Version:
interfaceextends Omit<UseVisionProviderOptions, "defaultModel" | "openaiCompatible">
UseOpenAICompatibleVisionProviderOptions
Options for useOpenAICompatibleVisionProvider.
Targets self-hosted servers that implement the OpenAI Chat Completions API
(e.g. vLLM, LMStudio, llama.cpp, LocalAI). Both the model ID and theopenaiCompatible server config are required because there is no sensible
default for either.
typescript
interface UseOpenAICompatibleVisionProviderOptions extends Omit<UseVisionProviderOptions, "defaultModel" | "openaiCompatible">Properties
| Name | Type | Description |
|---|---|---|
anthropic? | { apiKey: string; baseURL: string } | Anthropic provider options. |
defaultConfidence? | number | Default confidence threshold in the range [0, 1]. |
defaultMaxMatches? | number | Default max number of returned matches. |
matching? | VisionMatchingSettings | Explicit matcher tuning settings. When present, these values override equivalent top-level options. |
model | string | Model ID to send to the OpenAI-compatible server. |
ollama? | { baseURL: string } | Ollama provider options. |
openai? | { apiKey: string; baseURL: string } | OpenAI provider options. |
openaiCompatible | { apiKey: string; baseURL: string; headers: Record<string, string>; name: string; queryParams: Record<string, string>; supportsStructuredOutputs: boolean } | Connection details for the OpenAI-compatible server. |
Was this page helpful?