Open Responses supported AI SDK functions
Open Responses models support generateText and streamText functions, and they support structured data generation with Output (AI SDK Core).
AI SDK · Providers · all subjects
open-responses/capabilities
5 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.
Open Responses file inputs support
The provider supports image and non-image file inputs in user messages. Images are sent as input_image parts, while other media types such as PDFs are sent as input_file parts. Files can be provided as inline data or as URLs.
Open Responses file input example
Example code: import { createOpenResponses } from '@ai-sdk/open-responses'; import { readFileSync } from 'node:fs'; import { generateText } from 'ai'; const openResponses = createOpenResponses({ name: 'lmstudio', url: 'http://localhost:1234/v1/responses', }); const { text } = await generateText({ model: openResponses('your-file-capable-model-id'), messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.', }, { type: 'file', data: readFileSync('./document.pdf'), mediaType: 'application/pdf', filename: 'document.pdf', }, ], }, ], }); console.log(text);
Open Responses unsupported features
Stop sequences, topK, and seed are not supported and are ignored with warnings. The provider supports language models only and does not provide embedding or image generation models. Provider-specific built-in tools and options require a dedicated provider implementation. AI SDK function tools are supported.
Text generation with Open Responses
Open Responses integration supports both streaming and non-streaming text generation using the AI SDK. **Setup:** ```javascript import { createOpenResponses } from '@ai-sdk/open-responses'; import { streamText, generateText } from 'ai'; const openResponses = createOpenResponses({ name: 'lmstudio', url: 'http://localhost:1234/v1/responses', }); ``` **Streaming text with streamText:** ```javascript const result = streamText({ model: openResponses('your-model-id'), prompt: 'Invent a new holiday and describe its traditions.', }); for await (const textPart of result.textStream) { process.stdout.write(textPart); } ``` **Non-streaming text with generateText:** ```javascript const { text } = await generateText({ model: openResponses('your-model-id'), prompt: 'Invent a new holiday and describe its traditions.', }); console.log(text); ``` Both approaches use the same model initialization with LM Studio at `http://localhost:1234/v1/responses`.