@thanh01.pmt/research-kit 1.2.1 → 1.2.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (61) hide show
  1. package/dist/academic/index.cjs +11 -2
  2. package/dist/academic/index.cjs.map +1 -1
  3. package/dist/academic/index.d.cts +3 -3
  4. package/dist/academic/index.d.ts +3 -3
  5. package/dist/academic/index.js +1 -1
  6. package/dist/{catalogBuilder-DHV6y1gD.d.ts → catalogBuilder-B4eiLS_S.d.cts} +20 -6
  7. package/dist/{catalogBuilder-BaVRvg-9.d.cts → catalogBuilder-BNB_gaWP.d.ts} +20 -6
  8. package/dist/{chunk-X3X26W2I.js → chunk-HESXWQEF.js} +12 -7
  9. package/dist/chunk-HESXWQEF.js.map +1 -0
  10. package/dist/{chunk-QFYM2NV4.js → chunk-KXJDQBSJ.js} +3 -3
  11. package/dist/{chunk-QFYM2NV4.js.map → chunk-KXJDQBSJ.js.map} +1 -1
  12. package/dist/{chunk-RW7VS7NI.js → chunk-P6RHBJY2.js} +88 -25
  13. package/dist/chunk-P6RHBJY2.js.map +1 -0
  14. package/dist/{chunk-ON6VFCJO.js → chunk-QQZQNBJC.js} +51 -2
  15. package/dist/chunk-QQZQNBJC.js.map +1 -0
  16. package/dist/{chunk-HZNSZDSM.js → chunk-SAHBBO3U.js} +99 -11
  17. package/dist/chunk-SAHBBO3U.js.map +1 -0
  18. package/dist/{chunk-UKGR45VZ.js → chunk-SDDZFFL6.js} +13 -4
  19. package/dist/chunk-SDDZFFL6.js.map +1 -0
  20. package/dist/chunk-YICMTZS5.js +527 -0
  21. package/dist/chunk-YICMTZS5.js.map +1 -0
  22. package/dist/config/index.cjs +10 -5
  23. package/dist/config/index.cjs.map +1 -1
  24. package/dist/config/index.d.cts +1 -1
  25. package/dist/config/index.d.ts +1 -1
  26. package/dist/config/index.js +1 -1
  27. package/dist/evidence/index.cjs.map +1 -1
  28. package/dist/evidence/index.d.cts +2 -2
  29. package/dist/evidence/index.d.ts +2 -2
  30. package/dist/evidence/index.js +2 -2
  31. package/dist/harvester/index.cjs +674 -9
  32. package/dist/harvester/index.cjs.map +1 -1
  33. package/dist/harvester/index.d.cts +87 -5
  34. package/dist/harvester/index.d.ts +87 -5
  35. package/dist/harvester/index.js +3 -3
  36. package/dist/{index-DlngvZBr.d.cts → index-9rDiFuR4.d.cts} +43 -12
  37. package/dist/{index-DlngvZBr.d.ts → index-9rDiFuR4.d.ts} +43 -12
  38. package/dist/index.cjs +783 -35
  39. package/dist/index.cjs.map +1 -1
  40. package/dist/index.d.cts +13 -11
  41. package/dist/index.d.ts +13 -11
  42. package/dist/index.js +19 -12
  43. package/dist/index.js.map +1 -1
  44. package/dist/{literatureReview-C7hsjrn4.d.cts → literatureReview-BwidpYJo.d.cts} +2 -1
  45. package/dist/{literatureReview-DWl13r_3.d.ts → literatureReview-DOzgm9Q2.d.ts} +2 -1
  46. package/dist/pipeline/index.cjs +256 -32
  47. package/dist/pipeline/index.cjs.map +1 -1
  48. package/dist/pipeline/index.d.cts +10 -4
  49. package/dist/pipeline/index.d.ts +10 -4
  50. package/dist/pipeline/index.js +5 -5
  51. package/dist/{webScraper-yO9P-oLb.d.cts → webScraper-CAQjE46m.d.cts} +11 -2
  52. package/dist/{webScraper-DBFUIqoO.d.ts → webScraper-CXIpvyA6.d.ts} +11 -2
  53. package/package.json +9 -8
  54. package/LICENSE +0 -21
  55. package/dist/chunk-HZNSZDSM.js.map +0 -1
  56. package/dist/chunk-LSMSIPTZ.js +0 -3
  57. package/dist/chunk-LSMSIPTZ.js.map +0 -1
  58. package/dist/chunk-ON6VFCJO.js.map +0 -1
  59. package/dist/chunk-RW7VS7NI.js.map +0 -1
  60. package/dist/chunk-UKGR45VZ.js.map +0 -1
  61. package/dist/chunk-X3X26W2I.js.map +0 -1
@@ -1,7 +1,7 @@
1
- import { T as TechnicalDomain, S as ScrapedDocument } from '../webScraper-yO9P-oLb.cjs';
2
- export { D as DomainClassificationResult, E as ExtractedCodeBlock, a as WebScraper, W as WebScraperOptions, c as classifyTechnicalDomain, e as extractSubstantiveExcerpts, i as inferPrimaryCodeLanguage } from '../webScraper-yO9P-oLb.cjs';
3
- export { C as CatalogBuilder, H as HarvestedResourceItem, M as MultiSearchOptions, a as MultiSourceSearchEngine, R as ResourceCatalogBundle, S as SearchHit } from '../catalogBuilder-BaVRvg-9.cjs';
4
- import { E as ExtractedConceptNode, C as CourseResearchContext, L as LlmTextFn } from '../index-DlngvZBr.cjs';
1
+ import { T as TechnicalDomain, S as ScrapedDocument } from '../webScraper-CAQjE46m.cjs';
2
+ export { D as DomainClassificationResult, E as ExtractedCodeBlock, a as WebScraper, W as WebScraperOptions, c as classifyTechnicalDomain, e as extractSubstantiveExcerpts, i as inferPrimaryCodeLanguage } from '../webScraper-CAQjE46m.cjs';
3
+ export { C as CatalogBuilder, H as HarvestedResourceItem, M as MultiSearchOptions, b as MultiSourceSearchEngine, R as ResourceCatalogBundle, S as SearchHit, a as SearchTimeRange } from '../catalogBuilder-B4eiLS_S.cjs';
4
+ import { E as ExtractedConceptNode, C as CourseResearchContext, L as LlmTextFn } from '../index-9rDiFuR4.cjs';
5
5
  import 'zod';
6
6
 
7
7
  interface TranscriptSegment {
@@ -136,4 +136,86 @@ interface ContentQualityScore {
136
136
  */
137
137
  declare function evaluateTechnicalDensity(markdown: string): ContentQualityScore;
138
138
 
139
- export { type ContentQualityScore, ECOMMERCE_AND_COMMERCIAL_PATTERNS, ECOMMERCE_DOMAINS, type GraphEdge, type HealthAuditResult, HealthAuditor, PedagogicalTermExtractor, type ReducedGraphResult, ScrapedDocument, TechnicalDomain, type TermExtractionBundle, type TopoSortResult, type TranscriptSegment, YouTubeIngestionService, type YouTubeTranscriptResult, evaluateTechnicalDensity, extractYouTubeVideoId, formatTimestamp, isCommercialOrNoise, isYouTubeUrl, kahnTopologicalSort, stitchCaptionSegments, transitiveReduction };
139
+ /**
140
+ * STEM & Coding Resource Researcher (v1.2.2).
141
+ * Tự động tìm kiếm, đối chiếu và đề xuất tài nguyên giáo dục mở (OER):
142
+ * - Mô phỏng tương tác (PhET Simulations, Open Source Physics)
143
+ * - Khóa học & Lộ trình mở (freeCodeCamp, The Odin Project, Code.org, GitHub Curricula)
144
+ * - Hình ảnh khoa học & media mở bản quyền CC/Public Domain (Openverse, NASA Media Library)
145
+ * - Sách & giáo trình mở (OpenStax, MIT OCW)
146
+ * - Lập trình & Thử thách thực hành (CS Unplugged, Scratch, Exercism)
147
+ */
148
+ type StemResourceType = 'simulation' | 'curriculum' | 'media_image' | 'media_video' | 'hands_on_lab' | 'textbook' | 'problem_set';
149
+ type StemResourceQueryType = StemResourceType | 'interactive' | 'open_media';
150
+ type StemResourceProvider = 'openverse' | 'nasa' | 'github' | 'phet' | 'openstax' | 'cs_unplugged' | 'scratch' | 'exercism' | 'web';
151
+ interface StemResourceLicense {
152
+ type: string;
153
+ attributionText: string;
154
+ url?: string;
155
+ commercialUseAllowed: boolean;
156
+ }
157
+ interface StemResourceItem {
158
+ id: string;
159
+ title: string;
160
+ url: string;
161
+ description: string;
162
+ type: StemResourceType;
163
+ provider: StemResourceProvider;
164
+ thumbnailUrl?: string;
165
+ embedUrl?: string;
166
+ mediaType: 'interactive' | 'image' | 'video' | 'text' | 'code';
167
+ license: StemResourceLicense;
168
+ subject: 'computer_science' | 'physics' | 'robotics' | 'math' | 'electronics' | 'general_stem';
169
+ targetLevel: 'primary' | 'lower_secondary' | 'upper_secondary' | 'higher_ed' | 'developer' | 'all';
170
+ tags: string[];
171
+ relevanceScore: number;
172
+ }
173
+ interface StemResearchOptions {
174
+ types?: StemResourceQueryType[];
175
+ limit?: number;
176
+ licenseFilter?: 'creative_commons' | 'public_domain' | 'all';
177
+ level?: 'primary' | 'lower_secondary' | 'upper_secondary' | 'higher_ed' | 'developer' | 'all';
178
+ githubToken?: string;
179
+ timeoutMs?: number;
180
+ }
181
+ interface StemResourceCatalog {
182
+ query: string;
183
+ totalFound: number;
184
+ categoryCounts: Record<StemResourceType, number>;
185
+ resources: StemResourceItem[];
186
+ items: StemResourceItem[];
187
+ markdownSummary: string;
188
+ markdownReport: string;
189
+ }
190
+ declare class OpenverseClient {
191
+ private baseUrl;
192
+ searchImages(query: string, options?: {
193
+ limit?: number;
194
+ license?: string;
195
+ }): Promise<StemResourceItem[]>;
196
+ }
197
+ declare class NasaMediaClient {
198
+ private baseUrl;
199
+ search(query: string, options?: {
200
+ limit?: number;
201
+ mediaType?: 'image' | 'video' | 'audio';
202
+ }): Promise<StemResourceItem[]>;
203
+ }
204
+ declare class GitHubCurriculumClient {
205
+ private baseUrl;
206
+ searchCurricula(query: string, options?: {
207
+ limit?: number;
208
+ token?: string;
209
+ }): Promise<StemResourceItem[]>;
210
+ }
211
+ declare class StemResourceResearcher {
212
+ private openverse;
213
+ private nasa;
214
+ private github;
215
+ findResources(query: string, options?: StemResearchOptions): Promise<StemResourceCatalog>;
216
+ searchAndCatalog(query: string, options?: StemResearchOptions): Promise<StemResourceCatalog>;
217
+ generateMarkdown(catalog: StemResourceCatalog): string;
218
+ private generateMarkdownSummary;
219
+ }
220
+
221
+ export { type ContentQualityScore, ECOMMERCE_AND_COMMERCIAL_PATTERNS, ECOMMERCE_DOMAINS, GitHubCurriculumClient, type GraphEdge, type HealthAuditResult, HealthAuditor, NasaMediaClient, OpenverseClient, PedagogicalTermExtractor, type ReducedGraphResult, ScrapedDocument, type StemResearchOptions, type StemResourceCatalog, type StemResourceItem, type StemResourceLicense, type StemResourceProvider, type StemResourceQueryType, StemResourceResearcher, type StemResourceType, TechnicalDomain, type TermExtractionBundle, type TopoSortResult, type TranscriptSegment, YouTubeIngestionService, type YouTubeTranscriptResult, evaluateTechnicalDensity, extractYouTubeVideoId, formatTimestamp, isCommercialOrNoise, isYouTubeUrl, kahnTopologicalSort, stitchCaptionSegments, transitiveReduction };
@@ -1,7 +1,7 @@
1
- import { T as TechnicalDomain, S as ScrapedDocument } from '../webScraper-DBFUIqoO.js';
2
- export { D as DomainClassificationResult, E as ExtractedCodeBlock, a as WebScraper, W as WebScraperOptions, c as classifyTechnicalDomain, e as extractSubstantiveExcerpts, i as inferPrimaryCodeLanguage } from '../webScraper-DBFUIqoO.js';
3
- export { C as CatalogBuilder, H as HarvestedResourceItem, M as MultiSearchOptions, a as MultiSourceSearchEngine, R as ResourceCatalogBundle, S as SearchHit } from '../catalogBuilder-DHV6y1gD.js';
4
- import { E as ExtractedConceptNode, C as CourseResearchContext, L as LlmTextFn } from '../index-DlngvZBr.js';
1
+ import { T as TechnicalDomain, S as ScrapedDocument } from '../webScraper-CXIpvyA6.js';
2
+ export { D as DomainClassificationResult, E as ExtractedCodeBlock, a as WebScraper, W as WebScraperOptions, c as classifyTechnicalDomain, e as extractSubstantiveExcerpts, i as inferPrimaryCodeLanguage } from '../webScraper-CXIpvyA6.js';
3
+ export { C as CatalogBuilder, H as HarvestedResourceItem, M as MultiSearchOptions, b as MultiSourceSearchEngine, R as ResourceCatalogBundle, S as SearchHit, a as SearchTimeRange } from '../catalogBuilder-BNB_gaWP.js';
4
+ import { E as ExtractedConceptNode, C as CourseResearchContext, L as LlmTextFn } from '../index-9rDiFuR4.js';
5
5
  import 'zod';
6
6
 
7
7
  interface TranscriptSegment {
@@ -136,4 +136,86 @@ interface ContentQualityScore {
136
136
  */
137
137
  declare function evaluateTechnicalDensity(markdown: string): ContentQualityScore;
138
138
 
139
- export { type ContentQualityScore, ECOMMERCE_AND_COMMERCIAL_PATTERNS, ECOMMERCE_DOMAINS, type GraphEdge, type HealthAuditResult, HealthAuditor, PedagogicalTermExtractor, type ReducedGraphResult, ScrapedDocument, TechnicalDomain, type TermExtractionBundle, type TopoSortResult, type TranscriptSegment, YouTubeIngestionService, type YouTubeTranscriptResult, evaluateTechnicalDensity, extractYouTubeVideoId, formatTimestamp, isCommercialOrNoise, isYouTubeUrl, kahnTopologicalSort, stitchCaptionSegments, transitiveReduction };
139
+ /**
140
+ * STEM & Coding Resource Researcher (v1.2.2).
141
+ * Tự động tìm kiếm, đối chiếu và đề xuất tài nguyên giáo dục mở (OER):
142
+ * - Mô phỏng tương tác (PhET Simulations, Open Source Physics)
143
+ * - Khóa học & Lộ trình mở (freeCodeCamp, The Odin Project, Code.org, GitHub Curricula)
144
+ * - Hình ảnh khoa học & media mở bản quyền CC/Public Domain (Openverse, NASA Media Library)
145
+ * - Sách & giáo trình mở (OpenStax, MIT OCW)
146
+ * - Lập trình & Thử thách thực hành (CS Unplugged, Scratch, Exercism)
147
+ */
148
+ type StemResourceType = 'simulation' | 'curriculum' | 'media_image' | 'media_video' | 'hands_on_lab' | 'textbook' | 'problem_set';
149
+ type StemResourceQueryType = StemResourceType | 'interactive' | 'open_media';
150
+ type StemResourceProvider = 'openverse' | 'nasa' | 'github' | 'phet' | 'openstax' | 'cs_unplugged' | 'scratch' | 'exercism' | 'web';
151
+ interface StemResourceLicense {
152
+ type: string;
153
+ attributionText: string;
154
+ url?: string;
155
+ commercialUseAllowed: boolean;
156
+ }
157
+ interface StemResourceItem {
158
+ id: string;
159
+ title: string;
160
+ url: string;
161
+ description: string;
162
+ type: StemResourceType;
163
+ provider: StemResourceProvider;
164
+ thumbnailUrl?: string;
165
+ embedUrl?: string;
166
+ mediaType: 'interactive' | 'image' | 'video' | 'text' | 'code';
167
+ license: StemResourceLicense;
168
+ subject: 'computer_science' | 'physics' | 'robotics' | 'math' | 'electronics' | 'general_stem';
169
+ targetLevel: 'primary' | 'lower_secondary' | 'upper_secondary' | 'higher_ed' | 'developer' | 'all';
170
+ tags: string[];
171
+ relevanceScore: number;
172
+ }
173
+ interface StemResearchOptions {
174
+ types?: StemResourceQueryType[];
175
+ limit?: number;
176
+ licenseFilter?: 'creative_commons' | 'public_domain' | 'all';
177
+ level?: 'primary' | 'lower_secondary' | 'upper_secondary' | 'higher_ed' | 'developer' | 'all';
178
+ githubToken?: string;
179
+ timeoutMs?: number;
180
+ }
181
+ interface StemResourceCatalog {
182
+ query: string;
183
+ totalFound: number;
184
+ categoryCounts: Record<StemResourceType, number>;
185
+ resources: StemResourceItem[];
186
+ items: StemResourceItem[];
187
+ markdownSummary: string;
188
+ markdownReport: string;
189
+ }
190
+ declare class OpenverseClient {
191
+ private baseUrl;
192
+ searchImages(query: string, options?: {
193
+ limit?: number;
194
+ license?: string;
195
+ }): Promise<StemResourceItem[]>;
196
+ }
197
+ declare class NasaMediaClient {
198
+ private baseUrl;
199
+ search(query: string, options?: {
200
+ limit?: number;
201
+ mediaType?: 'image' | 'video' | 'audio';
202
+ }): Promise<StemResourceItem[]>;
203
+ }
204
+ declare class GitHubCurriculumClient {
205
+ private baseUrl;
206
+ searchCurricula(query: string, options?: {
207
+ limit?: number;
208
+ token?: string;
209
+ }): Promise<StemResourceItem[]>;
210
+ }
211
+ declare class StemResourceResearcher {
212
+ private openverse;
213
+ private nasa;
214
+ private github;
215
+ findResources(query: string, options?: StemResearchOptions): Promise<StemResourceCatalog>;
216
+ searchAndCatalog(query: string, options?: StemResearchOptions): Promise<StemResourceCatalog>;
217
+ generateMarkdown(catalog: StemResourceCatalog): string;
218
+ private generateMarkdownSummary;
219
+ }
220
+
221
+ export { type ContentQualityScore, ECOMMERCE_AND_COMMERCIAL_PATTERNS, ECOMMERCE_DOMAINS, GitHubCurriculumClient, type GraphEdge, type HealthAuditResult, HealthAuditor, NasaMediaClient, OpenverseClient, PedagogicalTermExtractor, type ReducedGraphResult, ScrapedDocument, type StemResearchOptions, type StemResourceCatalog, type StemResourceItem, type StemResourceLicense, type StemResourceProvider, type StemResourceQueryType, StemResourceResearcher, type StemResourceType, TechnicalDomain, type TermExtractionBundle, type TopoSortResult, type TranscriptSegment, YouTubeIngestionService, type YouTubeTranscriptResult, evaluateTechnicalDensity, extractYouTubeVideoId, formatTimestamp, isCommercialOrNoise, isYouTubeUrl, kahnTopologicalSort, stitchCaptionSegments, transitiveReduction };
@@ -1,6 +1,6 @@
1
- import '../chunk-LSMSIPTZ.js';
2
- export { CatalogBuilder, ECOMMERCE_AND_COMMERCIAL_PATTERNS, ECOMMERCE_DOMAINS, HealthAuditor, MultiSourceSearchEngine, PedagogicalTermExtractor, classifyTechnicalDomain, evaluateTechnicalDensity, inferPrimaryCodeLanguage, isCommercialOrNoise, kahnTopologicalSort, transitiveReduction } from '../chunk-HZNSZDSM.js';
1
+ export { GitHubCurriculumClient, NasaMediaClient, OpenverseClient, StemResourceResearcher } from '../chunk-YICMTZS5.js';
2
+ export { CatalogBuilder, ECOMMERCE_AND_COMMERCIAL_PATTERNS, ECOMMERCE_DOMAINS, HealthAuditor, MultiSourceSearchEngine, PedagogicalTermExtractor, classifyTechnicalDomain, evaluateTechnicalDensity, inferPrimaryCodeLanguage, isCommercialOrNoise, kahnTopologicalSort, transitiveReduction } from '../chunk-SAHBBO3U.js';
3
3
  import '../chunk-AKEI7H2C.js';
4
- export { WebScraper, YouTubeIngestionService, extractSubstantiveExcerpts, extractYouTubeVideoId, formatTimestamp, isYouTubeUrl, stitchCaptionSegments } from '../chunk-ON6VFCJO.js';
4
+ export { WebScraper, YouTubeIngestionService, extractSubstantiveExcerpts, extractYouTubeVideoId, formatTimestamp, isYouTubeUrl, stitchCaptionSegments } from '../chunk-QQZQNBJC.js';
5
5
  //# sourceMappingURL=index.js.map
6
6
  //# sourceMappingURL=index.js.map
@@ -75,14 +75,16 @@ declare class AcademicSearchEngine {
75
75
  searchPapers(query: string, options?: AcademicSearchOptions): Promise<AcademicPaper[]>;
76
76
  }
77
77
 
78
- type SearchProviderType = 'tavily' | 'exa' | 'serper' | 'searxng' | 'duckduckgo' | 'semantic_scholar' | 'openalex' | 'arxiv' | 'custom';
79
- type CrawlerProviderType = 'jina' | 'crawl4ai' | 'youtube' | 'defuddle' | 'direct' | 'custom';
78
+ type SearchProviderType = 'tavily' | 'exa' | 'serper' | 'searxng' | 'brightdata' | 'duckduckgo' | 'semantic_scholar' | 'openalex' | 'arxiv' | 'custom';
79
+ type CrawlerProviderType = 'jina' | 'crawl4ai' | 'brightdata' | 'youtube' | 'defuddle' | 'direct' | 'custom';
80
80
  interface ResearchApiKeys {
81
81
  tavily?: string;
82
82
  exa?: string;
83
83
  jina?: string;
84
84
  serper?: string;
85
85
  semanticScholar?: string;
86
+ brightdata?: string;
87
+ brightData?: string;
86
88
  }
87
89
  interface CourseResearchContext {
88
90
  courseTitle?: string;
@@ -183,7 +185,7 @@ interface CustomSynthesizerAdapter {
183
185
  }
184
186
  declare const ResearchConfigSchema: z.ZodObject<{
185
187
  search: z.ZodDefault<z.ZodObject<{
186
- preferredProvider: z.ZodDefault<z.ZodEnum<["tavily", "exa", "serper", "searxng", "duckduckgo", "semantic_scholar", "openalex", "arxiv", "custom"]>>;
188
+ preferredProvider: z.ZodDefault<z.ZodEnum<["tavily", "exa", "serper", "searxng", "brightdata", "duckduckgo", "semantic_scholar", "openalex", "arxiv", "custom"]>>;
187
189
  fallbackChain: z.ZodDefault<z.ZodArray<z.ZodString, "many">>;
188
190
  apiKeys: z.ZodDefault<z.ZodObject<{
189
191
  tavily: z.ZodOptional<z.ZodString>;
@@ -191,64 +193,83 @@ declare const ResearchConfigSchema: z.ZodObject<{
191
193
  jina: z.ZodOptional<z.ZodString>;
192
194
  serper: z.ZodOptional<z.ZodString>;
193
195
  semanticScholar: z.ZodOptional<z.ZodString>;
196
+ brightdata: z.ZodOptional<z.ZodString>;
197
+ brightData: z.ZodOptional<z.ZodString>;
194
198
  }, "strip", z.ZodTypeAny, {
195
199
  tavily?: string | undefined;
196
200
  exa?: string | undefined;
197
201
  serper?: string | undefined;
202
+ brightdata?: string | undefined;
198
203
  jina?: string | undefined;
199
204
  semanticScholar?: string | undefined;
205
+ brightData?: string | undefined;
200
206
  }, {
201
207
  tavily?: string | undefined;
202
208
  exa?: string | undefined;
203
209
  serper?: string | undefined;
210
+ brightdata?: string | undefined;
204
211
  jina?: string | undefined;
205
212
  semanticScholar?: string | undefined;
213
+ brightData?: string | undefined;
206
214
  }>>;
207
215
  searxngHost: z.ZodOptional<z.ZodString>;
216
+ brightDataZone: z.ZodOptional<z.ZodString>;
217
+ brightDataEngine: z.ZodDefault<z.ZodEnum<["google", "bing", "yandex"]>>;
208
218
  timeoutMs: z.ZodDefault<z.ZodNumber>;
209
219
  maxResultsPerQuery: z.ZodDefault<z.ZodNumber>;
210
220
  }, "strip", z.ZodTypeAny, {
211
- preferredProvider: "tavily" | "exa" | "serper" | "searxng" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom";
221
+ preferredProvider: "tavily" | "exa" | "serper" | "searxng" | "brightdata" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom";
212
222
  fallbackChain: string[];
213
223
  apiKeys: {
214
224
  tavily?: string | undefined;
215
225
  exa?: string | undefined;
216
226
  serper?: string | undefined;
227
+ brightdata?: string | undefined;
217
228
  jina?: string | undefined;
218
229
  semanticScholar?: string | undefined;
230
+ brightData?: string | undefined;
219
231
  };
232
+ brightDataEngine: "google" | "bing" | "yandex";
220
233
  timeoutMs: number;
221
234
  maxResultsPerQuery: number;
222
235
  searxngHost?: string | undefined;
236
+ brightDataZone?: string | undefined;
223
237
  }, {
224
- preferredProvider?: "tavily" | "exa" | "serper" | "searxng" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom" | undefined;
238
+ preferredProvider?: "tavily" | "exa" | "serper" | "searxng" | "brightdata" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom" | undefined;
225
239
  fallbackChain?: string[] | undefined;
226
240
  apiKeys?: {
227
241
  tavily?: string | undefined;
228
242
  exa?: string | undefined;
229
243
  serper?: string | undefined;
244
+ brightdata?: string | undefined;
230
245
  jina?: string | undefined;
231
246
  semanticScholar?: string | undefined;
247
+ brightData?: string | undefined;
232
248
  } | undefined;
233
249
  searxngHost?: string | undefined;
250
+ brightDataZone?: string | undefined;
251
+ brightDataEngine?: "google" | "bing" | "yandex" | undefined;
234
252
  timeoutMs?: number | undefined;
235
253
  maxResultsPerQuery?: number | undefined;
236
254
  }>>;
237
255
  crawler: z.ZodDefault<z.ZodObject<{
238
- preferredProvider: z.ZodDefault<z.ZodEnum<["jina", "crawl4ai", "youtube", "defuddle", "direct", "custom"]>>;
256
+ preferredProvider: z.ZodDefault<z.ZodEnum<["jina", "crawl4ai", "brightdata", "youtube", "defuddle", "direct", "custom"]>>;
239
257
  fallbackChain: z.ZodDefault<z.ZodArray<z.ZodString, "many">>;
240
258
  crawl4aiHost: z.ZodDefault<z.ZodString>;
259
+ brightDataZone: z.ZodOptional<z.ZodString>;
241
260
  timeoutMs: z.ZodDefault<z.ZodNumber>;
242
261
  maxContentLength: z.ZodDefault<z.ZodNumber>;
243
262
  }, "strip", z.ZodTypeAny, {
244
- preferredProvider: "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct";
263
+ preferredProvider: "brightdata" | "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct";
245
264
  fallbackChain: string[];
246
265
  timeoutMs: number;
247
266
  crawl4aiHost: string;
248
267
  maxContentLength: number;
268
+ brightDataZone?: string | undefined;
249
269
  }, {
250
- preferredProvider?: "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct" | undefined;
270
+ preferredProvider?: "brightdata" | "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct" | undefined;
251
271
  fallbackChain?: string[] | undefined;
272
+ brightDataZone?: string | undefined;
252
273
  timeoutMs?: number | undefined;
253
274
  crawl4aiHost?: string | undefined;
254
275
  maxContentLength?: number | undefined;
@@ -268,25 +289,30 @@ declare const ResearchConfigSchema: z.ZodObject<{
268
289
  }>>;
269
290
  }, "strip", z.ZodTypeAny, {
270
291
  search: {
271
- preferredProvider: "tavily" | "exa" | "serper" | "searxng" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom";
292
+ preferredProvider: "tavily" | "exa" | "serper" | "searxng" | "brightdata" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom";
272
293
  fallbackChain: string[];
273
294
  apiKeys: {
274
295
  tavily?: string | undefined;
275
296
  exa?: string | undefined;
276
297
  serper?: string | undefined;
298
+ brightdata?: string | undefined;
277
299
  jina?: string | undefined;
278
300
  semanticScholar?: string | undefined;
301
+ brightData?: string | undefined;
279
302
  };
303
+ brightDataEngine: "google" | "bing" | "yandex";
280
304
  timeoutMs: number;
281
305
  maxResultsPerQuery: number;
282
306
  searxngHost?: string | undefined;
307
+ brightDataZone?: string | undefined;
283
308
  };
284
309
  crawler: {
285
- preferredProvider: "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct";
310
+ preferredProvider: "brightdata" | "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct";
286
311
  fallbackChain: string[];
287
312
  timeoutMs: number;
288
313
  crawl4aiHost: string;
289
314
  maxContentLength: number;
315
+ brightDataZone?: string | undefined;
290
316
  };
291
317
  quality: {
292
318
  minRelevanceScore: number;
@@ -295,22 +321,27 @@ declare const ResearchConfigSchema: z.ZodObject<{
295
321
  };
296
322
  }, {
297
323
  search?: {
298
- preferredProvider?: "tavily" | "exa" | "serper" | "searxng" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom" | undefined;
324
+ preferredProvider?: "tavily" | "exa" | "serper" | "searxng" | "brightdata" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom" | undefined;
299
325
  fallbackChain?: string[] | undefined;
300
326
  apiKeys?: {
301
327
  tavily?: string | undefined;
302
328
  exa?: string | undefined;
303
329
  serper?: string | undefined;
330
+ brightdata?: string | undefined;
304
331
  jina?: string | undefined;
305
332
  semanticScholar?: string | undefined;
333
+ brightData?: string | undefined;
306
334
  } | undefined;
307
335
  searxngHost?: string | undefined;
336
+ brightDataZone?: string | undefined;
337
+ brightDataEngine?: "google" | "bing" | "yandex" | undefined;
308
338
  timeoutMs?: number | undefined;
309
339
  maxResultsPerQuery?: number | undefined;
310
340
  } | undefined;
311
341
  crawler?: {
312
- preferredProvider?: "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct" | undefined;
342
+ preferredProvider?: "brightdata" | "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct" | undefined;
313
343
  fallbackChain?: string[] | undefined;
344
+ brightDataZone?: string | undefined;
314
345
  timeoutMs?: number | undefined;
315
346
  crawl4aiHost?: string | undefined;
316
347
  maxContentLength?: number | undefined;
@@ -75,14 +75,16 @@ declare class AcademicSearchEngine {
75
75
  searchPapers(query: string, options?: AcademicSearchOptions): Promise<AcademicPaper[]>;
76
76
  }
77
77
 
78
- type SearchProviderType = 'tavily' | 'exa' | 'serper' | 'searxng' | 'duckduckgo' | 'semantic_scholar' | 'openalex' | 'arxiv' | 'custom';
79
- type CrawlerProviderType = 'jina' | 'crawl4ai' | 'youtube' | 'defuddle' | 'direct' | 'custom';
78
+ type SearchProviderType = 'tavily' | 'exa' | 'serper' | 'searxng' | 'brightdata' | 'duckduckgo' | 'semantic_scholar' | 'openalex' | 'arxiv' | 'custom';
79
+ type CrawlerProviderType = 'jina' | 'crawl4ai' | 'brightdata' | 'youtube' | 'defuddle' | 'direct' | 'custom';
80
80
  interface ResearchApiKeys {
81
81
  tavily?: string;
82
82
  exa?: string;
83
83
  jina?: string;
84
84
  serper?: string;
85
85
  semanticScholar?: string;
86
+ brightdata?: string;
87
+ brightData?: string;
86
88
  }
87
89
  interface CourseResearchContext {
88
90
  courseTitle?: string;
@@ -183,7 +185,7 @@ interface CustomSynthesizerAdapter {
183
185
  }
184
186
  declare const ResearchConfigSchema: z.ZodObject<{
185
187
  search: z.ZodDefault<z.ZodObject<{
186
- preferredProvider: z.ZodDefault<z.ZodEnum<["tavily", "exa", "serper", "searxng", "duckduckgo", "semantic_scholar", "openalex", "arxiv", "custom"]>>;
188
+ preferredProvider: z.ZodDefault<z.ZodEnum<["tavily", "exa", "serper", "searxng", "brightdata", "duckduckgo", "semantic_scholar", "openalex", "arxiv", "custom"]>>;
187
189
  fallbackChain: z.ZodDefault<z.ZodArray<z.ZodString, "many">>;
188
190
  apiKeys: z.ZodDefault<z.ZodObject<{
189
191
  tavily: z.ZodOptional<z.ZodString>;
@@ -191,64 +193,83 @@ declare const ResearchConfigSchema: z.ZodObject<{
191
193
  jina: z.ZodOptional<z.ZodString>;
192
194
  serper: z.ZodOptional<z.ZodString>;
193
195
  semanticScholar: z.ZodOptional<z.ZodString>;
196
+ brightdata: z.ZodOptional<z.ZodString>;
197
+ brightData: z.ZodOptional<z.ZodString>;
194
198
  }, "strip", z.ZodTypeAny, {
195
199
  tavily?: string | undefined;
196
200
  exa?: string | undefined;
197
201
  serper?: string | undefined;
202
+ brightdata?: string | undefined;
198
203
  jina?: string | undefined;
199
204
  semanticScholar?: string | undefined;
205
+ brightData?: string | undefined;
200
206
  }, {
201
207
  tavily?: string | undefined;
202
208
  exa?: string | undefined;
203
209
  serper?: string | undefined;
210
+ brightdata?: string | undefined;
204
211
  jina?: string | undefined;
205
212
  semanticScholar?: string | undefined;
213
+ brightData?: string | undefined;
206
214
  }>>;
207
215
  searxngHost: z.ZodOptional<z.ZodString>;
216
+ brightDataZone: z.ZodOptional<z.ZodString>;
217
+ brightDataEngine: z.ZodDefault<z.ZodEnum<["google", "bing", "yandex"]>>;
208
218
  timeoutMs: z.ZodDefault<z.ZodNumber>;
209
219
  maxResultsPerQuery: z.ZodDefault<z.ZodNumber>;
210
220
  }, "strip", z.ZodTypeAny, {
211
- preferredProvider: "tavily" | "exa" | "serper" | "searxng" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom";
221
+ preferredProvider: "tavily" | "exa" | "serper" | "searxng" | "brightdata" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom";
212
222
  fallbackChain: string[];
213
223
  apiKeys: {
214
224
  tavily?: string | undefined;
215
225
  exa?: string | undefined;
216
226
  serper?: string | undefined;
227
+ brightdata?: string | undefined;
217
228
  jina?: string | undefined;
218
229
  semanticScholar?: string | undefined;
230
+ brightData?: string | undefined;
219
231
  };
232
+ brightDataEngine: "google" | "bing" | "yandex";
220
233
  timeoutMs: number;
221
234
  maxResultsPerQuery: number;
222
235
  searxngHost?: string | undefined;
236
+ brightDataZone?: string | undefined;
223
237
  }, {
224
- preferredProvider?: "tavily" | "exa" | "serper" | "searxng" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom" | undefined;
238
+ preferredProvider?: "tavily" | "exa" | "serper" | "searxng" | "brightdata" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom" | undefined;
225
239
  fallbackChain?: string[] | undefined;
226
240
  apiKeys?: {
227
241
  tavily?: string | undefined;
228
242
  exa?: string | undefined;
229
243
  serper?: string | undefined;
244
+ brightdata?: string | undefined;
230
245
  jina?: string | undefined;
231
246
  semanticScholar?: string | undefined;
247
+ brightData?: string | undefined;
232
248
  } | undefined;
233
249
  searxngHost?: string | undefined;
250
+ brightDataZone?: string | undefined;
251
+ brightDataEngine?: "google" | "bing" | "yandex" | undefined;
234
252
  timeoutMs?: number | undefined;
235
253
  maxResultsPerQuery?: number | undefined;
236
254
  }>>;
237
255
  crawler: z.ZodDefault<z.ZodObject<{
238
- preferredProvider: z.ZodDefault<z.ZodEnum<["jina", "crawl4ai", "youtube", "defuddle", "direct", "custom"]>>;
256
+ preferredProvider: z.ZodDefault<z.ZodEnum<["jina", "crawl4ai", "brightdata", "youtube", "defuddle", "direct", "custom"]>>;
239
257
  fallbackChain: z.ZodDefault<z.ZodArray<z.ZodString, "many">>;
240
258
  crawl4aiHost: z.ZodDefault<z.ZodString>;
259
+ brightDataZone: z.ZodOptional<z.ZodString>;
241
260
  timeoutMs: z.ZodDefault<z.ZodNumber>;
242
261
  maxContentLength: z.ZodDefault<z.ZodNumber>;
243
262
  }, "strip", z.ZodTypeAny, {
244
- preferredProvider: "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct";
263
+ preferredProvider: "brightdata" | "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct";
245
264
  fallbackChain: string[];
246
265
  timeoutMs: number;
247
266
  crawl4aiHost: string;
248
267
  maxContentLength: number;
268
+ brightDataZone?: string | undefined;
249
269
  }, {
250
- preferredProvider?: "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct" | undefined;
270
+ preferredProvider?: "brightdata" | "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct" | undefined;
251
271
  fallbackChain?: string[] | undefined;
272
+ brightDataZone?: string | undefined;
252
273
  timeoutMs?: number | undefined;
253
274
  crawl4aiHost?: string | undefined;
254
275
  maxContentLength?: number | undefined;
@@ -268,25 +289,30 @@ declare const ResearchConfigSchema: z.ZodObject<{
268
289
  }>>;
269
290
  }, "strip", z.ZodTypeAny, {
270
291
  search: {
271
- preferredProvider: "tavily" | "exa" | "serper" | "searxng" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom";
292
+ preferredProvider: "tavily" | "exa" | "serper" | "searxng" | "brightdata" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom";
272
293
  fallbackChain: string[];
273
294
  apiKeys: {
274
295
  tavily?: string | undefined;
275
296
  exa?: string | undefined;
276
297
  serper?: string | undefined;
298
+ brightdata?: string | undefined;
277
299
  jina?: string | undefined;
278
300
  semanticScholar?: string | undefined;
301
+ brightData?: string | undefined;
279
302
  };
303
+ brightDataEngine: "google" | "bing" | "yandex";
280
304
  timeoutMs: number;
281
305
  maxResultsPerQuery: number;
282
306
  searxngHost?: string | undefined;
307
+ brightDataZone?: string | undefined;
283
308
  };
284
309
  crawler: {
285
- preferredProvider: "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct";
310
+ preferredProvider: "brightdata" | "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct";
286
311
  fallbackChain: string[];
287
312
  timeoutMs: number;
288
313
  crawl4aiHost: string;
289
314
  maxContentLength: number;
315
+ brightDataZone?: string | undefined;
290
316
  };
291
317
  quality: {
292
318
  minRelevanceScore: number;
@@ -295,22 +321,27 @@ declare const ResearchConfigSchema: z.ZodObject<{
295
321
  };
296
322
  }, {
297
323
  search?: {
298
- preferredProvider?: "tavily" | "exa" | "serper" | "searxng" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom" | undefined;
324
+ preferredProvider?: "tavily" | "exa" | "serper" | "searxng" | "brightdata" | "duckduckgo" | "semantic_scholar" | "openalex" | "arxiv" | "custom" | undefined;
299
325
  fallbackChain?: string[] | undefined;
300
326
  apiKeys?: {
301
327
  tavily?: string | undefined;
302
328
  exa?: string | undefined;
303
329
  serper?: string | undefined;
330
+ brightdata?: string | undefined;
304
331
  jina?: string | undefined;
305
332
  semanticScholar?: string | undefined;
333
+ brightData?: string | undefined;
306
334
  } | undefined;
307
335
  searxngHost?: string | undefined;
336
+ brightDataZone?: string | undefined;
337
+ brightDataEngine?: "google" | "bing" | "yandex" | undefined;
308
338
  timeoutMs?: number | undefined;
309
339
  maxResultsPerQuery?: number | undefined;
310
340
  } | undefined;
311
341
  crawler?: {
312
- preferredProvider?: "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct" | undefined;
342
+ preferredProvider?: "brightdata" | "custom" | "jina" | "crawl4ai" | "youtube" | "defuddle" | "direct" | undefined;
313
343
  fallbackChain?: string[] | undefined;
344
+ brightDataZone?: string | undefined;
314
345
  timeoutMs?: number | undefined;
315
346
  crawl4aiHost?: string | undefined;
316
347
  maxContentLength?: number | undefined;