@runpod/ai-sdk-provider 0.3.1 → 0.3.3

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # @runpod/ai-sdk-provider
 
+## 0.3.3
+
+### Patch Changes
+
+- 7adbc33: docs: moved everything into "about Runpod"
+
+## 0.3.2
+
+### Patch Changes
+
+- 012cb6f: docs: moved "get api key on console" into "apiKey"
+
 ## 0.3.1
 
 ### Patch Changes

package/README.md

@@ -2,8 +2,6 @@
 
 The **Runpod provider** for the [AI SDK](https://ai-sdk.dev/docs) contains language model and image generation support for [Runpod's](https://runpod.io) public endpoints.
 
-Runpod is the foundation for developers to build, deploy, and scale custom AI systems.
-
 ## Setup
 
 The Runpod provider is available in the `@runpod/ai-sdk-provider` module. You can install it with:
@@ -56,6 +54,7 @@ You can use the following optional settings to customize the Runpod provider ins
 
   API key that is being sent using the `Authorization` header.
   It defaults to the `RUNPOD_API_KEY` environment variable.
+  You can obtain your api key from the [Runpod Console](https://console.runpod.io/user/settings) under "API Keys".
 
 - **headers** _Record<string,string>_
 
@@ -67,8 +66,6 @@ You can use the following optional settings to customize the Runpod provider ins
   You can use it as a middleware to intercept requests,
   or to provide a custom fetch implementation for e.g. testing.
 
-You can obtain your Runpod API key from the [Runpod Console](https://console.runpod.io/user/settings) under "API Keys".
-
 ## Language Models
 
 You can create language models using the provider instance. The first argument is the model ID:
@@ -167,7 +164,6 @@ const { object } = await generateObject({
 ## Image Models
 
 You can create Runpod image models using the `.imageModel()` factory method.
-For more on image generation with the AI SDK see [generateImage()](/docs/reference/ai-sdk-core/generate-image).
 
 ### Basic Usage
 
@@ -304,13 +300,8 @@ Runpod image models support flexible provider options through the `providerOptio
 | `maxPollAttempts`       | `number`  | `60`    | Maximum polling attempts for async generation                           |
 | `pollIntervalMillis`    | `number`  | `5000`  | Polling interval in milliseconds (5 seconds)                            |
 
-## Advanced Features
-
-Runpod offers public endpoints (everything above), custom serverless endpoints / pods / clusters and a hub of open-source AI repositories including ComfyUI, Axolotl, FLUX.1-dev-juiced, Chatterbox, vLLM, and SGLang.
+## About Runpod
 
-## Links
+[Runpod](https://runpod.io) is the foundation for developers to build, deploy, and scale custom AI systems.
 
-- [Runpod](https://runpod.io) - Cloud platform for AI compute
-- [Runpod Public Endpoints Documentation](https://docs.runpod.io/hub/public-endpoints)
-- [AI SDK Documentation](https://ai-sdk.dev/docs)
-- [GitHub Repository](https://github.com/runpod/ai-sdk-provider)
+Beyond some of the public endpoints you've seen above (+ more generative media apis), Runpod offers custom [serverless endpoints](https://docs.runpod.io/serverless/overview), dedicated [pods](https://docs.runpod.io/pods/overview) and [instant clusters](https://docs.runpod.io/instant-clusters), [fine-tuning](https://docs.runpod.io/fine-tune), and a comprehensive [hub of open-source AI repos](https://docs.runpod.io/hub/overview) (like ComfyUI, Axolotl, FLUX.1-dev-juiced, Chatterbox, vLLM or SGLang).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@runpod/ai-sdk-provider",
-  "version": "0.3.1",
+  "version": "0.3.3",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",