  ### Patch Changes
package/dist/index.d.mts CHANGED
@@ -2456,8 +2456,9 @@ interface EmbedManyResult<VALUE> {
2456
2456
  Embed several values using an embedding model. The type of the value is defined
2457
2457
  by the embedding model.
2458
2458
 
2459
- `embedMany` automatically splits large requests into smaller chunks if the model
2460
- has a limit on how many embeddings can be generated in a single call.
2459
+ `embedMany` automatically splits large requests into smaller chunks when the
2460
+ model has a limit on either the number of embeddings or the UTF-8 input bytes
2461
+ that can be processed in a single call.
2461
2462
 
2462
2463
  @param model - The embedding model to use.
2463
2464
  @param values - The values that should be embedded.
package/dist/index.d.ts CHANGED
@@ -2456,8 +2456,9 @@ interface EmbedManyResult<VALUE> {
2456
2456
  Embed several values using an embedding model. The type of the value is defined
2457
2457
  by the embedding model.
2458
2458
 
2459
- `embedMany` automatically splits large requests into smaller chunks if the model
2460
- has a limit on how many embeddings can be generated in a single call.
2459
+ `embedMany` automatically splits large requests into smaller chunks when the
2460
+ model has a limit on either the number of embeddings or the UTF-8 input bytes
2461
+ that can be processed in a single call.
2461
2462
 
2462
2463
  @param model - The embedding model to use.
2463
2464
  @param values - The values that should be embedded.