@runpod/ai-sdk-provider 0.3.0 → 0.3.2
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 +12 -0
- package/README.md +5 -18
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,17 @@
|
|
|
1
1
|
# @runpod/ai-sdk-provider
|
|
2
2
|
|
|
3
|
+
## 0.3.2
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- 012cb6f: docs: moved "get api key on console" into "apiKey"
|
|
8
|
+
|
|
9
|
+
## 0.3.1
|
|
10
|
+
|
|
11
|
+
### Patch Changes
|
|
12
|
+
|
|
13
|
+
- 179e006: docs: improve intro and outro
|
|
14
|
+
|
|
3
15
|
## 0.3.0
|
|
4
16
|
|
|
5
17
|
### Minor Changes
|
package/README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
|
1
1
|
# Runpod AI SDK Provider
|
|
2
2
|
|
|
3
|
-
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.
|
|
3
|
+
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.
|
|
4
|
+
|
|
5
|
+
Runpod is the foundation for developers to build, deploy, and scale custom AI systems.
|
|
4
6
|
|
|
5
7
|
## Setup
|
|
6
8
|
|
|
@@ -54,6 +56,7 @@ You can use the following optional settings to customize the Runpod provider ins
|
|
|
54
56
|
|
|
55
57
|
API key that is being sent using the `Authorization` header.
|
|
56
58
|
It defaults to the `RUNPOD_API_KEY` environment variable.
|
|
59
|
+
You can obtain your api key from the [Runpod Console](https://console.runpod.io/user/settings) under "API Keys".
|
|
57
60
|
|
|
58
61
|
- **headers** _Record<string,string>_
|
|
59
62
|
|
|
@@ -65,8 +68,6 @@ You can use the following optional settings to customize the Runpod provider ins
|
|
|
65
68
|
You can use it as a middleware to intercept requests,
|
|
66
69
|
or to provide a custom fetch implementation for e.g. testing.
|
|
67
70
|
|
|
68
|
-
You can obtain your Runpod API key from the [Runpod Console](https://console.runpod.io/user/settings) under "API Keys".
|
|
69
|
-
|
|
70
71
|
## Language Models
|
|
71
72
|
|
|
72
73
|
You can create language models using the provider instance. The first argument is the model ID:
|
|
@@ -304,21 +305,7 @@ Runpod image models support flexible provider options through the `providerOptio
|
|
|
304
305
|
|
|
305
306
|
## Advanced Features
|
|
306
307
|
|
|
307
|
-
Runpod offers
|
|
308
|
-
|
|
309
|
-
1. **Multiple Model Families**: Access to both language models (LLMs) and cutting-edge image generation models.
|
|
310
|
-
|
|
311
|
-
2. **OpenAI Compatibility**: Language models support full OpenAI API features including function calling and structured output.
|
|
312
|
-
|
|
313
|
-
3. **Custom Endpoint Support**: Use with vLLM, SGLang, or any OpenAI-compatible server.
|
|
314
|
-
|
|
315
|
-
4. **Advanced Image Controls**: Fine-tune image generation with parameters like inference steps, guidance scale, and output format.
|
|
316
|
-
|
|
317
|
-
5. **Context-Aware Generation**: Transform existing images with Flux Kontext models using URL or base64 inputs.
|
|
318
|
-
|
|
319
|
-
6. **Automatic Polling**: Seamless handling of both synchronous and asynchronous image generation.
|
|
320
|
-
|
|
321
|
-
7. **Strict Validation**: Clear error messages for unsupported parameters to prevent confusion.
|
|
308
|
+
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.
|
|
322
309
|
|
|
323
310
|
## Links
|
|
324
311
|
|