wong2

Support Azure AI Model Inference API provider

1

### Feature Description Today I deployed the Llama 3.1 model using Azure AI Studio and got it ready to use through the AI SDK. I originally thought its API was...

I understand that when asking specific questions, we can use vector search to find relevant part of the document. But if the user ask "Please summarize the document", vector searching...

Fix requestOptions in startChat

7

Fix https://github.com/google-gemini/generative-ai-js/issues/227 In PR https://github.com/google-gemini/generative-ai-js/pull/144, the `requestOptions` of `GenerativeModel` is renamed to `_requestOptions`, but there's a `requestOptions` type declaration on the class, so TypeScript didn't catch the miss use of...

### Description of the bug: I'm upgrading the sdk from 0.15.0 and found that the `baseUrl` requestion option stops working. ### Actual vs expected behavior: I have the following code:...

Failed to import `vaul/style.css`

5

I'm using v1.0.0, import 'vaul/style.css' results in an error: ``` [plugin:vite:import-analysis] Missing "./style.css" specifier in "vaul" package ``` I found a similar case https://github.com/vitejs/vite/issues/6480#issuecomment-1011937533

Interactive updates (`pnpm update -i`) crashes in packages that use the catalog protocol

5

### Verify latest release - [X] I verified that the issue exists in the latest pnpm release ### pnpm version 9.11.0 ### Which area(s) of pnpm are affected? (leave empty...

`clientLoader` behaviour change since v2.12.0

4

### Reproduction I have a route using client loader like this: ``` export const loader = async ({ params }: LoaderFunctionArgs) => { const botInfo = BUILTIN_CHATBOTS[params.botId] return { title:...

### Description Currently, when errors happen in tool execution, an exception is thrown and the generation stops. However, error is actually a valid result for function calling in OpenAI/Anthropic. So...