@ai-sdk/gmicloud 3.0.48 → 3.0.49

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 +1,16 @@
1
1
  # @ai-sdk/gmicloud
2
2
 
3
+ ## 3.0.49
4
+
5
+ ### Patch Changes
6
+
7
+ - e729d58: chore(docs): update `README.md` for consistent format and to avoid duplication
8
+ - Updated dependencies [5475347]
9
+ - Updated dependencies [e729d58]
10
+ - @ai-sdk/provider@4.0.34
11
+ - @ai-sdk/openai-compatible@3.0.78
12
+ - @ai-sdk/provider-utils@5.0.68
13
+
3
14
  ## 3.0.48
4
15
 
5
16
  ### Patch Changes
package/README.md CHANGED
@@ -6,31 +6,11 @@ The **GMI Cloud provider** for the [AI SDK](https://ai-sdk.dev/docs) contains la
6
6
 
7
7
  ## Setup
8
8
 
9
- The GMI Cloud provider is available in the `@ai-sdk/gmicloud` module. You can install it with
10
-
11
9
  ```bash
12
- npm i @ai-sdk/gmicloud
10
+ npm i ai @ai-sdk/gmicloud
13
11
  ```
14
12
 
15
- ## Provider Instance
16
-
17
- You can import the default provider instance `gmicloud` from `@ai-sdk/gmicloud`:
18
-
19
- ```ts
20
- import { gmicloud } from '@ai-sdk/gmicloud';
21
- ```
22
-
23
- The GMI Cloud API key is read from the `GMI_CLOUD_APIKEY` environment variable by default. For custom configuration, use `createGmicloud`:
24
-
25
- ```ts
26
- import { createGmicloud } from '@ai-sdk/gmicloud';
27
-
28
- const gmicloud = createGmicloud({
29
- apiKey: process.env.GMI_CLOUD_APIKEY ?? '',
30
- });
31
- ```
32
-
33
- ## Language Models
13
+ ## Usage
34
14
 
35
15
  ```ts
36
16
  import { gmicloud } from '@ai-sdk/gmicloud';
@@ -42,8 +22,4 @@ const { text } = await generateText({
42
22
  });
43
23
  ```
44
24
 
45
- GMI Cloud serves an evolving catalog of open-weight models over chat completions, so model ids are typed as `string`. Embedding and image models are not supported.
46
-
47
- ## Error diagnostics
48
-
49
- GMI Cloud's edge reports a generic banner in `error.message` on rejections and nests the backend engine's diagnostic in `error.details`. This provider unwraps the nested diagnostic, so `AI_APICallError.message` carries the engine's reason (e.g. `The request is invalid: Invalid max_tokens value, the valid range of max_tokens is [1, 393216].`) instead of `Backend request failed with status 400`.
25
+ See the [GMI Cloud Provider documentation](https://ai-sdk.dev/providers/ai-sdk-providers/gmicloud) for more information.
package/dist/index.js CHANGED
@@ -46,7 +46,7 @@ const gmicloudErrorStructure = {
46
46
  };
47
47
  //#endregion
48
48
  //#region src/version.ts
49
- const VERSION = "3.0.48";
49
+ const VERSION = "3.0.49";
50
50
  //#endregion
51
51
  //#region src/gmicloud-provider.ts
52
52
  function createGmicloud(options = {}) {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@ai-sdk/gmicloud",
3
- "version": "3.0.48",
3
+ "version": "3.0.49",
4
4
  "type": "module",
5
5
  "license": "Apache-2.0",
6
6
  "sideEffects": false,
@@ -29,9 +29,9 @@
29
29
  }
30
30
  },
31
31
  "dependencies": {
32
- "@ai-sdk/openai-compatible": "3.0.77",
33
- "@ai-sdk/provider": "4.0.33",
34
- "@ai-sdk/provider-utils": "5.0.67"
32
+ "@ai-sdk/openai-compatible": "3.0.78",
33
+ "@ai-sdk/provider": "4.0.34",
34
+ "@ai-sdk/provider-utils": "5.0.68"
35
35
  },
36
36
  "devDependencies": {
37
37
  "@types/node": "22.19.19",