Protected ReadonlyDEFAULT_ProtectedhostProtected ReadonlyloggerProtectedmodelProtected ReadonlyparamsReadonlyproviderOptionalproxyOptionalreasoningProtected ReadonlytoolReadonlyvendorProtectedcheckCheck if the Ollama server supports thinking.
Use the Ollama 'show' request to get information about the model, so we can check the capabilities for the 'thinking' capability.
The Ollama client instance.
The name of the Ollama model.
A boolean indicating whether the Ollama model supports thinking.
ProtecteddispatchOptionalcancellation: CancellationTokenOptionalreasoning: ReasoningSettingsProtectedgetRetrieves the settings for the chat request, merging the request-specific settings with the default settings.
The language model request containing specific settings.
A partial ChatRequest object containing the merged settings.
ProtectedgetProtectedhandleOptionalcancellation: CancellationTokenOptionalreasoning: ReasoningSettingsProtectedhandleOptionalcancellation: CancellationTokenOptionalreasoning: ReasoningSettingsProtectedhandleProtectedinitProtectedinitializeProtectedmergeProtectednormalizeFlatten anyOf by merging the first non-null branch into the top-level prop so that fields carried by the branch (e.g. items, properties) are visible to the callers.
ProtectedprocessOptionalcancellation: CancellationTokenProtectedrecurseOptionalcancellationToken: CancellationTokenProtectedrequiresChecks if the model requires effort levels instead of a boolean for think.
ProtectedtoProtectedtoProtectedtoProtectedtransformProtectedtransform
See also VS Code
ILanguageModelChatMetadata