@ai-sdk/deepinfra 2.0.17 → 2.0.18

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @ai-sdk/deepinfra
 
+## 2.0.18
+
+### Patch Changes
+
+- 2b8369d: chore: add docs to package dist
+
 ## 2.0.17
 
 ### Patch Changes

package/dist/index.js

@@ -161,7 +161,7 @@ async function fileToBlob(file) {
 }
 
 // src/version.ts
-var VERSION = true ? "2.0.17" : "0.0.0-test";
+var VERSION = true ? "2.0.18" : "0.0.0-test";
 
 // src/deepinfra-provider.ts
 function createDeepInfra(options = {}) {

package/dist/index.mjs

@@ -150,7 +150,7 @@ async function fileToBlob(file) {
 }
 
 // src/version.ts
-var VERSION = true ? "2.0.17" : "0.0.0-test";
+var VERSION = true ? "2.0.18" : "0.0.0-test";
 
 // src/deepinfra-provider.ts
 function createDeepInfra(options = {}) {

package/docs/11-deepinfra.mdx

@@ -0,0 +1,292 @@
+---
+title: DeepInfra
+description: Learn how to use DeepInfra's models with the AI SDK.
+---
+
+# DeepInfra Provider
+
+The [DeepInfra](https://deepinfra.com) provider contains support for state-of-the-art models through the DeepInfra API, including Llama 3, Mixtral, Qwen, and many other popular open-source models.
+
+## Setup
+
+The DeepInfra provider is available via the `@ai-sdk/deepinfra` module. You can install it with:
+
+<Tabs items={['pnpm', 'npm', 'yarn', 'bun']}>
+  <Tab>
+    <Snippet text="pnpm add @ai-sdk/deepinfra" dark />
+  </Tab>
+  <Tab>
+    <Snippet text="npm install @ai-sdk/deepinfra" dark />
+  </Tab>
+  <Tab>
+    <Snippet text="yarn add @ai-sdk/deepinfra" dark />
+  </Tab>
+
+  <Tab>
+    <Snippet text="bun add @ai-sdk/deepinfra" dark />
+  </Tab>
+</Tabs>
+
+## Provider Instance
+
+You can import the default provider instance `deepinfra` from `@ai-sdk/deepinfra`:
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+```
+
+If you need a customized setup, you can import `createDeepInfra` from `@ai-sdk/deepinfra` and create a provider instance with your settings:
+
+```ts
+import { createDeepInfra } from '@ai-sdk/deepinfra';
+
+const deepinfra = createDeepInfra({
+  apiKey: process.env.DEEPINFRA_API_KEY ?? '',
+});
+```
+
+You can use the following optional settings to customize the DeepInfra provider instance:
+
+- **baseURL** _string_
+
+  Use a different URL prefix for API calls, e.g. to use proxy servers.
+  The default prefix is `https://api.deepinfra.com/v1`.
+
+  Note: Language models and embeddings use OpenAI-compatible endpoints at `{baseURL}/openai`,
+  while image models use `{baseURL}/inference`.
+
+- **apiKey** _string_
+
+  API key that is being sent using the `Authorization` header. It defaults to
+  the `DEEPINFRA_API_KEY` environment variable.
+
+- **headers** _Record&lt;string,string&gt;_
+
+  Custom headers to include in the requests.
+
+- **fetch** _(input: RequestInfo, init?: RequestInit) => Promise&lt;Response&gt;_
+
+  Custom [fetch](https://developer.mozilla.org/en-US/docs/Web/API/fetch) implementation.
+  Defaults to the global `fetch` function.
+  You can use it as a middleware to intercept requests,
+  or to provide a custom fetch implementation for e.g. testing.
+
+## Language Models
+
+You can create language models using a provider instance. The first argument is the model ID, for example:
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+import { generateText } from 'ai';
+
+const { text } = await generateText({
+  model: deepinfra('meta-llama/Meta-Llama-3.1-70B-Instruct'),
+  prompt: 'Write a vegetarian lasagna recipe for 4 people.',
+});
+```
+
+DeepInfra language models can also be used in the `streamText` function (see [AI SDK Core](/docs/ai-sdk-core)).
+
+## Model Capabilities
+
+| Model                                               | Image Input         | Object Generation   | Tool Usage          | Tool Streaming      |
+| --------------------------------------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
+| `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `meta-llama/Llama-4-Scout-17B-16E-Instruct`         | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `meta-llama/Llama-3.3-70B-Instruct-Turbo`           | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Llama-3.3-70B-Instruct`                 | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Meta-Llama-3.1-405B-Instruct`           | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`      | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Meta-Llama-3.1-70B-Instruct`            | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`       | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
+| `meta-llama/Meta-Llama-3.1-8B-Instruct`             | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Llama-3.2-11B-Vision-Instruct`          | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `meta-llama/Llama-3.2-90B-Vision-Instruct`          | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `mistralai/Mixtral-8x7B-Instruct-v0.1`              | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
+| `deepseek-ai/DeepSeek-V3`                           | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `deepseek-ai/DeepSeek-R1`                           | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`         | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `deepseek-ai/DeepSeek-R1-Turbo`                     | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `nvidia/Llama-3.1-Nemotron-70B-Instruct`            | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
+| `Qwen/Qwen2-7B-Instruct`                            | <Cross size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `Qwen/Qwen2.5-72B-Instruct`                         | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `Qwen/Qwen2.5-Coder-32B-Instruct`                   | <Cross size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `Qwen/QwQ-32B-Preview`                              | <Cross size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `google/codegemma-7b-it`                            | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `google/gemma-2-9b-it`                              | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `microsoft/WizardLM-2-8x22B`                        | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+
+<Note>
+  The table above lists popular models. Please see the [DeepInfra
+  docs](https://deepinfra.com) for a full list of available models. You can also
+  pass any available provider model ID as a string if needed.
+</Note>
+
+## Image Models
+
+You can create DeepInfra image models using the `.image()` factory method.
+For more on image generation with the AI SDK see [generateImage()](/docs/reference/ai-sdk-core/generate-image).
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+import { generateImage } from 'ai';
+
+const { image } = await generateImage({
+  model: deepinfra.image('stabilityai/sd3.5'),
+  prompt: 'A futuristic cityscape at sunset',
+  aspectRatio: '16:9',
+});
+```
+
+<Note>
+  Model support for `size` and `aspectRatio` parameters varies by model. Please
+  check the individual model documentation on [DeepInfra's models
+  page](https://deepinfra.com/models/text-to-image) for supported options and
+  additional parameters.
+</Note>
+
+### Model-specific options
+
+You can pass model-specific parameters using the `providerOptions.deepinfra` field:
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+import { generateImage } from 'ai';
+
+const { image } = await generateImage({
+  model: deepinfra.image('stabilityai/sd3.5'),
+  prompt: 'A futuristic cityscape at sunset',
+  aspectRatio: '16:9',
+  providerOptions: {
+    deepinfra: {
+      num_inference_steps: 30, // Control the number of denoising steps (1-50)
+    },
+  },
+});
+```
+
+### Image Editing
+
+DeepInfra supports image editing through models like `Qwen/Qwen-Image-Edit`. Pass input images via `prompt.images` to transform or edit existing images.
+
+#### Basic Image Editing
+
+Transform an existing image using text prompts:
+
+```ts
+const imageBuffer = readFileSync('./input-image.png');
+
+const { images } = await generateImage({
+  model: deepinfra.image('Qwen/Qwen-Image-Edit'),
+  prompt: {
+    text: 'Turn the cat into a golden retriever dog',
+    images: [imageBuffer],
+  },
+  size: '1024x1024',
+});
+```
+
+#### Inpainting with Mask
+
+Edit specific parts of an image using a mask. Transparent areas in the mask indicate where the image should be edited:
+
+```ts
+const image = readFileSync('./input-image.png');
+const mask = readFileSync('./mask.png');
+
+const { images } = await generateImage({
+  model: deepinfra.image('Qwen/Qwen-Image-Edit'),
+  prompt: {
+    text: 'A sunlit indoor lounge area with a pool containing a flamingo',
+    images: [image],
+    mask: mask,
+  },
+});
+```
+
+#### Multi-Image Combining
+
+Combine multiple reference images into a single output:
+
+```ts
+const cat = readFileSync('./cat.png');
+const dog = readFileSync('./dog.png');
+
+const { images } = await generateImage({
+  model: deepinfra.image('Qwen/Qwen-Image-Edit'),
+  prompt: {
+    text: 'Create a scene with both animals together, playing as friends',
+    images: [cat, dog],
+  },
+});
+```
+
+<Note>
+  Input images can be provided as `Buffer`, `ArrayBuffer`, `Uint8Array`, or
+  base64-encoded strings. DeepInfra uses an OpenAI-compatible image editing API
+  at `https://api.deepinfra.com/v1/openai/images/edits`.
+</Note>
+
+### Model Capabilities
+
+For models supporting aspect ratios, the following ratios are typically supported:
+`1:1 (default), 16:9, 1:9, 3:2, 2:3, 4:5, 5:4, 9:16, 9:21`
+
+For models supporting size parameters, dimensions must typically be:
+
+- Multiples of 32
+- Width and height between 256 and 1440 pixels
+- Default size is 1024x1024
+
+| Model                              | Dimensions Specification | Notes                                                    |
+| ---------------------------------- | ------------------------ | -------------------------------------------------------- |
+| `stabilityai/sd3.5`                | Aspect Ratio             | Premium quality base model, 8B parameters                |
+| `black-forest-labs/FLUX-1.1-pro`   | Size                     | Latest state-of-art model with superior prompt following |
+| `black-forest-labs/FLUX-1-schnell` | Size                     | Fast generation in 1-4 steps                             |
+| `black-forest-labs/FLUX-1-dev`     | Size                     | Optimized for anatomical accuracy                        |
+| `black-forest-labs/FLUX-pro`       | Size                     | Flagship Flux model                                      |
+| `stabilityai/sd3.5-medium`         | Aspect Ratio             | Balanced 2.5B parameter model                            |
+| `stabilityai/sdxl-turbo`           | Aspect Ratio             | Optimized for fast generation                            |
+
+For more details and pricing information, see the [DeepInfra text-to-image models page](https://deepinfra.com/models/text-to-image).
+
+## Embedding Models
+
+You can create DeepInfra embedding models using the `.embedding()` factory method.
+For more on embedding models with the AI SDK see [embed()](/docs/reference/ai-sdk-core/embed).
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+import { embed } from 'ai';
+
+const { embedding } = await embed({
+  model: deepinfra.embedding('BAAI/bge-large-en-v1.5'),
+  value: 'sunny day at the beach',
+});
+```
+
+### Model Capabilities
+
+| Model                                                 | Dimensions | Max Tokens |
+| ----------------------------------------------------- | ---------- | ---------- |
+| `BAAI/bge-base-en-v1.5`                               | 768        | 512        |
+| `BAAI/bge-large-en-v1.5`                              | 1024       | 512        |
+| `BAAI/bge-m3`                                         | 1024       | 8192       |
+| `intfloat/e5-base-v2`                                 | 768        | 512        |
+| `intfloat/e5-large-v2`                                | 1024       | 512        |
+| `intfloat/multilingual-e5-large`                      | 1024       | 512        |
+| `sentence-transformers/all-MiniLM-L12-v2`             | 384        | 256        |
+| `sentence-transformers/all-MiniLM-L6-v2`              | 384        | 256        |
+| `sentence-transformers/all-mpnet-base-v2`             | 768        | 384        |
+| `sentence-transformers/clip-ViT-B-32`                 | 512        | 77         |
+| `sentence-transformers/clip-ViT-B-32-multilingual-v1` | 512        | 77         |
+| `sentence-transformers/multi-qa-mpnet-base-dot-v1`    | 768        | 512        |
+| `sentence-transformers/paraphrase-MiniLM-L6-v2`       | 384        | 128        |
+| `shibing624/text2vec-base-chinese`                    | 768        | 512        |
+| `thenlper/gte-base`                                   | 768        | 512        |
+| `thenlper/gte-large`                                  | 1024       | 512        |
+
+<Note>
+  For a complete list of available embedding models, see the [DeepInfra
+  embeddings page](https://deepinfra.com/models/embeddings).
+</Note>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/deepinfra",
-  "version": "2.0.17",
+  "version": "2.0.18",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -8,10 +8,14 @@
   "types": "./dist/index.d.ts",
   "files": [
     "dist/**/*",
+    "docs/**/*",
     "src",
     "CHANGELOG.md",
     "README.md"
   ],
+  "directories": {
+    "doc": "./docs"
+  },
   "exports": {
     "./package.json": "./package.json",
     ".": {
@@ -56,7 +60,7 @@
   "scripts": {
     "build": "pnpm clean && tsup --tsconfig tsconfig.build.json",
     "build:watch": "pnpm clean && tsup --watch",
-    "clean": "del-cli dist *.tsbuildinfo",
+    "clean": "del-cli dist docs *.tsbuildinfo",
     "lint": "eslint \"./**/*.ts*\"",
     "type-check": "tsc --build",
     "prettier-check": "prettier --check \"./**/*.ts*\"",