nodes/generated

Interface PerplexityNodeParameters

Source
interface PerplexityNodeParameters {
    input?: string;
    messages?: {
        message: {
            content?: string;
            role: "system" | "user" | "assistant";
        }[];
    };
    model?: | { mode: "id"
    | "list"; value: string }
    | "sonar"
    | "sonar-deep-research"
    | "sonar-pro"
    | "sonar-reasoning-pro"
    | "pplx-embed-v1-0.6b"
    | "pplx-embed-v1-4b"
    | "pplx-embed-context-v1-4b";
    operation?:
        | "search"
        | "complete"
        | "createResponse"
        | "createEmbedding"
        | "createContextualized";
    options?: | {
        instructions?: string;
        languagePreference?: string;
        maxOutputTokens?: number;
        maxSteps?: number;
        modelsFallback?: string;
        reasoning?: string;
        responseFormat?: string;
        tools?: string;
    }
    | {
        disableSearch?: boolean;
        enableSearchClassifier?: boolean;
        frequencyPenalty?: number;
        imageDomainFilter?: string;
        imageFormatFilter?: string;
        languagePreference?: string;
        lastUpdatedAfter?: string;
        lastUpdatedBefore?: string;
        maxTokens?: number;
        presencePenalty?: number;
        reasoningEffort?: | "low"
        | "high"
        | "medium"
        | "minimal";
        responseFormat?: string;
        returnImages?: boolean;
        returnRelatedQuestions?: boolean;
        searchAfterDate?: string;
        searchBeforeDate?: string;
        searchDomainFilter?: string;
        searchLanguageFilter?: string;
        searchMode?: "web"
        | "academic"
        | "sec";
        searchRecency?:
            | "hour"
            | "day"
            | "week"
            | "month"
            | "year";
        stop?: string;
        temperature?: number;
        topK?: number;
        topP?: number;
        webSearchOptions?: string;
    }
    | {
        dimensions?: number;
        encoding_format?: "base64_int8"
        | "base64_binary";
    }
    | {
        country?: string;
        lastUpdatedAfter?: string;
        lastUpdatedBefore?: string;
        maxResults?: number;
        maxTokens?: number;
        maxTokensPerPage?: number;
        searchAfterDate?: string;
        searchBeforeDate?: string;
        searchDomainFilter?: string;
        searchLanguageFilter?: string;
        searchRecencyFilter?: | "hour"
        | "day"
        | "week"
        | "month"
        | "year";
    };
    preset?: string;
    query?: string;
    resource?: "search"
    | "agent"
    | "chat"
    | "embedding";
    simplify?: boolean;
}

Properties§

§readonly input?: string

The input text prompt to send to the agent Type options: {"rows":3}

§readonly messages?: { ... }

Any optional system messages must be sent first, followed by alternating user and assistant messages Default: {"message":[{"role":"user","content":""}]} Type options: {"multipleValues":true,"sortable":true}

§readonly model?:
    | { mode: "id"
    | "list"; value: string }
    | "sonar"
    | "sonar-deep-research"
    | "sonar-pro"
    | "sonar-reasoning-pro"
    | "pplx-embed-v1-0.6b"
    | "pplx-embed-v1-4b"
    | "pplx-embed-context-v1-4b"

The model to use. Uses provider/model format (e.g. openai/gpt-5.2). Leave empty when using a preset. Default: {"mode":"list","value":""}

§readonly operation?:
    | "search"
    | "complete"
    | "createResponse"
    | "createEmbedding"
    | "createContextualized"

Default: "createResponse"

§readonly options?:
    | {
        instructions?: string;
        languagePreference?: string;
        maxOutputTokens?: number;
        maxSteps?: number;
        modelsFallback?: string;
        reasoning?: string;
        responseFormat?: string;
        tools?: string;
    }
    | {
        disableSearch?: boolean;
        enableSearchClassifier?: boolean;
        frequencyPenalty?: number;
        imageDomainFilter?: string;
        imageFormatFilter?: string;
        languagePreference?: string;
        lastUpdatedAfter?: string;
        lastUpdatedBefore?: string;
        maxTokens?: number;
        presencePenalty?: number;
        reasoningEffort?: | "low"
        | "high"
        | "medium"
        | "minimal";
        responseFormat?: string;
        returnImages?: boolean;
        returnRelatedQuestions?: boolean;
        searchAfterDate?: string;
        searchBeforeDate?: string;
        searchDomainFilter?: string;
        searchLanguageFilter?: string;
        searchMode?: "web"
        | "academic"
        | "sec";
        searchRecency?:
            | "hour"
            | "day"
            | "week"
            | "month"
            | "year";
        stop?: string;
        temperature?: number;
        topK?: number;
        topP?: number;
        webSearchOptions?: string;
    }
    | {
        dimensions?: number;
        encoding_format?: "base64_int8"
        | "base64_binary";
    }
    | {
        country?: string;
        lastUpdatedAfter?: string;
        lastUpdatedBefore?: string;
        maxResults?: number;
        maxTokens?: number;
        maxTokensPerPage?: number;
        searchAfterDate?: string;
        searchBeforeDate?: string;
        searchDomainFilter?: string;
        searchLanguageFilter?: string;
        searchRecencyFilter?: | "hour"
        | "day"
        | "week"
        | "month"
        | "year";
    }

Default: {}

§readonly preset?: string

Preset name to use. Use preset OR model, not both.

§readonly query?: string

The search query string

§readonly resource?: "search" | "agent" | "chat" | "embedding"

Default: "chat"

§readonly simplify?: boolean

Whether to return only essential fields (ID, model, output text, citations)