@kadoa/node-sdk 0.19.0 → 0.19.2

package/dist/index.d.mts

@@ -639,6 +639,22 @@ interface AgenticWorkflow {
      * Additional data for the workflow (e.g. IDs from your system to link data)
      */
     'additionalData'?: any | null;
+    /**
+     * Maximum pages to crawl (default: 10,000, max: 100,000). Only used when navigationMode is \'all-pages\'
+     */
+    'maxPages'?: number;
+    /**
+     * Maximum crawl depth (default: 50, max: 200). Only used when navigationMode is \'all-pages\'
+     */
+    'maxDepth'?: number;
+    /**
+     * Regex patterns to include specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterIn'?: Array<string>;
+    /**
+     * Regex patterns to exclude specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterOut'?: Array<string>;
     /**
      * Natural language instructions for the AI agent (10-5000 characters). Describe what data to extract and how to navigate the site
      */
@@ -1159,6 +1175,22 @@ interface WorkflowWithEntityAndFields {
      * Additional data for the workflow (e.g. IDs from your system to link data)
      */
     'additionalData'?: any | null;
+    /**
+     * Maximum pages to crawl (default: 10,000, max: 100,000). Only used when navigationMode is \'all-pages\'
+     */
+    'maxPages'?: number;
+    /**
+     * Maximum crawl depth (default: 50, max: 200). Only used when navigationMode is \'all-pages\'
+     */
+    'maxDepth'?: number;
+    /**
+     * Regex patterns to include specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterIn'?: Array<string>;
+    /**
+     * Regex patterns to exclude specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterOut'?: Array<string>;
     /**
      * Entity name for extraction (e.g., \'Product\', \'JobListing\')
      */
@@ -1173,6 +1205,7 @@ declare const WorkflowWithEntityAndFieldsNavigationModeEnum: {
     readonly PaginatedPage: "paginated-page";
     readonly PageAndDetail: "page-and-detail";
     readonly AgenticNavigation: "agentic-navigation";
+    readonly AllPages: "all-pages";
 };
 type WorkflowWithEntityAndFieldsNavigationModeEnum = typeof WorkflowWithEntityAndFieldsNavigationModeEnum[keyof typeof WorkflowWithEntityAndFieldsNavigationModeEnum];
 declare const WorkflowWithEntityAndFieldsIntervalEnum: {
@@ -1267,6 +1300,22 @@ interface WorkflowWithExistingSchema {
      * Additional data for the workflow (e.g. IDs from your system to link data)
      */
     'additionalData'?: any | null;
+    /**
+     * Maximum pages to crawl (default: 10,000, max: 100,000). Only used when navigationMode is \'all-pages\'
+     */
+    'maxPages'?: number;
+    /**
+     * Maximum crawl depth (default: 50, max: 200). Only used when navigationMode is \'all-pages\'
+     */
+    'maxDepth'?: number;
+    /**
+     * Regex patterns to include specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterIn'?: Array<string>;
+    /**
+     * Regex patterns to exclude specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterOut'?: Array<string>;
     /**
      * ID of an existing schema configuration. Use this to reference a previously defined schema without re-defining extraction fields
      */
@@ -1277,6 +1326,7 @@ declare const WorkflowWithExistingSchemaNavigationModeEnum: {
     readonly PaginatedPage: "paginated-page";
     readonly PageAndDetail: "page-and-detail";
     readonly AgenticNavigation: "agentic-navigation";
+    readonly AllPages: "all-pages";
 };
 type WorkflowWithExistingSchemaNavigationModeEnum = typeof WorkflowWithExistingSchemaNavigationModeEnum[keyof typeof WorkflowWithExistingSchemaNavigationModeEnum];
 declare const WorkflowWithExistingSchemaIntervalEnum: {
@@ -3632,6 +3682,22 @@ interface V4WorkflowsWorkflowIdMetadataPutRequest {
      * Additional static data for the workflow
      */
     'additionalData'?: object;
+    /**
+     * Maximum pages to crawl (only for crawler workflows)
+     */
+    'maxPages'?: number;
+    /**
+     * Maximum crawl depth (only for crawler workflows)
+     */
+    'maxDepth'?: number;
+    /**
+     * Regex patterns to include specific paths (only for crawler workflows)
+     */
+    'pathsFilterIn'?: Array<string>;
+    /**
+     * Regex patterns to exclude specific paths (only for crawler workflows)
+     */
+    'pathsFilterOut'?: Array<string>;
 }
 declare const V4WorkflowsWorkflowIdMetadataPutRequestUpdateIntervalEnum: {
     readonly OnlyOnce: "ONLY_ONCE";
@@ -6316,7 +6382,7 @@ declare class ExtractionBuilderService {
     get workflowId(): string;
     get jobId(): string;
     constructor(workflowsCoreService: WorkflowsCoreService, entityResolverService: EntityResolverService, dataFetcherService: DataFetcherService, notificationSetupService: NotificationSetupService);
-    extract({ urls, name, description, navigationMode, extraction, additionalData, bypassPreview, }: ExtractOptions): PreparedExtraction;
+    extract({ urls, name, description, navigationMode, extraction, additionalData, bypassPreview, userPrompt, interval, schedules, location, }: ExtractOptions): PreparedExtraction;
     withNotifications(options: Omit<NotificationOptions, "workflowId">): PreparedExtraction;
     withMonitoring(options: WorkflowMonitoringConfig): PreparedExtraction;
     bypassPreview(): PreparedExtraction;

package/dist/index.d.ts

@@ -639,6 +639,22 @@ interface AgenticWorkflow {
      * Additional data for the workflow (e.g. IDs from your system to link data)
      */
     'additionalData'?: any | null;
+    /**
+     * Maximum pages to crawl (default: 10,000, max: 100,000). Only used when navigationMode is \'all-pages\'
+     */
+    'maxPages'?: number;
+    /**
+     * Maximum crawl depth (default: 50, max: 200). Only used when navigationMode is \'all-pages\'
+     */
+    'maxDepth'?: number;
+    /**
+     * Regex patterns to include specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterIn'?: Array<string>;
+    /**
+     * Regex patterns to exclude specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterOut'?: Array<string>;
     /**
      * Natural language instructions for the AI agent (10-5000 characters). Describe what data to extract and how to navigate the site
      */
@@ -1159,6 +1175,22 @@ interface WorkflowWithEntityAndFields {
      * Additional data for the workflow (e.g. IDs from your system to link data)
      */
     'additionalData'?: any | null;
+    /**
+     * Maximum pages to crawl (default: 10,000, max: 100,000). Only used when navigationMode is \'all-pages\'
+     */
+    'maxPages'?: number;
+    /**
+     * Maximum crawl depth (default: 50, max: 200). Only used when navigationMode is \'all-pages\'
+     */
+    'maxDepth'?: number;
+    /**
+     * Regex patterns to include specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterIn'?: Array<string>;
+    /**
+     * Regex patterns to exclude specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterOut'?: Array<string>;
     /**
      * Entity name for extraction (e.g., \'Product\', \'JobListing\')
      */
@@ -1173,6 +1205,7 @@ declare const WorkflowWithEntityAndFieldsNavigationModeEnum: {
     readonly PaginatedPage: "paginated-page";
     readonly PageAndDetail: "page-and-detail";
     readonly AgenticNavigation: "agentic-navigation";
+    readonly AllPages: "all-pages";
 };
 type WorkflowWithEntityAndFieldsNavigationModeEnum = typeof WorkflowWithEntityAndFieldsNavigationModeEnum[keyof typeof WorkflowWithEntityAndFieldsNavigationModeEnum];
 declare const WorkflowWithEntityAndFieldsIntervalEnum: {
@@ -1267,6 +1300,22 @@ interface WorkflowWithExistingSchema {
      * Additional data for the workflow (e.g. IDs from your system to link data)
      */
     'additionalData'?: any | null;
+    /**
+     * Maximum pages to crawl (default: 10,000, max: 100,000). Only used when navigationMode is \'all-pages\'
+     */
+    'maxPages'?: number;
+    /**
+     * Maximum crawl depth (default: 50, max: 200). Only used when navigationMode is \'all-pages\'
+     */
+    'maxDepth'?: number;
+    /**
+     * Regex patterns to include specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterIn'?: Array<string>;
+    /**
+     * Regex patterns to exclude specific paths during crawling. Only used when navigationMode is \'all-pages\'
+     */
+    'pathsFilterOut'?: Array<string>;
     /**
      * ID of an existing schema configuration. Use this to reference a previously defined schema without re-defining extraction fields
      */
@@ -1277,6 +1326,7 @@ declare const WorkflowWithExistingSchemaNavigationModeEnum: {
     readonly PaginatedPage: "paginated-page";
     readonly PageAndDetail: "page-and-detail";
     readonly AgenticNavigation: "agentic-navigation";
+    readonly AllPages: "all-pages";
 };
 type WorkflowWithExistingSchemaNavigationModeEnum = typeof WorkflowWithExistingSchemaNavigationModeEnum[keyof typeof WorkflowWithExistingSchemaNavigationModeEnum];
 declare const WorkflowWithExistingSchemaIntervalEnum: {
@@ -3632,6 +3682,22 @@ interface V4WorkflowsWorkflowIdMetadataPutRequest {
      * Additional static data for the workflow
      */
     'additionalData'?: object;
+    /**
+     * Maximum pages to crawl (only for crawler workflows)
+     */
+    'maxPages'?: number;
+    /**
+     * Maximum crawl depth (only for crawler workflows)
+     */
+    'maxDepth'?: number;
+    /**
+     * Regex patterns to include specific paths (only for crawler workflows)
+     */
+    'pathsFilterIn'?: Array<string>;
+    /**
+     * Regex patterns to exclude specific paths (only for crawler workflows)
+     */
+    'pathsFilterOut'?: Array<string>;
 }
 declare const V4WorkflowsWorkflowIdMetadataPutRequestUpdateIntervalEnum: {
     readonly OnlyOnce: "ONLY_ONCE";
@@ -6316,7 +6382,7 @@ declare class ExtractionBuilderService {
     get workflowId(): string;
     get jobId(): string;
     constructor(workflowsCoreService: WorkflowsCoreService, entityResolverService: EntityResolverService, dataFetcherService: DataFetcherService, notificationSetupService: NotificationSetupService);
-    extract({ urls, name, description, navigationMode, extraction, additionalData, bypassPreview, }: ExtractOptions): PreparedExtraction;
+    extract({ urls, name, description, navigationMode, extraction, additionalData, bypassPreview, userPrompt, interval, schedules, location, }: ExtractOptions): PreparedExtraction;
     withNotifications(options: Omit<NotificationOptions, "workflowId">): PreparedExtraction;
     withMonitoring(options: WorkflowMonitoringConfig): PreparedExtraction;
     bypassPreview(): PreparedExtraction;

package/dist/index.js

@@ -4598,7 +4598,11 @@ var ExtractionBuilderService = class {
     navigationMode,
     extraction,
     additionalData,
-    bypassPreview
+    bypassPreview,
+    userPrompt,
+    interval,
+    schedules,
+    location
   }) {
     let entity = "ai-detection";
     if (extraction) {
@@ -4610,6 +4614,9 @@ var ExtractionBuilderService = class {
         entity = builtSchema.entityName ? { name: builtSchema.entityName, fields: builtSchema.fields } : { fields: builtSchema.fields };
       }
     }
+    if (userPrompt) {
+      this._userPrompt = userPrompt;
+    }
     this._options = {
       urls,
       name,
@@ -4617,7 +4624,11 @@ var ExtractionBuilderService = class {
       navigationMode: navigationMode || "single-page",
       entity,
       bypassPreview: bypassPreview ?? false,
-      additionalData
+      additionalData,
+      userPrompt,
+      interval,
+      schedules,
+      location
     };
     return this;
   }
@@ -4679,15 +4690,12 @@ var ExtractionBuilderService = class {
         fields: typeof entity === "object" && "fields" in entity ? entity.fields : []
       };
     } else {
-      resolvedEntity = await this.entityResolverService.resolveEntity(
-        entity,
-        {
-          link: urls[0],
-          location: this._options.location,
-          navigationMode,
-          selectorMode: useSelectorMode
-        }
-      );
+      resolvedEntity = await this.entityResolverService.resolveEntity(entity, {
+        link: urls[0],
+        location: this._options.location,
+        navigationMode,
+        selectorMode: useSelectorMode
+      });
     }
     const workflow = await this.workflowsCoreService.create({
       urls,
@@ -5227,7 +5235,7 @@ var WSS_API_URI = process.env.KADOA_WSS_API_URI ?? "wss://realtime.kadoa.com";
 var REALTIME_API_URI = process.env.KADOA_REALTIME_API_URI ?? "https://realtime.kadoa.com";
 
 // src/version.ts
-var SDK_VERSION = "0.19.0";
+var SDK_VERSION = "0.19.2";
 var SDK_NAME = "kadoa-node-sdk";
 var SDK_LANGUAGE = "node";