Params to initiate a multiturn chat with the model via startChat.
Package
@google-cloud/vertexaiProperties
apiEndpoint
apiEndpoint?: string;
Optional. The base Vertex AI endpoint to use for the request.
cachedContent
cachedContent?: string;
Optional. The name of the cached content used as context to serve the prediction. This is the name of a CachedContent
and not the cache object itself.
generationConfig
generationConfig?: GenerationConfig;
Optional. GenerationConfig.
history
history?: Content[];
Optional. History of the chat session. Content
safetySettings
safetySettings?: SafetySetting[];
Optional. Array of SafetySetting.
systemInstruction
systemInstruction?: string | Content;
Optional. The user provided system instructions for the model. Note: only text should be used in parts of Content
toolConfig
toolConfig?: ToolConfig;
Optional. This config is shared for all tools provided in the request.
tools
tools?: Tool[];
Optional. Array of Tool.