@picsart/ai-sdk 6.53.2 → 6.55.0
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 +5 -4
- package/_vendor/workflows-types/index.d.ts +3001 -2817
- package/index.d.ts +38 -1
- package/index.js +135 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -194,7 +194,7 @@ names or catalog model IDs from an arbitrary vendor request.
|
|
|
194
194
|
|
|
195
195
|
## Text Generation (LLMs)
|
|
196
196
|
|
|
197
|
-
Claude, GPT, Gemini, Kimi and
|
|
197
|
+
Claude, GPT, Gemini, Kimi, Grok and MiniMax text models are called with `generateText()`. Single-shot:
|
|
198
198
|
pass a prompt and optional image(s)/video, get text back. They surface in the catalog
|
|
199
199
|
as `mode: 'text'`. Each vendor uses its own native workflow, so capabilities aren't lost
|
|
200
200
|
— Gemini accepts video input, Claude uses the Anthropic-native messages API.
|
|
@@ -227,9 +227,10 @@ await ai.generateText(Models.Gemini3Pro, {
|
|
|
227
227
|
catalog.find({ output: 'text' })
|
|
228
228
|
```
|
|
229
229
|
|
|
230
|
-
> Thinking level maps per vendor: OpenAI, Kimi and
|
|
231
|
-
> `thinkingConfig.thinkingLevel` (LOW/HIGH). Kimi K3
|
|
232
|
-
> they have no `off`.
|
|
230
|
+
> Thinking level maps per vendor: OpenAI, Kimi, Grok and MiniMax M3.1 Flash → `reasoning_effort`, Gemini →
|
|
231
|
+
> `thinkingConfig.thinkingLevel` (LOW/HIGH). Kimi K3, Grok 4.7 and MiniMax M3.1 Flash
|
|
232
|
+
> always reason, so they have no `off`. MiniMax M3 reasons adaptively and has no
|
|
233
|
+
> thinking knob. Claude’s `claude/v1/messages`
|
|
233
234
|
> workflow exposes no thinking knob, so Claude models omit `thinking`.
|
|
234
235
|
|
|
235
236
|
`generateText()` is type-narrowed to text models (`TextModelId`); calling it with an
|