@semiont/vectors 0.5.11 → 0.5.13

package/dist/{chunk-TYDOHCBS.js → chunk-VFNOQC4M.js}

@@ -121,25 +121,37 @@ var QdrantVectorStore = class {
     ]);
     return resources.count + annotations.count;
   }
-  async listResourceChecksums() {
-    const checksums = /* @__PURE__ */ new Map();
+  async updateResourceEntityTypes(resourceId, entityTypes) {
+    await this.qdrant.setPayload("resources", {
+      payload: { entityTypes },
+      filter: {
+        must: [{ key: "resourceId", match: { value: String(resourceId) } }]
+      }
+    });
+  }
+  async listResourceStamps() {
+    const stamps = /* @__PURE__ */ new Map();
     let offset = void 0;
     do {
       const page = await this.qdrant.scroll("resources", {
         limit: 1e3,
         offset,
-        with_payload: ["resourceId", "contentChecksum"],
+        with_payload: ["resourceId", "contentChecksum", "entityTypes"],
         with_vector: false
       });
       for (const point of page.points) {
         const rid = point.payload?.resourceId;
-        if (typeof rid !== "string" || checksums.has(rid)) continue;
+        if (typeof rid !== "string" || stamps.has(rid)) continue;
         const checksum = point.payload?.contentChecksum;
-        checksums.set(rid, typeof checksum === "string" ? checksum : void 0);
+        const entityTypes = point.payload?.entityTypes;
+        stamps.set(rid, {
+          contentChecksum: typeof checksum === "string" ? checksum : void 0,
+          entityTypes: Array.isArray(entityTypes) ? entityTypes.filter((t) => typeof t === "string") : []
+        });
       }
       offset = page.next_page_offset ?? void 0;
     } while (offset !== void 0 && offset !== null);
-    return checksums;
+    return stamps;
   }
   async listAnnotationIds() {
     return this.scrollPayloadField("annotations", "annotationId");
@@ -266,4 +278,4 @@ var QdrantVectorStore = class {
 export {
   QdrantVectorStore
 };
-//# sourceMappingURL=chunk-TYDOHCBS.js.map
+//# sourceMappingURL=chunk-VFNOQC4M.js.map

package/dist/chunk-VFNOQC4M.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/store/qdrant.ts"],"sourcesContent":["/**\n * Qdrant VectorStore Implementation\n *\n * Uses the Qdrant REST API via @qdrant/js-client-rest.\n * Manages two collections: 'resources' and 'annotations'.\n */\n\nimport { createHash } from 'crypto';\nimport type { QdrantClient, Schemas } from '@qdrant/js-client-rest';\nimport type { ResourceId, AnnotationId } from '@semiont/core';\nimport type { VectorStore, EmbeddingChunk, AnnotationPayload, VectorSearchResult, SearchOptions } from './interface';\n\n/**\n * Generate a deterministic UUID v5-style ID from an arbitrary string.\n * Qdrant requires point IDs to be UUIDs or unsigned integers.\n */\nfunction toQdrantId(input: string): string {\n  const hex = createHash('md5').update(input).digest('hex');\n  return `${hex.slice(0, 8)}-${hex.slice(8, 12)}-${hex.slice(12, 16)}-${hex.slice(16, 20)}-${hex.slice(20, 32)}`;\n}\n\nexport interface QdrantConfig {\n  host: string;\n  port: number;\n  dimensions: number;\n}\n\nexport class QdrantVectorStore implements VectorStore {\n  private client: QdrantClient | null = null;\n  private config: QdrantConfig;\n\n  constructor(config: QdrantConfig) {\n    this.config = config;\n  }\n\n  private get qdrant(): QdrantClient {\n    if (!this.client) throw new Error('QdrantVectorStore is not connected');\n    return this.client;\n  }\n\n  async connect(): Promise<void> {\n    const { QdrantClient } = await import('@qdrant/js-client-rest');\n    this.client = new QdrantClient({\n      host: this.config.host,\n      port: this.config.port,\n    });\n\n    // Ensure collections exist\n    await this.ensureCollection('resources', this.config.dimensions);\n    await this.ensureCollection('annotations', this.config.dimensions);\n    // Payload indexes so filtered operations scale:\n    //  - entityTypes: the excludeEntityTypes recall filter.\n    //  - resourceId: searchByResource's by-resource scroll + self-exclusion, and\n    //    the per-resource delete paths (deleteResourceVectors /\n    //    deleteAnnotationVectorsForResource).\n    await this.ensurePayloadIndex('resources', 'entityTypes');\n    await this.ensurePayloadIndex('resources', 'resourceId');\n    await this.ensurePayloadIndex('annotations', 'resourceId');\n  }\n\n  async disconnect(): Promise<void> {\n    this.client = null;\n  }\n\n  async clearAll(): Promise<void> {\n    try { await this.qdrant.deleteCollection('resources'); } catch { /* may not exist */ }\n    try { await this.qdrant.deleteCollection('annotations'); } catch { /* may not exist */ }\n    await this.ensureCollection('resources', this.config.dimensions);\n    await this.ensureCollection('annotations', this.config.dimensions);\n  }\n\n  isConnected(): boolean {\n    return this.client !== null;\n  }\n\n  private async ensureCollection(name: string, dimensions: number): Promise<void> {\n    try {\n      await this.qdrant.getCollection(name);\n    } catch {\n      await this.qdrant.createCollection(name, {\n        vectors: { size: dimensions, distance: 'Cosine' },\n      });\n    }\n  }\n\n  /**\n   * Idempotently create a keyword payload index. Qdrant accepts a repeat call\n   * for an already-indexed field, so this runs safely on every connect and\n   * back-fills the index on collections created before the field was indexed.\n   */\n  private async ensurePayloadIndex(collection: string, field: string): Promise<void> {\n    try {\n      await this.qdrant.createPayloadIndex(collection, { field_name: field, field_schema: 'keyword' });\n    } catch { /* already indexed, or created concurrently */ }\n  }\n\n  async upsertResourceVectors(resourceId: ResourceId, chunks: EmbeddingChunk[], contentChecksum: string, entityTypes: string[]): Promise<void> {\n    // Replace semantics: purge existing chunks first, or a resource that\n    // shrinks leaves orphan points at the higher chunk indices.\n    await this.deleteResourceVectors(resourceId);\n    if (chunks.length === 0) return;\n\n    const points = chunks.map((chunk) => ({\n      id: toQdrantId(`${resourceId}-${chunk.chunkIndex}`),\n      vector: chunk.embedding,\n      payload: {\n        resourceId: String(resourceId),\n        chunkIndex: chunk.chunkIndex,\n        text: chunk.text,\n        contentChecksum,\n        entityTypes,\n      },\n    }));\n\n    await this.qdrant.upsert('resources', { points });\n  }\n\n  async upsertAnnotationVector(\n    annotationId: AnnotationId,\n    embedding: number[],\n    payload: AnnotationPayload\n  ): Promise<void> {\n    await this.qdrant.upsert('annotations', {\n      points: [{\n        id: toQdrantId(String(annotationId)),\n        vector: embedding,\n        payload: {\n          annotationId: String(payload.annotationId),\n          resourceId: String(payload.resourceId),\n          motivation: payload.motivation,\n          entityTypes: payload.entityTypes,\n          text: payload.exactText,\n        },\n      }],\n    });\n  }\n\n  async deleteResourceVectors(resourceId: ResourceId): Promise<void> {\n    await this.qdrant.delete('resources', {\n      filter: {\n        must: [{ key: 'resourceId', match: { value: String(resourceId) } }],\n      },\n    });\n  }\n\n  async deleteAnnotationVector(annotationId: AnnotationId): Promise<void> {\n    await this.qdrant.delete('annotations', {\n      points: [toQdrantId(String(annotationId))],\n    });\n  }\n\n  async deleteAnnotationVectorsForResource(resourceId: ResourceId): Promise<void> {\n    await this.qdrant.delete('annotations', {\n      filter: {\n        must: [{ key: 'resourceId', match: { value: String(resourceId) } }],\n      },\n    });\n  }\n\n  async count(): Promise<number> {\n    const [resources, annotations] = await Promise.all([\n      this.qdrant.count('resources', { exact: true }),\n      this.qdrant.count('annotations', { exact: true }),\n    ]);\n    return resources.count + annotations.count;\n  }\n\n  async updateResourceEntityTypes(resourceId: ResourceId, entityTypes: string[]): Promise<void> {\n    // Payload-only rewrite across the resource's points — no vectors touched,\n    // no embedding involved (S13). Qdrant set_payload with a filter is a\n    // no-op when the resource has no points.\n    await this.qdrant.setPayload('resources', {\n      payload: { entityTypes },\n      filter: {\n        must: [{ key: 'resourceId', match: { value: String(resourceId) } }],\n      },\n    });\n  }\n\n  async listResourceStamps(): Promise<Map<string, { contentChecksum: string | undefined; entityTypes: string[] }>> {\n    const stamps = new Map<string, { contentChecksum: string | undefined; entityTypes: string[] }>();\n    let offset: Schemas['ScrollRequest']['offset'] = undefined;\n    do {\n      const page = await this.qdrant.scroll('resources', {\n        limit: 1000,\n        offset,\n        with_payload: ['resourceId', 'contentChecksum', 'entityTypes'],\n        with_vector: false,\n      });\n      for (const point of page.points) {\n        const rid = point.payload?.resourceId;\n        if (typeof rid !== 'string' || stamps.has(rid)) continue;\n        const checksum = point.payload?.contentChecksum;\n        const entityTypes = point.payload?.entityTypes;\n        stamps.set(rid, {\n          contentChecksum: typeof checksum === 'string' ? checksum : undefined,\n          entityTypes: Array.isArray(entityTypes)\n            ? entityTypes.filter((t): t is string => typeof t === 'string')\n            : [],\n        });\n      }\n      offset = page.next_page_offset ?? undefined;\n    } while (offset !== undefined && offset !== null);\n    return stamps;\n  }\n\n  async listAnnotationIds(): Promise<Set<string>> {\n    return this.scrollPayloadField('annotations', 'annotationId');\n  }\n\n  /** Collect the distinct values of one payload field across a collection. */\n  private async scrollPayloadField(collection: string, field: string): Promise<Set<string>> {\n    const values = new Set<string>();\n    let offset: Schemas['ScrollRequest']['offset'] = undefined;\n    do {\n      const page = await this.qdrant.scroll(collection, {\n        limit: 1000,\n        offset,\n        with_payload: [field],\n        with_vector: false,\n      });\n      for (const point of page.points) {\n        const value = point.payload?.[field];\n        if (typeof value === 'string') values.add(value);\n      }\n      offset = page.next_page_offset ?? undefined;\n    } while (offset !== undefined && offset !== null);\n    return values;\n  }\n\n  async searchResources(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    return this.search('resources', embedding, opts);\n  }\n\n  async searchAnnotations(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    return this.search('annotations', embedding, opts);\n  }\n\n  async searchByResource(resourceId: ResourceId, opts: SearchOptions): Promise<VectorSearchResult[]> {\n    // Fetch the resource's stored chunk vectors (page through all of them so a\n    // long resource isn't silently truncated).\n    const queryVectors: number[][] = [];\n    let offset: Schemas['ScrollRequest']['offset'] = undefined;\n    do {\n      const page = await this.qdrant.scroll('resources', {\n        filter: { must: [{ key: 'resourceId', match: { value: String(resourceId) } }] },\n        with_vector: true,\n        with_payload: false,\n        limit: 256,\n        offset,\n      });\n      for (const point of page.points) {\n        if (Array.isArray(point.vector)) queryVectors.push(point.vector as number[]);\n      }\n      offset = page.next_page_offset ?? undefined;\n    } while (offset !== undefined && offset !== null);\n\n    if (queryVectors.length === 0) return [];\n\n    // Self-exclude the source; carry the caller's filter (e.g. excludeEntityTypes).\n    const filter = this.buildFilter({ ...opts.filter, excludeResourceId: resourceId });\n\n    // One batched search per query chunk (single round-trip), top-`limit` each;\n    // over-fetch beyond `limit` is unnecessary because the max-sim merge only\n    // needs a target in some chunk's top-K to surface.\n    const searches = queryVectors.map((vector) => ({\n      vector,\n      limit: opts.limit,\n      score_threshold: opts.scoreThreshold,\n      filter: filter ?? undefined,\n      with_payload: true,\n    }));\n    const batches = await this.qdrant.searchBatch('resources', { searches });\n\n    // Max-sim merge: dedup by resourceId, keep the best (query-chunk × target-chunk)\n    // score and the best-matching target chunk's payload.\n    const bestByResource = new Map<string, { id: string; score: number; payload: Record<string, unknown> }>();\n    for (const batch of batches) {\n      for (const r of batch) {\n        const payload = r.payload ?? {};\n        const tid = String(payload.resourceId);\n        const prev = bestByResource.get(tid);\n        if (!prev || r.score > prev.score) {\n          bestByResource.set(tid, { id: String(r.id), score: r.score, payload });\n        }\n      }\n    }\n\n    return [...bestByResource.values()]\n      .sort((a, b) => b.score - a.score)\n      .slice(0, opts.limit)\n      .map((m) => ({\n        id: m.id,\n        score: m.score,\n        resourceId: m.payload.resourceId as ResourceId,\n        annotationId: m.payload.annotationId as AnnotationId | undefined,\n        text: m.payload.text as string,\n        entityTypes: m.payload.entityTypes as string[] | undefined,\n      }));\n  }\n\n  private async search(collection: string, embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    const filter = this.buildFilter(opts.filter);\n\n    const results = await this.qdrant.search(collection, {\n      vector: embedding,\n      limit: opts.limit,\n      score_threshold: opts.scoreThreshold,\n      filter: filter ?? undefined,\n      with_payload: true,\n    });\n\n    return results.map((r) => {\n      const payload = r.payload ?? {};\n      return {\n        id: String(r.id),\n        score: r.score,\n        resourceId: payload.resourceId as ResourceId,\n        annotationId: payload.annotationId as AnnotationId | undefined,\n        text: payload.text as string,\n        entityTypes: payload.entityTypes as string[] | undefined,\n      };\n    });\n  }\n\n  private buildFilter(filter?: SearchOptions['filter']): Schemas['Filter'] | null {\n    if (!filter) return null;\n\n    const must: Schemas['FieldCondition'][] = [];\n\n    if (filter.entityTypes && filter.entityTypes.length > 0) {\n      // any-of: match payloads whose `entityTypes` array contains at least one\n      // of the requested types. Matches the memory store's `some(t => ...)`\n      // semantics; pushing one `must` clause per type would mean all-of.\n      must.push({ key: 'entityTypes', match: { any: filter.entityTypes } });\n    }\n\n    if (filter.resourceId) {\n      must.push({ key: 'resourceId', match: { value: String(filter.resourceId) } });\n    }\n\n    if (filter.motivation) {\n      must.push({ key: 'motivation', match: { value: filter.motivation } });\n    }\n\n    const must_not: Schemas['FieldCondition'][] = [];\n\n    if (filter.excludeResourceId) {\n      must_not.push({ key: 'resourceId', match: { value: String(filter.excludeResourceId) } });\n    }\n\n    if (filter.excludeEntityTypes && filter.excludeEntityTypes.length > 0) {\n      // any-of exclusion: drop points whose entityTypes contain any of these.\n      must_not.push({ key: 'entityTypes', match: { any: filter.excludeEntityTypes } });\n    }\n\n    if (must.length === 0 && must_not.length === 0) return null;\n\n    return {\n      ...(must.length > 0 ? { must } : {}),\n      ...(must_not.length > 0 ? { must_not } : {}),\n    };\n  }\n}\n"],"mappings":";AAOA,SAAS,kBAAkB;AAS3B,SAAS,WAAW,OAAuB;AACzC,QAAM,MAAM,WAAW,KAAK,EAAE,OAAO,KAAK,EAAE,OAAO,KAAK;AACxD,SAAO,GAAG,IAAI,MAAM,GAAG,CAAC,CAAC,IAAI,IAAI,MAAM,GAAG,EAAE,CAAC,IAAI,IAAI,MAAM,IAAI,EAAE,CAAC,IAAI,IAAI,MAAM,IAAI,EAAE,CAAC,IAAI,IAAI,MAAM,IAAI,EAAE,CAAC;AAC9G;AAQO,IAAM,oBAAN,MAA+C;AAAA,EAC5C,SAA8B;AAAA,EAC9B;AAAA,EAER,YAAY,QAAsB;AAChC,SAAK,SAAS;AAAA,EAChB;AAAA,EAEA,IAAY,SAAuB;AACjC,QAAI,CAAC,KAAK,OAAQ,OAAM,IAAI,MAAM,oCAAoC;AACtE,WAAO,KAAK;AAAA,EACd;AAAA,EAEA,MAAM,UAAyB;AAC7B,UAAM,EAAE,aAAa,IAAI,MAAM,OAAO,wBAAwB;AAC9D,SAAK,SAAS,IAAI,aAAa;AAAA,MAC7B,MAAM,KAAK,OAAO;AAAA,MAClB,MAAM,KAAK,OAAO;AAAA,IACpB,CAAC;AAGD,UAAM,KAAK,iBAAiB,aAAa,KAAK,OAAO,UAAU;AAC/D,UAAM,KAAK,iBAAiB,eAAe,KAAK,OAAO,UAAU;AAMjE,UAAM,KAAK,mBAAmB,aAAa,aAAa;AACxD,UAAM,KAAK,mBAAmB,aAAa,YAAY;AACvD,UAAM,KAAK,mBAAmB,eAAe,YAAY;AAAA,EAC3D;AAAA,EAEA,MAAM,aAA4B;AAChC,SAAK,SAAS;AAAA,EAChB;AAAA,EAEA,MAAM,WAA0B;AAC9B,QAAI;AAAE,YAAM,KAAK,OAAO,iBAAiB,WAAW;AAAA,IAAG,QAAQ;AAAA,IAAsB;AACrF,QAAI;AAAE,YAAM,KAAK,OAAO,iBAAiB,aAAa;AAAA,IAAG,QAAQ;AAAA,IAAsB;AACvF,UAAM,KAAK,iBAAiB,aAAa,KAAK,OAAO,UAAU;AAC/D,UAAM,KAAK,iBAAiB,eAAe,KAAK,OAAO,UAAU;AAAA,EACnE;AAAA,EAEA,cAAuB;AACrB,WAAO,KAAK,WAAW;AAAA,EACzB;AAAA,EAEA,MAAc,iBAAiB,MAAc,YAAmC;AAC9E,QAAI;AACF,YAAM,KAAK,OAAO,cAAc,IAAI;AAAA,IACtC,QAAQ;AACN,YAAM,KAAK,OAAO,iBAAiB,MAAM;AAAA,QACvC,SAAS,EAAE,MAAM,YAAY,UAAU,SAAS;AAAA,MAClD,CAAC;AAAA,IACH;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAc,mBAAmB,YAAoB,OAA8B;AACjF,QAAI;AACF,YAAM,KAAK,OAAO,mBAAmB,YAAY,EAAE,YAAY,OAAO,cAAc,UAAU,CAAC;AAAA,IACjG,QAAQ;AAAA,IAAiD;AAAA,EAC3D;AAAA,EAEA,MAAM,sBAAsB,YAAwB,QAA0B,iBAAyB,aAAsC;AAG3I,UAAM,KAAK,sBAAsB,UAAU;AAC3C,QAAI,OAAO,WAAW,EAAG;AAEzB,UAAM,SAAS,OAAO,IAAI,CAAC,WAAW;AAAA,MACpC,IAAI,WAAW,GAAG,UAAU,IAAI,MAAM,UAAU,EAAE;AAAA,MAClD,QAAQ,MAAM;AAAA,MACd,SAAS;AAAA,QACP,YAAY,OAAO,UAAU;AAAA,QAC7B,YAAY,MAAM;AAAA,QAClB,MAAM,MAAM;AAAA,QACZ;AAAA,QACA;AAAA,MACF;AAAA,IACF,EAAE;AAEF,UAAM,KAAK,OAAO,OAAO,aAAa,EAAE,OAAO,CAAC;AAAA,EAClD;AAAA,EAEA,MAAM,uBACJ,cACA,WACA,SACe;AACf,UAAM,KAAK,OAAO,OAAO,eAAe;AAAA,MACtC,QAAQ,CAAC;AAAA,QACP,IAAI,WAAW,OAAO,YAAY,CAAC;AAAA,QACnC,QAAQ;AAAA,QACR,SAAS;AAAA,UACP,cAAc,OAAO,QAAQ,YAAY;AAAA,UACzC,YAAY,OAAO,QAAQ,UAAU;AAAA,UACrC,YAAY,QAAQ;AAAA,UACpB,aAAa,QAAQ;AAAA,UACrB,MAAM,QAAQ;AAAA,QAChB;AAAA,MACF,CAAC;AAAA,IACH,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,sBAAsB,YAAuC;AACjE,UAAM,KAAK,OAAO,OAAO,aAAa;AAAA,MACpC,QAAQ;AAAA,QACN,MAAM,CAAC,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,UAAU,EAAE,EAAE,CAAC;AAAA,MACpE;AAAA,IACF,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,uBAAuB,cAA2C;AACtE,UAAM,KAAK,OAAO,OAAO,eAAe;AAAA,MACtC,QAAQ,CAAC,WAAW,OAAO,YAAY,CAAC,CAAC;AAAA,IAC3C,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,mCAAmC,YAAuC;AAC9E,UAAM,KAAK,OAAO,OAAO,eAAe;AAAA,MACtC,QAAQ;AAAA,QACN,MAAM,CAAC,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,UAAU,EAAE,EAAE,CAAC;AAAA,MACpE;AAAA,IACF,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,QAAyB;AAC7B,UAAM,CAAC,WAAW,WAAW,IAAI,MAAM,QAAQ,IAAI;AAAA,MACjD,KAAK,OAAO,MAAM,aAAa,EAAE,OAAO,KAAK,CAAC;AAAA,MAC9C,KAAK,OAAO,MAAM,eAAe,EAAE,OAAO,KAAK,CAAC;AAAA,IAClD,CAAC;AACD,WAAO,UAAU,QAAQ,YAAY;AAAA,EACvC;AAAA,EAEA,MAAM,0BAA0B,YAAwB,aAAsC;AAI5F,UAAM,KAAK,OAAO,WAAW,aAAa;AAAA,MACxC,SAAS,EAAE,YAAY;AAAA,MACvB,QAAQ;AAAA,QACN,MAAM,CAAC,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,UAAU,EAAE,EAAE,CAAC;AAAA,MACpE;AAAA,IACF,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,qBAA2G;AAC/G,UAAM,SAAS,oBAAI,IAA4E;AAC/F,QAAI,SAA6C;AACjD,OAAG;AACD,YAAM,OAAO,MAAM,KAAK,OAAO,OAAO,aAAa;AAAA,QACjD,OAAO;AAAA,QACP;AAAA,QACA,cAAc,CAAC,cAAc,mBAAmB,aAAa;AAAA,QAC7D,aAAa;AAAA,MACf,CAAC;AACD,iBAAW,SAAS,KAAK,QAAQ;AAC/B,cAAM,MAAM,MAAM,SAAS;AAC3B,YAAI,OAAO,QAAQ,YAAY,OAAO,IAAI,GAAG,EAAG;AAChD,cAAM,WAAW,MAAM,SAAS;AAChC,cAAM,cAAc,MAAM,SAAS;AACnC,eAAO,IAAI,KAAK;AAAA,UACd,iBAAiB,OAAO,aAAa,WAAW,WAAW;AAAA,UAC3D,aAAa,MAAM,QAAQ,WAAW,IAClC,YAAY,OAAO,CAAC,MAAmB,OAAO,MAAM,QAAQ,IAC5D,CAAC;AAAA,QACP,CAAC;AAAA,MACH;AACA,eAAS,KAAK,oBAAoB;AAAA,IACpC,SAAS,WAAW,UAAa,WAAW;AAC5C,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,oBAA0C;AAC9C,WAAO,KAAK,mBAAmB,eAAe,cAAc;AAAA,EAC9D;AAAA;AAAA,EAGA,MAAc,mBAAmB,YAAoB,OAAqC;AACxF,UAAM,SAAS,oBAAI,IAAY;AAC/B,QAAI,SAA6C;AACjD,OAAG;AACD,YAAM,OAAO,MAAM,KAAK,OAAO,OAAO,YAAY;AAAA,QAChD,OAAO;AAAA,QACP;AAAA,QACA,cAAc,CAAC,KAAK;AAAA,QACpB,aAAa;AAAA,MACf,CAAC;AACD,iBAAW,SAAS,KAAK,QAAQ;AAC/B,cAAM,QAAQ,MAAM,UAAU,KAAK;AACnC,YAAI,OAAO,UAAU,SAAU,QAAO,IAAI,KAAK;AAAA,MACjD;AACA,eAAS,KAAK,oBAAoB;AAAA,IACpC,SAAS,WAAW,UAAa,WAAW;AAC5C,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,gBAAgB,WAAqB,MAAoD;AAC7F,WAAO,KAAK,OAAO,aAAa,WAAW,IAAI;AAAA,EACjD;AAAA,EAEA,MAAM,kBAAkB,WAAqB,MAAoD;AAC/F,WAAO,KAAK,OAAO,eAAe,WAAW,IAAI;AAAA,EACnD;AAAA,EAEA,MAAM,iBAAiB,YAAwB,MAAoD;AAGjG,UAAM,eAA2B,CAAC;AAClC,QAAI,SAA6C;AACjD,OAAG;AACD,YAAM,OAAO,MAAM,KAAK,OAAO,OAAO,aAAa;AAAA,QACjD,QAAQ,EAAE,MAAM,CAAC,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,UAAU,EAAE,EAAE,CAAC,EAAE;AAAA,QAC9E,aAAa;AAAA,QACb,cAAc;AAAA,QACd,OAAO;AAAA,QACP;AAAA,MACF,CAAC;AACD,iBAAW,SAAS,KAAK,QAAQ;AAC/B,YAAI,MAAM,QAAQ,MAAM,MAAM,EAAG,cAAa,KAAK,MAAM,MAAkB;AAAA,MAC7E;AACA,eAAS,KAAK,oBAAoB;AAAA,IACpC,SAAS,WAAW,UAAa,WAAW;AAE5C,QAAI,aAAa,WAAW,EAAG,QAAO,CAAC;AAGvC,UAAM,SAAS,KAAK,YAAY,EAAE,GAAG,KAAK,QAAQ,mBAAmB,WAAW,CAAC;AAKjF,UAAM,WAAW,aAAa,IAAI,CAAC,YAAY;AAAA,MAC7C;AAAA,MACA,OAAO,KAAK;AAAA,MACZ,iBAAiB,KAAK;AAAA,MACtB,QAAQ,UAAU;AAAA,MAClB,cAAc;AAAA,IAChB,EAAE;AACF,UAAM,UAAU,MAAM,KAAK,OAAO,YAAY,aAAa,EAAE,SAAS,CAAC;AAIvE,UAAM,iBAAiB,oBAAI,IAA6E;AACxG,eAAW,SAAS,SAAS;AAC3B,iBAAW,KAAK,OAAO;AACrB,cAAM,UAAU,EAAE,WAAW,CAAC;AAC9B,cAAM,MAAM,OAAO,QAAQ,UAAU;AACrC,cAAM,OAAO,eAAe,IAAI,GAAG;AACnC,YAAI,CAAC,QAAQ,EAAE,QAAQ,KAAK,OAAO;AACjC,yBAAe,IAAI,KAAK,EAAE,IAAI,OAAO,EAAE,EAAE,GAAG,OAAO,EAAE,OAAO,QAAQ,CAAC;AAAA,QACvE;AAAA,MACF;AAAA,IACF;AAEA,WAAO,CAAC,GAAG,eAAe,OAAO,CAAC,EAC/B,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK,EAChC,MAAM,GAAG,KAAK,KAAK,EACnB,IAAI,CAAC,OAAO;AAAA,MACX,IAAI,EAAE;AAAA,MACN,OAAO,EAAE;AAAA,MACT,YAAY,EAAE,QAAQ;AAAA,MACtB,cAAc,EAAE,QAAQ;AAAA,MACxB,MAAM,EAAE,QAAQ;AAAA,MAChB,aAAa,EAAE,QAAQ;AAAA,IACzB,EAAE;AAAA,EACN;AAAA,EAEA,MAAc,OAAO,YAAoB,WAAqB,MAAoD;AAChH,UAAM,SAAS,KAAK,YAAY,KAAK,MAAM;AAE3C,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,YAAY;AAAA,MACnD,QAAQ;AAAA,MACR,OAAO,KAAK;AAAA,MACZ,iBAAiB,KAAK;AAAA,MACtB,QAAQ,UAAU;AAAA,MAClB,cAAc;AAAA,IAChB,CAAC;AAED,WAAO,QAAQ,IAAI,CAAC,MAAM;AACxB,YAAM,UAAU,EAAE,WAAW,CAAC;AAC9B,aAAO;AAAA,QACL,IAAI,OAAO,EAAE,EAAE;AAAA,QACf,OAAO,EAAE;AAAA,QACT,YAAY,QAAQ;AAAA,QACpB,cAAc,QAAQ;AAAA,QACtB,MAAM,QAAQ;AAAA,QACd,aAAa,QAAQ;AAAA,MACvB;AAAA,IACF,CAAC;AAAA,EACH;AAAA,EAEQ,YAAY,QAA4D;AAC9E,QAAI,CAAC,OAAQ,QAAO;AAEpB,UAAM,OAAoC,CAAC;AAE3C,QAAI,OAAO,eAAe,OAAO,YAAY,SAAS,GAAG;AAIvD,WAAK,KAAK,EAAE,KAAK,eAAe,OAAO,EAAE,KAAK,OAAO,YAAY,EAAE,CAAC;AAAA,IACtE;AAEA,QAAI,OAAO,YAAY;AACrB,WAAK,KAAK,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,OAAO,UAAU,EAAE,EAAE,CAAC;AAAA,IAC9E;AAEA,QAAI,OAAO,YAAY;AACrB,WAAK,KAAK,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,WAAW,EAAE,CAAC;AAAA,IACtE;AAEA,UAAM,WAAwC,CAAC;AAE/C,QAAI,OAAO,mBAAmB;AAC5B,eAAS,KAAK,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,OAAO,iBAAiB,EAAE,EAAE,CAAC;AAAA,IACzF;AAEA,QAAI,OAAO,sBAAsB,OAAO,mBAAmB,SAAS,GAAG;AAErE,eAAS,KAAK,EAAE,KAAK,eAAe,OAAO,EAAE,KAAK,OAAO,mBAAmB,EAAE,CAAC;AAAA,IACjF;AAEA,QAAI,KAAK,WAAW,KAAK,SAAS,WAAW,EAAG,QAAO;AAEvD,WAAO;AAAA,MACL,GAAI,KAAK,SAAS,IAAI,EAAE,KAAK,IAAI,CAAC;AAAA,MAClC,GAAI,SAAS,SAAS,IAAI,EAAE,SAAS,IAAI,CAAC;AAAA,IAC5C;AAAA,EACF;AACF;","names":[]}

package/dist/index.d.ts

@@ -61,6 +61,13 @@ interface VectorStore {
      * discriminate by kind (e.g. exclude `['Question']` from recall).
      */
     upsertResourceVectors(resourceId: ResourceId, chunks: EmbeddingChunk[], contentChecksum: string, entityTypes: string[]): Promise<void>;
+    /**
+     * Rewrite the `entityTypes` stamp on a resource's existing points —
+     * payload-only, no embedding involved (SMELTER-AXIOMS.md, S13: a tag edit
+     * must never trigger an embedding call). No-op when the resource has no
+     * points: the stamp rides the next embed.
+     */
+    updateResourceEntityTypes(resourceId: ResourceId, entityTypes: string[]): Promise<void>;
     upsertAnnotationVector(annotationId: AnnotationId, embedding: number[], payload: AnnotationPayload): Promise<void>;
     deleteResourceVectors(resourceId: ResourceId): Promise<void>;
     deleteAnnotationVector(annotationId: AnnotationId): Promise<void>;
@@ -90,10 +97,15 @@ interface VectorStore {
     count(): Promise<number>;
     /**
      * Distinct resourceIds present in the resources collection, each with its
-     * stamped content checksum (undefined for points written before stamping
-     * existed — reconciliation treats those as stale and re-embeds them).
+     * stamps: the content checksum (undefined for points written before
+     * stamping existed — reconciliation treats those as stale and re-embeds)
+     * and the entity-type set (missing stamp reads as `[]`). Drives both the
+     * S12 content-staleness diff and the S13 tag-staleness diff.
      */
-    listResourceChecksums(): Promise<Map<string, string | undefined>>;
+    listResourceStamps(): Promise<Map<string, {
+        contentChecksum: string | undefined;
+        entityTypes: string[];
+    }>>;
     /** Distinct annotationIds present in the annotations collection. */
     listAnnotationIds(): Promise<Set<string>>;
 }
@@ -132,7 +144,11 @@ declare class QdrantVectorStore implements VectorStore {
     deleteAnnotationVector(annotationId: AnnotationId): Promise<void>;
     deleteAnnotationVectorsForResource(resourceId: ResourceId): Promise<void>;
     count(): Promise<number>;
-    listResourceChecksums(): Promise<Map<string, string | undefined>>;
+    updateResourceEntityTypes(resourceId: ResourceId, entityTypes: string[]): Promise<void>;
+    listResourceStamps(): Promise<Map<string, {
+        contentChecksum: string | undefined;
+        entityTypes: string[];
+    }>>;
     listAnnotationIds(): Promise<Set<string>>;
     /** Collect the distinct values of one payload field across a collection. */
     private scrollPayloadField;
@@ -164,7 +180,11 @@ declare class MemoryVectorStore implements VectorStore {
     deleteAnnotationVector(annotationId: AnnotationId): Promise<void>;
     deleteAnnotationVectorsForResource(resourceId: ResourceId): Promise<void>;
     count(): Promise<number>;
-    listResourceChecksums(): Promise<Map<string, string | undefined>>;
+    updateResourceEntityTypes(resourceId: ResourceId, entityTypes: string[]): Promise<void>;
+    listResourceStamps(): Promise<Map<string, {
+        contentChecksum: string | undefined;
+        entityTypes: string[];
+    }>>;
     listAnnotationIds(): Promise<Set<string>>;
     searchResources(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]>;
     searchAnnotations(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]>;

package/dist/index.js

@@ -1,6 +1,6 @@
 import {
   QdrantVectorStore
-} from "./chunk-TYDOHCBS.js";
+} from "./chunk-VFNOQC4M.js";
 import {
   VoyageEmbeddingProvider
 } from "./chunk-UM3RNDW4.js";
@@ -80,14 +80,24 @@ var MemoryVectorStore = class {
   async count() {
     return this.resources.length + this.annotations.length;
   }
-  async listResourceChecksums() {
-    const checksums = /* @__PURE__ */ new Map();
+  async updateResourceEntityTypes(resourceId, entityTypes) {
     for (const p of this.resources) {
-      if (!checksums.has(p.payload.resourceId)) {
-        checksums.set(p.payload.resourceId, p.payload.contentChecksum);
+      if (p.payload.resourceId === String(resourceId)) {
+        p.payload.entityTypes = entityTypes;
       }
     }
-    return checksums;
+  }
+  async listResourceStamps() {
+    const stamps = /* @__PURE__ */ new Map();
+    for (const p of this.resources) {
+      if (!stamps.has(p.payload.resourceId)) {
+        stamps.set(p.payload.resourceId, {
+          contentChecksum: p.payload.contentChecksum,
+          entityTypes: p.payload.entityTypes ?? []
+        });
+      }
+    }
+    return stamps;
   }
   async listAnnotationIds() {
     const ids = /* @__PURE__ */ new Set();
@@ -173,7 +183,7 @@ var MemoryVectorStore = class {
 async function createVectorStore(config) {
   let store;
   if (config.type === "qdrant") {
-    const { QdrantVectorStore: QdrantVectorStore2 } = await import("./qdrant-R7IW5NII.js");
+    const { QdrantVectorStore: QdrantVectorStore2 } = await import("./qdrant-A765QRQF.js");
     store = new QdrantVectorStore2({
       host: config.host ?? "localhost",
       port: config.port ?? 6333,

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/store/memory.ts","../src/store/factory.ts","../src/embedding/factory.ts","../src/chunking.ts"],"sourcesContent":["/**\n * In-Memory VectorStore Implementation\n *\n * For testing and development without a running Qdrant instance.\n * Uses brute-force cosine similarity search.\n */\n\nimport type { ResourceId, AnnotationId } from '@semiont/core';\nimport type { VectorStore, EmbeddingChunk, AnnotationPayload, VectorSearchResult, SearchOptions } from './interface';\n\ninterface StoredPoint {\n  id: string;\n  vector: number[];\n  payload: {\n    resourceId: string;\n    annotationId?: string;\n    chunkIndex?: number;\n    text: string;\n    contentChecksum?: string;\n    motivation?: string;\n    entityTypes?: string[];\n  };\n}\n\nfunction cosineSimilarity(a: number[], b: number[]): number {\n  let dotProduct = 0;\n  let normA = 0;\n  let normB = 0;\n  for (let i = 0; i < a.length; i++) {\n    dotProduct += a[i] * b[i];\n    normA += a[i] * a[i];\n    normB += b[i] * b[i];\n  }\n  const denom = Math.sqrt(normA) * Math.sqrt(normB);\n  return denom === 0 ? 0 : dotProduct / denom;\n}\n\nexport class MemoryVectorStore implements VectorStore {\n  private resources: StoredPoint[] = [];\n  private annotations: StoredPoint[] = [];\n  private connected = false;\n\n  async connect(): Promise<void> {\n    this.connected = true;\n  }\n\n  async disconnect(): Promise<void> {\n    this.connected = false;\n  }\n\n  async clearAll(): Promise<void> {\n    this.resources = [];\n    this.annotations = [];\n  }\n\n  isConnected(): boolean {\n    return this.connected;\n  }\n\n  async upsertResourceVectors(resourceId: ResourceId, chunks: EmbeddingChunk[], contentChecksum: string, entityTypes: string[]): Promise<void> {\n    // Remove existing vectors for this resource\n    this.resources = this.resources.filter(p => p.payload.resourceId !== String(resourceId));\n\n    for (const chunk of chunks) {\n      this.resources.push({\n        id: `${resourceId}-${chunk.chunkIndex}`,\n        vector: chunk.embedding,\n        payload: {\n          resourceId: String(resourceId),\n          chunkIndex: chunk.chunkIndex,\n          text: chunk.text,\n          contentChecksum,\n          entityTypes,\n        },\n      });\n    }\n  }\n\n  async upsertAnnotationVector(\n    annotationId: AnnotationId,\n    embedding: number[],\n    payload: AnnotationPayload\n  ): Promise<void> {\n    this.annotations = this.annotations.filter(p => p.id !== String(annotationId));\n    this.annotations.push({\n      id: String(annotationId),\n      vector: embedding,\n      payload: {\n        annotationId: String(payload.annotationId),\n        resourceId: String(payload.resourceId),\n        motivation: payload.motivation,\n        entityTypes: payload.entityTypes,\n        text: payload.exactText,\n      },\n    });\n  }\n\n  async deleteResourceVectors(resourceId: ResourceId): Promise<void> {\n    this.resources = this.resources.filter(p => p.payload.resourceId !== String(resourceId));\n  }\n\n  async deleteAnnotationVector(annotationId: AnnotationId): Promise<void> {\n    this.annotations = this.annotations.filter(p => p.id !== String(annotationId));\n  }\n\n  async deleteAnnotationVectorsForResource(resourceId: ResourceId): Promise<void> {\n    this.annotations = this.annotations.filter(p => p.payload.resourceId !== String(resourceId));\n  }\n\n  async count(): Promise<number> {\n    return this.resources.length + this.annotations.length;\n  }\n\n  async listResourceChecksums(): Promise<Map<string, string | undefined>> {\n    const checksums = new Map<string, string | undefined>();\n    for (const p of this.resources) {\n      if (!checksums.has(p.payload.resourceId)) {\n        checksums.set(p.payload.resourceId, p.payload.contentChecksum);\n      }\n    }\n    return checksums;\n  }\n\n  async listAnnotationIds(): Promise<Set<string>> {\n    const ids = new Set<string>();\n    for (const p of this.annotations) {\n      if (p.payload.annotationId) ids.add(p.payload.annotationId);\n    }\n    return ids;\n  }\n\n  async searchResources(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    return this.search(this.resources, embedding, opts);\n  }\n\n  async searchAnnotations(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    return this.search(this.annotations, embedding, opts);\n  }\n\n  async searchByResource(resourceId: ResourceId, opts: SearchOptions): Promise<VectorSearchResult[]> {\n    const rid = String(resourceId);\n    const queryPoints = this.resources.filter(p => p.payload.resourceId === rid);\n    if (queryPoints.length === 0) return [];\n\n    // Self-exclude the source; carry the caller's filter (e.g. excludeEntityTypes).\n    const filter: SearchOptions['filter'] = { ...opts.filter, excludeResourceId: resourceId };\n\n    // Per-chunk max-sim, merged by resource: each candidate point scores as the\n    // best similarity to any of the source's query chunks; keep, per target\n    // resource, the single best-matching point (its score and its text).\n    const bestByResource = new Map<string, StoredPoint & { score: number }>();\n    for (const cand of this.resources) {\n      if (!this.passesFilter(cand, filter)) continue;\n      let best = -Infinity;\n      for (const q of queryPoints) {\n        const score = cosineSimilarity(q.vector, cand.vector);\n        if (score > best) best = score;\n      }\n      const prev = bestByResource.get(cand.payload.resourceId);\n      if (!prev || best > prev.score) {\n        bestByResource.set(cand.payload.resourceId, { ...cand, score: best });\n      }\n    }\n\n    let merged = [...bestByResource.values()];\n    if (opts.scoreThreshold !== undefined) {\n      const threshold = opts.scoreThreshold;\n      merged = merged.filter(s => s.score >= threshold);\n    }\n    merged.sort((a, b) => b.score - a.score);\n    return merged.slice(0, opts.limit).map(s => this.toResult(s));\n  }\n\n  private passesFilter(p: StoredPoint, filter: SearchOptions['filter']): boolean {\n    if (!filter) return true;\n    const f = filter;\n    if (f.resourceId && p.payload.resourceId !== String(f.resourceId)) return false;\n    if (f.excludeResourceId && p.payload.resourceId === String(f.excludeResourceId)) return false;\n    if (f.motivation && p.payload.motivation !== f.motivation) return false;\n    if (f.entityTypes && f.entityTypes.length > 0) {\n      const pTypes = p.payload.entityTypes ?? [];\n      if (!f.entityTypes.some(t => pTypes.includes(t))) return false;\n    }\n    if (f.excludeEntityTypes && f.excludeEntityTypes.length > 0) {\n      const pTypes = p.payload.entityTypes ?? [];\n      if (f.excludeEntityTypes.some(t => pTypes.includes(t))) return false;\n    }\n    return true;\n  }\n\n  private search(points: StoredPoint[], embedding: number[], opts: SearchOptions): VectorSearchResult[] {\n    const filtered = points.filter(p => this.passesFilter(p, opts.filter));\n\n    const scored = filtered.map(p => ({\n      ...p,\n      score: cosineSimilarity(embedding, p.vector),\n    }));\n\n    scored.sort((a, b) => b.score - a.score);\n\n    if (opts.scoreThreshold !== undefined) {\n      const threshold = opts.scoreThreshold;\n      return scored\n        .filter(s => s.score >= threshold)\n        .slice(0, opts.limit)\n        .map(s => this.toResult(s));\n    }\n\n    return scored.slice(0, opts.limit).map(s => this.toResult(s));\n  }\n\n  private toResult(s: StoredPoint & { score: number }): VectorSearchResult {\n    return {\n      id: s.id,\n      score: s.score,\n      resourceId: s.payload.resourceId as ResourceId,\n      annotationId: s.payload.annotationId as AnnotationId | undefined,\n      text: s.payload.text,\n      entityTypes: s.payload.entityTypes,\n    };\n  }\n}\n","/**\n * VectorStore Factory\n *\n * Creates a connected VectorStore instance based on configuration.\n */\n\nimport type { VectorStore } from './interface';\nimport { MemoryVectorStore } from './memory';\n\nexport interface VectorStoreConfig {\n  type: 'qdrant' | 'memory';\n  host?: string;\n  port?: number;\n  dimensions: number;\n}\n\nexport async function createVectorStore(config: VectorStoreConfig): Promise<VectorStore> {\n  let store: VectorStore;\n\n  if (config.type === 'qdrant') {\n    const { QdrantVectorStore } = await import('./qdrant');\n    store = new QdrantVectorStore({\n      host: config.host ?? 'localhost',\n      port: config.port ?? 6333,\n      dimensions: config.dimensions,\n    });\n  } else {\n    store = new MemoryVectorStore();\n  }\n\n  await store.connect();\n  return store;\n}\n","/**\n * EmbeddingProvider Factory\n */\n\nimport type { EmbeddingProvider } from './interface';\n\nexport interface EmbeddingConfig {\n  type: 'voyage' | 'ollama';\n  model: string;\n  apiKey?: string;\n  baseURL?: string;\n  endpoint?: string;\n}\n\nexport async function createEmbeddingProvider(config: EmbeddingConfig): Promise<EmbeddingProvider> {\n  if (config.type === 'voyage') {\n    const { VoyageEmbeddingProvider } = await import('./voyage');\n    if (!config.apiKey) throw new Error('apiKey is required for Voyage embedding provider');\n    return new VoyageEmbeddingProvider({\n      apiKey: config.apiKey,\n      model: config.model,\n      endpoint: config.endpoint,\n    });\n  }\n\n  if (config.type === 'ollama') {\n    const { OllamaEmbeddingProvider } = await import('./ollama');\n    return new OllamaEmbeddingProvider({\n      model: config.model,\n      baseURL: config.baseURL,\n    });\n  }\n\n  throw new Error(`Unknown embedding provider type: ${config.type}`);\n}\n","/**\n * Text Chunking Utilities\n *\n * Splits long text into overlapping chunks for embedding.\n * Each chunk is a passage that fits within the embedding model's context window.\n */\n\nexport interface ChunkingConfig {\n  chunkSize: number;   // approximate tokens per chunk\n  overlap: number;     // tokens of overlap between adjacent chunks\n}\n\nexport const DEFAULT_CHUNKING_CONFIG: ChunkingConfig = {\n  chunkSize: 512,\n  overlap: 64,\n};\n\n/**\n * Rough token count estimate: ~4 characters per token for English text.\n */\nfunction estimateTokens(text: string): number {\n  return Math.ceil(text.length / 4);\n}\n\n/**\n * Split text into overlapping chunks.\n *\n * Splits on paragraph boundaries when possible, falling back to sentence\n * boundaries, then word boundaries. Each chunk overlaps with the previous\n * by `overlap` tokens worth of text.\n */\nexport function chunkText(text: string, config: ChunkingConfig = DEFAULT_CHUNKING_CONFIG): string[] {\n  if (text.length === 0) return [];\n  const totalTokens = estimateTokens(text);\n  if (totalTokens <= config.chunkSize) {\n    return [text];\n  }\n\n  const chunkChars = config.chunkSize * 4;\n  const overlapChars = config.overlap * 4;\n  const chunks: string[] = [];\n  let start = 0;\n\n  while (start < text.length) {\n    let end = Math.min(start + chunkChars, text.length);\n\n    // Try to break at a paragraph boundary\n    if (end < text.length) {\n      const paraBreak = text.lastIndexOf('\\n\\n', end);\n      if (paraBreak > start + chunkChars / 2) {\n        end = paraBreak;\n      } else {\n        // Try sentence boundary\n        const sentenceBreak = text.lastIndexOf('. ', end);\n        if (sentenceBreak > start + chunkChars / 2) {\n          end = sentenceBreak + 1;\n        } else {\n          // Try word boundary\n          const wordBreak = text.lastIndexOf(' ', end);\n          if (wordBreak > start + chunkChars / 2) {\n            end = wordBreak;\n          }\n        }\n      }\n    }\n\n    chunks.push(text.slice(start, end).trim());\n    const nextStart = end - overlapChars;\n    start = nextStart > start ? nextStart : end;\n    if (start >= text.length) break;\n  }\n\n  return chunks.filter(c => c.length > 0);\n}\n"],"mappings":";;;;;;;;;;;AAwBA,SAAS,iBAAiB,GAAa,GAAqB;AAC1D,MAAI,aAAa;AACjB,MAAI,QAAQ;AACZ,MAAI,QAAQ;AACZ,WAAS,IAAI,GAAG,IAAI,EAAE,QAAQ,KAAK;AACjC,kBAAc,EAAE,CAAC,IAAI,EAAE,CAAC;AACxB,aAAS,EAAE,CAAC,IAAI,EAAE,CAAC;AACnB,aAAS,EAAE,CAAC,IAAI,EAAE,CAAC;AAAA,EACrB;AACA,QAAM,QAAQ,KAAK,KAAK,KAAK,IAAI,KAAK,KAAK,KAAK;AAChD,SAAO,UAAU,IAAI,IAAI,aAAa;AACxC;AAEO,IAAM,oBAAN,MAA+C;AAAA,EAC5C,YAA2B,CAAC;AAAA,EAC5B,cAA6B,CAAC;AAAA,EAC9B,YAAY;AAAA,EAEpB,MAAM,UAAyB;AAC7B,SAAK,YAAY;AAAA,EACnB;AAAA,EAEA,MAAM,aAA4B;AAChC,SAAK,YAAY;AAAA,EACnB;AAAA,EAEA,MAAM,WAA0B;AAC9B,SAAK,YAAY,CAAC;AAClB,SAAK,cAAc,CAAC;AAAA,EACtB;AAAA,EAEA,cAAuB;AACrB,WAAO,KAAK;AAAA,EACd;AAAA,EAEA,MAAM,sBAAsB,YAAwB,QAA0B,iBAAyB,aAAsC;AAE3I,SAAK,YAAY,KAAK,UAAU,OAAO,OAAK,EAAE,QAAQ,eAAe,OAAO,UAAU,CAAC;AAEvF,eAAW,SAAS,QAAQ;AAC1B,WAAK,UAAU,KAAK;AAAA,QAClB,IAAI,GAAG,UAAU,IAAI,MAAM,UAAU;AAAA,QACrC,QAAQ,MAAM;AAAA,QACd,SAAS;AAAA,UACP,YAAY,OAAO,UAAU;AAAA,UAC7B,YAAY,MAAM;AAAA,UAClB,MAAM,MAAM;AAAA,UACZ;AAAA,UACA;AAAA,QACF;AAAA,MACF,CAAC;AAAA,IACH;AAAA,EACF;AAAA,EAEA,MAAM,uBACJ,cACA,WACA,SACe;AACf,SAAK,cAAc,KAAK,YAAY,OAAO,OAAK,EAAE,OAAO,OAAO,YAAY,CAAC;AAC7E,SAAK,YAAY,KAAK;AAAA,MACpB,IAAI,OAAO,YAAY;AAAA,MACvB,QAAQ;AAAA,MACR,SAAS;AAAA,QACP,cAAc,OAAO,QAAQ,YAAY;AAAA,QACzC,YAAY,OAAO,QAAQ,UAAU;AAAA,QACrC,YAAY,QAAQ;AAAA,QACpB,aAAa,QAAQ;AAAA,QACrB,MAAM,QAAQ;AAAA,MAChB;AAAA,IACF,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,sBAAsB,YAAuC;AACjE,SAAK,YAAY,KAAK,UAAU,OAAO,OAAK,EAAE,QAAQ,eAAe,OAAO,UAAU,CAAC;AAAA,EACzF;AAAA,EAEA,MAAM,uBAAuB,cAA2C;AACtE,SAAK,cAAc,KAAK,YAAY,OAAO,OAAK,EAAE,OAAO,OAAO,YAAY,CAAC;AAAA,EAC/E;AAAA,EAEA,MAAM,mCAAmC,YAAuC;AAC9E,SAAK,cAAc,KAAK,YAAY,OAAO,OAAK,EAAE,QAAQ,eAAe,OAAO,UAAU,CAAC;AAAA,EAC7F;AAAA,EAEA,MAAM,QAAyB;AAC7B,WAAO,KAAK,UAAU,SAAS,KAAK,YAAY;AAAA,EAClD;AAAA,EAEA,MAAM,wBAAkE;AACtE,UAAM,YAAY,oBAAI,IAAgC;AACtD,eAAW,KAAK,KAAK,WAAW;AAC9B,UAAI,CAAC,UAAU,IAAI,EAAE,QAAQ,UAAU,GAAG;AACxC,kBAAU,IAAI,EAAE,QAAQ,YAAY,EAAE,QAAQ,eAAe;AAAA,MAC/D;AAAA,IACF;AACA,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,oBAA0C;AAC9C,UAAM,MAAM,oBAAI,IAAY;AAC5B,eAAW,KAAK,KAAK,aAAa;AAChC,UAAI,EAAE,QAAQ,aAAc,KAAI,IAAI,EAAE,QAAQ,YAAY;AAAA,IAC5D;AACA,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,gBAAgB,WAAqB,MAAoD;AAC7F,WAAO,KAAK,OAAO,KAAK,WAAW,WAAW,IAAI;AAAA,EACpD;AAAA,EAEA,MAAM,kBAAkB,WAAqB,MAAoD;AAC/F,WAAO,KAAK,OAAO,KAAK,aAAa,WAAW,IAAI;AAAA,EACtD;AAAA,EAEA,MAAM,iBAAiB,YAAwB,MAAoD;AACjG,UAAM,MAAM,OAAO,UAAU;AAC7B,UAAM,cAAc,KAAK,UAAU,OAAO,OAAK,EAAE,QAAQ,eAAe,GAAG;AAC3E,QAAI,YAAY,WAAW,EAAG,QAAO,CAAC;AAGtC,UAAM,SAAkC,EAAE,GAAG,KAAK,QAAQ,mBAAmB,WAAW;AAKxF,UAAM,iBAAiB,oBAAI,IAA6C;AACxE,eAAW,QAAQ,KAAK,WAAW;AACjC,UAAI,CAAC,KAAK,aAAa,MAAM,MAAM,EAAG;AACtC,UAAI,OAAO;AACX,iBAAW,KAAK,aAAa;AAC3B,cAAM,QAAQ,iBAAiB,EAAE,QAAQ,KAAK,MAAM;AACpD,YAAI,QAAQ,KAAM,QAAO;AAAA,MAC3B;AACA,YAAM,OAAO,eAAe,IAAI,KAAK,QAAQ,UAAU;AACvD,UAAI,CAAC,QAAQ,OAAO,KAAK,OAAO;AAC9B,uBAAe,IAAI,KAAK,QAAQ,YAAY,EAAE,GAAG,MAAM,OAAO,KAAK,CAAC;AAAA,MACtE;AAAA,IACF;AAEA,QAAI,SAAS,CAAC,GAAG,eAAe,OAAO,CAAC;AACxC,QAAI,KAAK,mBAAmB,QAAW;AACrC,YAAM,YAAY,KAAK;AACvB,eAAS,OAAO,OAAO,OAAK,EAAE,SAAS,SAAS;AAAA,IAClD;AACA,WAAO,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AACvC,WAAO,OAAO,MAAM,GAAG,KAAK,KAAK,EAAE,IAAI,OAAK,KAAK,SAAS,CAAC,CAAC;AAAA,EAC9D;AAAA,EAEQ,aAAa,GAAgB,QAA0C;AAC7E,QAAI,CAAC,OAAQ,QAAO;AACpB,UAAM,IAAI;AACV,QAAI,EAAE,cAAc,EAAE,QAAQ,eAAe,OAAO,EAAE,UAAU,EAAG,QAAO;AAC1E,QAAI,EAAE,qBAAqB,EAAE,QAAQ,eAAe,OAAO,EAAE,iBAAiB,EAAG,QAAO;AACxF,QAAI,EAAE,cAAc,EAAE,QAAQ,eAAe,EAAE,WAAY,QAAO;AAClE,QAAI,EAAE,eAAe,EAAE,YAAY,SAAS,GAAG;AAC7C,YAAM,SAAS,EAAE,QAAQ,eAAe,CAAC;AACzC,UAAI,CAAC,EAAE,YAAY,KAAK,OAAK,OAAO,SAAS,CAAC,CAAC,EAAG,QAAO;AAAA,IAC3D;AACA,QAAI,EAAE,sBAAsB,EAAE,mBAAmB,SAAS,GAAG;AAC3D,YAAM,SAAS,EAAE,QAAQ,eAAe,CAAC;AACzC,UAAI,EAAE,mBAAmB,KAAK,OAAK,OAAO,SAAS,CAAC,CAAC,EAAG,QAAO;AAAA,IACjE;AACA,WAAO;AAAA,EACT;AAAA,EAEQ,OAAO,QAAuB,WAAqB,MAA2C;AACpG,UAAM,WAAW,OAAO,OAAO,OAAK,KAAK,aAAa,GAAG,KAAK,MAAM,CAAC;AAErE,UAAM,SAAS,SAAS,IAAI,QAAM;AAAA,MAChC,GAAG;AAAA,MACH,OAAO,iBAAiB,WAAW,EAAE,MAAM;AAAA,IAC7C,EAAE;AAEF,WAAO,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AAEvC,QAAI,KAAK,mBAAmB,QAAW;AACrC,YAAM,YAAY,KAAK;AACvB,aAAO,OACJ,OAAO,OAAK,EAAE,SAAS,SAAS,EAChC,MAAM,GAAG,KAAK,KAAK,EACnB,IAAI,OAAK,KAAK,SAAS,CAAC,CAAC;AAAA,IAC9B;AAEA,WAAO,OAAO,MAAM,GAAG,KAAK,KAAK,EAAE,IAAI,OAAK,KAAK,SAAS,CAAC,CAAC;AAAA,EAC9D;AAAA,EAEQ,SAAS,GAAwD;AACvE,WAAO;AAAA,MACL,IAAI,EAAE;AAAA,MACN,OAAO,EAAE;AAAA,MACT,YAAY,EAAE,QAAQ;AAAA,MACtB,cAAc,EAAE,QAAQ;AAAA,MACxB,MAAM,EAAE,QAAQ;AAAA,MAChB,aAAa,EAAE,QAAQ;AAAA,IACzB;AAAA,EACF;AACF;;;AC7MA,eAAsB,kBAAkB,QAAiD;AACvF,MAAI;AAEJ,MAAI,OAAO,SAAS,UAAU;AAC5B,UAAM,EAAE,mBAAAA,mBAAkB,IAAI,MAAM,OAAO,sBAAU;AACrD,YAAQ,IAAIA,mBAAkB;AAAA,MAC5B,MAAM,OAAO,QAAQ;AAAA,MACrB,MAAM,OAAO,QAAQ;AAAA,MACrB,YAAY,OAAO;AAAA,IACrB,CAAC;AAAA,EACH,OAAO;AACL,YAAQ,IAAI,kBAAkB;AAAA,EAChC;AAEA,QAAM,MAAM,QAAQ;AACpB,SAAO;AACT;;;AClBA,eAAsB,wBAAwB,QAAqD;AACjG,MAAI,OAAO,SAAS,UAAU;AAC5B,UAAM,EAAE,yBAAAC,yBAAwB,IAAI,MAAM,OAAO,sBAAU;AAC3D,QAAI,CAAC,OAAO,OAAQ,OAAM,IAAI,MAAM,kDAAkD;AACtF,WAAO,IAAIA,yBAAwB;AAAA,MACjC,QAAQ,OAAO;AAAA,MACf,OAAO,OAAO;AAAA,MACd,UAAU,OAAO;AAAA,IACnB,CAAC;AAAA,EACH;AAEA,MAAI,OAAO,SAAS,UAAU;AAC5B,UAAM,EAAE,yBAAAC,yBAAwB,IAAI,MAAM,OAAO,sBAAU;AAC3D,WAAO,IAAIA,yBAAwB;AAAA,MACjC,OAAO,OAAO;AAAA,MACd,SAAS,OAAO;AAAA,IAClB,CAAC;AAAA,EACH;AAEA,QAAM,IAAI,MAAM,oCAAoC,OAAO,IAAI,EAAE;AACnE;;;ACtBO,IAAM,0BAA0C;AAAA,EACrD,WAAW;AAAA,EACX,SAAS;AACX;AAKA,SAAS,eAAe,MAAsB;AAC5C,SAAO,KAAK,KAAK,KAAK,SAAS,CAAC;AAClC;AASO,SAAS,UAAU,MAAc,SAAyB,yBAAmC;AAClG,MAAI,KAAK,WAAW,EAAG,QAAO,CAAC;AAC/B,QAAM,cAAc,eAAe,IAAI;AACvC,MAAI,eAAe,OAAO,WAAW;AACnC,WAAO,CAAC,IAAI;AAAA,EACd;AAEA,QAAM,aAAa,OAAO,YAAY;AACtC,QAAM,eAAe,OAAO,UAAU;AACtC,QAAM,SAAmB,CAAC;AAC1B,MAAI,QAAQ;AAEZ,SAAO,QAAQ,KAAK,QAAQ;AAC1B,QAAI,MAAM,KAAK,IAAI,QAAQ,YAAY,KAAK,MAAM;AAGlD,QAAI,MAAM,KAAK,QAAQ;AACrB,YAAM,YAAY,KAAK,YAAY,QAAQ,GAAG;AAC9C,UAAI,YAAY,QAAQ,aAAa,GAAG;AACtC,cAAM;AAAA,MACR,OAAO;AAEL,cAAM,gBAAgB,KAAK,YAAY,MAAM,GAAG;AAChD,YAAI,gBAAgB,QAAQ,aAAa,GAAG;AAC1C,gBAAM,gBAAgB;AAAA,QACxB,OAAO;AAEL,gBAAM,YAAY,KAAK,YAAY,KAAK,GAAG;AAC3C,cAAI,YAAY,QAAQ,aAAa,GAAG;AACtC,kBAAM;AAAA,UACR;AAAA,QACF;AAAA,MACF;AAAA,IACF;AAEA,WAAO,KAAK,KAAK,MAAM,OAAO,GAAG,EAAE,KAAK,CAAC;AACzC,UAAM,YAAY,MAAM;AACxB,YAAQ,YAAY,QAAQ,YAAY;AACxC,QAAI,SAAS,KAAK,OAAQ;AAAA,EAC5B;AAEA,SAAO,OAAO,OAAO,OAAK,EAAE,SAAS,CAAC;AACxC;","names":["QdrantVectorStore","VoyageEmbeddingProvider","OllamaEmbeddingProvider"]}
+{"version":3,"sources":["../src/store/memory.ts","../src/store/factory.ts","../src/embedding/factory.ts","../src/chunking.ts"],"sourcesContent":["/**\n * In-Memory VectorStore Implementation\n *\n * For testing and development without a running Qdrant instance.\n * Uses brute-force cosine similarity search.\n */\n\nimport type { ResourceId, AnnotationId } from '@semiont/core';\nimport type { VectorStore, EmbeddingChunk, AnnotationPayload, VectorSearchResult, SearchOptions } from './interface';\n\ninterface StoredPoint {\n  id: string;\n  vector: number[];\n  payload: {\n    resourceId: string;\n    annotationId?: string;\n    chunkIndex?: number;\n    text: string;\n    contentChecksum?: string;\n    motivation?: string;\n    entityTypes?: string[];\n  };\n}\n\nfunction cosineSimilarity(a: number[], b: number[]): number {\n  let dotProduct = 0;\n  let normA = 0;\n  let normB = 0;\n  for (let i = 0; i < a.length; i++) {\n    dotProduct += a[i] * b[i];\n    normA += a[i] * a[i];\n    normB += b[i] * b[i];\n  }\n  const denom = Math.sqrt(normA) * Math.sqrt(normB);\n  return denom === 0 ? 0 : dotProduct / denom;\n}\n\nexport class MemoryVectorStore implements VectorStore {\n  private resources: StoredPoint[] = [];\n  private annotations: StoredPoint[] = [];\n  private connected = false;\n\n  async connect(): Promise<void> {\n    this.connected = true;\n  }\n\n  async disconnect(): Promise<void> {\n    this.connected = false;\n  }\n\n  async clearAll(): Promise<void> {\n    this.resources = [];\n    this.annotations = [];\n  }\n\n  isConnected(): boolean {\n    return this.connected;\n  }\n\n  async upsertResourceVectors(resourceId: ResourceId, chunks: EmbeddingChunk[], contentChecksum: string, entityTypes: string[]): Promise<void> {\n    // Remove existing vectors for this resource\n    this.resources = this.resources.filter(p => p.payload.resourceId !== String(resourceId));\n\n    for (const chunk of chunks) {\n      this.resources.push({\n        id: `${resourceId}-${chunk.chunkIndex}`,\n        vector: chunk.embedding,\n        payload: {\n          resourceId: String(resourceId),\n          chunkIndex: chunk.chunkIndex,\n          text: chunk.text,\n          contentChecksum,\n          entityTypes,\n        },\n      });\n    }\n  }\n\n  async upsertAnnotationVector(\n    annotationId: AnnotationId,\n    embedding: number[],\n    payload: AnnotationPayload\n  ): Promise<void> {\n    this.annotations = this.annotations.filter(p => p.id !== String(annotationId));\n    this.annotations.push({\n      id: String(annotationId),\n      vector: embedding,\n      payload: {\n        annotationId: String(payload.annotationId),\n        resourceId: String(payload.resourceId),\n        motivation: payload.motivation,\n        entityTypes: payload.entityTypes,\n        text: payload.exactText,\n      },\n    });\n  }\n\n  async deleteResourceVectors(resourceId: ResourceId): Promise<void> {\n    this.resources = this.resources.filter(p => p.payload.resourceId !== String(resourceId));\n  }\n\n  async deleteAnnotationVector(annotationId: AnnotationId): Promise<void> {\n    this.annotations = this.annotations.filter(p => p.id !== String(annotationId));\n  }\n\n  async deleteAnnotationVectorsForResource(resourceId: ResourceId): Promise<void> {\n    this.annotations = this.annotations.filter(p => p.payload.resourceId !== String(resourceId));\n  }\n\n  async count(): Promise<number> {\n    return this.resources.length + this.annotations.length;\n  }\n\n  async updateResourceEntityTypes(resourceId: ResourceId, entityTypes: string[]): Promise<void> {\n    for (const p of this.resources) {\n      if (p.payload.resourceId === String(resourceId)) {\n        p.payload.entityTypes = entityTypes;\n      }\n    }\n  }\n\n  async listResourceStamps(): Promise<Map<string, { contentChecksum: string | undefined; entityTypes: string[] }>> {\n    const stamps = new Map<string, { contentChecksum: string | undefined; entityTypes: string[] }>();\n    for (const p of this.resources) {\n      if (!stamps.has(p.payload.resourceId)) {\n        stamps.set(p.payload.resourceId, {\n          contentChecksum: p.payload.contentChecksum,\n          entityTypes: p.payload.entityTypes ?? [],\n        });\n      }\n    }\n    return stamps;\n  }\n\n  async listAnnotationIds(): Promise<Set<string>> {\n    const ids = new Set<string>();\n    for (const p of this.annotations) {\n      if (p.payload.annotationId) ids.add(p.payload.annotationId);\n    }\n    return ids;\n  }\n\n  async searchResources(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    return this.search(this.resources, embedding, opts);\n  }\n\n  async searchAnnotations(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    return this.search(this.annotations, embedding, opts);\n  }\n\n  async searchByResource(resourceId: ResourceId, opts: SearchOptions): Promise<VectorSearchResult[]> {\n    const rid = String(resourceId);\n    const queryPoints = this.resources.filter(p => p.payload.resourceId === rid);\n    if (queryPoints.length === 0) return [];\n\n    // Self-exclude the source; carry the caller's filter (e.g. excludeEntityTypes).\n    const filter: SearchOptions['filter'] = { ...opts.filter, excludeResourceId: resourceId };\n\n    // Per-chunk max-sim, merged by resource: each candidate point scores as the\n    // best similarity to any of the source's query chunks; keep, per target\n    // resource, the single best-matching point (its score and its text).\n    const bestByResource = new Map<string, StoredPoint & { score: number }>();\n    for (const cand of this.resources) {\n      if (!this.passesFilter(cand, filter)) continue;\n      let best = -Infinity;\n      for (const q of queryPoints) {\n        const score = cosineSimilarity(q.vector, cand.vector);\n        if (score > best) best = score;\n      }\n      const prev = bestByResource.get(cand.payload.resourceId);\n      if (!prev || best > prev.score) {\n        bestByResource.set(cand.payload.resourceId, { ...cand, score: best });\n      }\n    }\n\n    let merged = [...bestByResource.values()];\n    if (opts.scoreThreshold !== undefined) {\n      const threshold = opts.scoreThreshold;\n      merged = merged.filter(s => s.score >= threshold);\n    }\n    merged.sort((a, b) => b.score - a.score);\n    return merged.slice(0, opts.limit).map(s => this.toResult(s));\n  }\n\n  private passesFilter(p: StoredPoint, filter: SearchOptions['filter']): boolean {\n    if (!filter) return true;\n    const f = filter;\n    if (f.resourceId && p.payload.resourceId !== String(f.resourceId)) return false;\n    if (f.excludeResourceId && p.payload.resourceId === String(f.excludeResourceId)) return false;\n    if (f.motivation && p.payload.motivation !== f.motivation) return false;\n    if (f.entityTypes && f.entityTypes.length > 0) {\n      const pTypes = p.payload.entityTypes ?? [];\n      if (!f.entityTypes.some(t => pTypes.includes(t))) return false;\n    }\n    if (f.excludeEntityTypes && f.excludeEntityTypes.length > 0) {\n      const pTypes = p.payload.entityTypes ?? [];\n      if (f.excludeEntityTypes.some(t => pTypes.includes(t))) return false;\n    }\n    return true;\n  }\n\n  private search(points: StoredPoint[], embedding: number[], opts: SearchOptions): VectorSearchResult[] {\n    const filtered = points.filter(p => this.passesFilter(p, opts.filter));\n\n    const scored = filtered.map(p => ({\n      ...p,\n      score: cosineSimilarity(embedding, p.vector),\n    }));\n\n    scored.sort((a, b) => b.score - a.score);\n\n    if (opts.scoreThreshold !== undefined) {\n      const threshold = opts.scoreThreshold;\n      return scored\n        .filter(s => s.score >= threshold)\n        .slice(0, opts.limit)\n        .map(s => this.toResult(s));\n    }\n\n    return scored.slice(0, opts.limit).map(s => this.toResult(s));\n  }\n\n  private toResult(s: StoredPoint & { score: number }): VectorSearchResult {\n    return {\n      id: s.id,\n      score: s.score,\n      resourceId: s.payload.resourceId as ResourceId,\n      annotationId: s.payload.annotationId as AnnotationId | undefined,\n      text: s.payload.text,\n      entityTypes: s.payload.entityTypes,\n    };\n  }\n}\n","/**\n * VectorStore Factory\n *\n * Creates a connected VectorStore instance based on configuration.\n */\n\nimport type { VectorStore } from './interface';\nimport { MemoryVectorStore } from './memory';\n\nexport interface VectorStoreConfig {\n  type: 'qdrant' | 'memory';\n  host?: string;\n  port?: number;\n  dimensions: number;\n}\n\nexport async function createVectorStore(config: VectorStoreConfig): Promise<VectorStore> {\n  let store: VectorStore;\n\n  if (config.type === 'qdrant') {\n    const { QdrantVectorStore } = await import('./qdrant');\n    store = new QdrantVectorStore({\n      host: config.host ?? 'localhost',\n      port: config.port ?? 6333,\n      dimensions: config.dimensions,\n    });\n  } else {\n    store = new MemoryVectorStore();\n  }\n\n  await store.connect();\n  return store;\n}\n","/**\n * EmbeddingProvider Factory\n */\n\nimport type { EmbeddingProvider } from './interface';\n\nexport interface EmbeddingConfig {\n  type: 'voyage' | 'ollama';\n  model: string;\n  apiKey?: string;\n  baseURL?: string;\n  endpoint?: string;\n}\n\nexport async function createEmbeddingProvider(config: EmbeddingConfig): Promise<EmbeddingProvider> {\n  if (config.type === 'voyage') {\n    const { VoyageEmbeddingProvider } = await import('./voyage');\n    if (!config.apiKey) throw new Error('apiKey is required for Voyage embedding provider');\n    return new VoyageEmbeddingProvider({\n      apiKey: config.apiKey,\n      model: config.model,\n      endpoint: config.endpoint,\n    });\n  }\n\n  if (config.type === 'ollama') {\n    const { OllamaEmbeddingProvider } = await import('./ollama');\n    return new OllamaEmbeddingProvider({\n      model: config.model,\n      baseURL: config.baseURL,\n    });\n  }\n\n  throw new Error(`Unknown embedding provider type: ${config.type}`);\n}\n","/**\n * Text Chunking Utilities\n *\n * Splits long text into overlapping chunks for embedding.\n * Each chunk is a passage that fits within the embedding model's context window.\n */\n\nexport interface ChunkingConfig {\n  chunkSize: number;   // approximate tokens per chunk\n  overlap: number;     // tokens of overlap between adjacent chunks\n}\n\nexport const DEFAULT_CHUNKING_CONFIG: ChunkingConfig = {\n  chunkSize: 512,\n  overlap: 64,\n};\n\n/**\n * Rough token count estimate: ~4 characters per token for English text.\n */\nfunction estimateTokens(text: string): number {\n  return Math.ceil(text.length / 4);\n}\n\n/**\n * Split text into overlapping chunks.\n *\n * Splits on paragraph boundaries when possible, falling back to sentence\n * boundaries, then word boundaries. Each chunk overlaps with the previous\n * by `overlap` tokens worth of text.\n */\nexport function chunkText(text: string, config: ChunkingConfig = DEFAULT_CHUNKING_CONFIG): string[] {\n  if (text.length === 0) return [];\n  const totalTokens = estimateTokens(text);\n  if (totalTokens <= config.chunkSize) {\n    return [text];\n  }\n\n  const chunkChars = config.chunkSize * 4;\n  const overlapChars = config.overlap * 4;\n  const chunks: string[] = [];\n  let start = 0;\n\n  while (start < text.length) {\n    let end = Math.min(start + chunkChars, text.length);\n\n    // Try to break at a paragraph boundary\n    if (end < text.length) {\n      const paraBreak = text.lastIndexOf('\\n\\n', end);\n      if (paraBreak > start + chunkChars / 2) {\n        end = paraBreak;\n      } else {\n        // Try sentence boundary\n        const sentenceBreak = text.lastIndexOf('. ', end);\n        if (sentenceBreak > start + chunkChars / 2) {\n          end = sentenceBreak + 1;\n        } else {\n          // Try word boundary\n          const wordBreak = text.lastIndexOf(' ', end);\n          if (wordBreak > start + chunkChars / 2) {\n            end = wordBreak;\n          }\n        }\n      }\n    }\n\n    chunks.push(text.slice(start, end).trim());\n    const nextStart = end - overlapChars;\n    start = nextStart > start ? nextStart : end;\n    if (start >= text.length) break;\n  }\n\n  return chunks.filter(c => c.length > 0);\n}\n"],"mappings":";;;;;;;;;;;AAwBA,SAAS,iBAAiB,GAAa,GAAqB;AAC1D,MAAI,aAAa;AACjB,MAAI,QAAQ;AACZ,MAAI,QAAQ;AACZ,WAAS,IAAI,GAAG,IAAI,EAAE,QAAQ,KAAK;AACjC,kBAAc,EAAE,CAAC,IAAI,EAAE,CAAC;AACxB,aAAS,EAAE,CAAC,IAAI,EAAE,CAAC;AACnB,aAAS,EAAE,CAAC,IAAI,EAAE,CAAC;AAAA,EACrB;AACA,QAAM,QAAQ,KAAK,KAAK,KAAK,IAAI,KAAK,KAAK,KAAK;AAChD,SAAO,UAAU,IAAI,IAAI,aAAa;AACxC;AAEO,IAAM,oBAAN,MAA+C;AAAA,EAC5C,YAA2B,CAAC;AAAA,EAC5B,cAA6B,CAAC;AAAA,EAC9B,YAAY;AAAA,EAEpB,MAAM,UAAyB;AAC7B,SAAK,YAAY;AAAA,EACnB;AAAA,EAEA,MAAM,aAA4B;AAChC,SAAK,YAAY;AAAA,EACnB;AAAA,EAEA,MAAM,WAA0B;AAC9B,SAAK,YAAY,CAAC;AAClB,SAAK,cAAc,CAAC;AAAA,EACtB;AAAA,EAEA,cAAuB;AACrB,WAAO,KAAK;AAAA,EACd;AAAA,EAEA,MAAM,sBAAsB,YAAwB,QAA0B,iBAAyB,aAAsC;AAE3I,SAAK,YAAY,KAAK,UAAU,OAAO,OAAK,EAAE,QAAQ,eAAe,OAAO,UAAU,CAAC;AAEvF,eAAW,SAAS,QAAQ;AAC1B,WAAK,UAAU,KAAK;AAAA,QAClB,IAAI,GAAG,UAAU,IAAI,MAAM,UAAU;AAAA,QACrC,QAAQ,MAAM;AAAA,QACd,SAAS;AAAA,UACP,YAAY,OAAO,UAAU;AAAA,UAC7B,YAAY,MAAM;AAAA,UAClB,MAAM,MAAM;AAAA,UACZ;AAAA,UACA;AAAA,QACF;AAAA,MACF,CAAC;AAAA,IACH;AAAA,EACF;AAAA,EAEA,MAAM,uBACJ,cACA,WACA,SACe;AACf,SAAK,cAAc,KAAK,YAAY,OAAO,OAAK,EAAE,OAAO,OAAO,YAAY,CAAC;AAC7E,SAAK,YAAY,KAAK;AAAA,MACpB,IAAI,OAAO,YAAY;AAAA,MACvB,QAAQ;AAAA,MACR,SAAS;AAAA,QACP,cAAc,OAAO,QAAQ,YAAY;AAAA,QACzC,YAAY,OAAO,QAAQ,UAAU;AAAA,QACrC,YAAY,QAAQ;AAAA,QACpB,aAAa,QAAQ;AAAA,QACrB,MAAM,QAAQ;AAAA,MAChB;AAAA,IACF,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,sBAAsB,YAAuC;AACjE,SAAK,YAAY,KAAK,UAAU,OAAO,OAAK,EAAE,QAAQ,eAAe,OAAO,UAAU,CAAC;AAAA,EACzF;AAAA,EAEA,MAAM,uBAAuB,cAA2C;AACtE,SAAK,cAAc,KAAK,YAAY,OAAO,OAAK,EAAE,OAAO,OAAO,YAAY,CAAC;AAAA,EAC/E;AAAA,EAEA,MAAM,mCAAmC,YAAuC;AAC9E,SAAK,cAAc,KAAK,YAAY,OAAO,OAAK,EAAE,QAAQ,eAAe,OAAO,UAAU,CAAC;AAAA,EAC7F;AAAA,EAEA,MAAM,QAAyB;AAC7B,WAAO,KAAK,UAAU,SAAS,KAAK,YAAY;AAAA,EAClD;AAAA,EAEA,MAAM,0BAA0B,YAAwB,aAAsC;AAC5F,eAAW,KAAK,KAAK,WAAW;AAC9B,UAAI,EAAE,QAAQ,eAAe,OAAO,UAAU,GAAG;AAC/C,UAAE,QAAQ,cAAc;AAAA,MAC1B;AAAA,IACF;AAAA,EACF;AAAA,EAEA,MAAM,qBAA2G;AAC/G,UAAM,SAAS,oBAAI,IAA4E;AAC/F,eAAW,KAAK,KAAK,WAAW;AAC9B,UAAI,CAAC,OAAO,IAAI,EAAE,QAAQ,UAAU,GAAG;AACrC,eAAO,IAAI,EAAE,QAAQ,YAAY;AAAA,UAC/B,iBAAiB,EAAE,QAAQ;AAAA,UAC3B,aAAa,EAAE,QAAQ,eAAe,CAAC;AAAA,QACzC,CAAC;AAAA,MACH;AAAA,IACF;AACA,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,oBAA0C;AAC9C,UAAM,MAAM,oBAAI,IAAY;AAC5B,eAAW,KAAK,KAAK,aAAa;AAChC,UAAI,EAAE,QAAQ,aAAc,KAAI,IAAI,EAAE,QAAQ,YAAY;AAAA,IAC5D;AACA,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,gBAAgB,WAAqB,MAAoD;AAC7F,WAAO,KAAK,OAAO,KAAK,WAAW,WAAW,IAAI;AAAA,EACpD;AAAA,EAEA,MAAM,kBAAkB,WAAqB,MAAoD;AAC/F,WAAO,KAAK,OAAO,KAAK,aAAa,WAAW,IAAI;AAAA,EACtD;AAAA,EAEA,MAAM,iBAAiB,YAAwB,MAAoD;AACjG,UAAM,MAAM,OAAO,UAAU;AAC7B,UAAM,cAAc,KAAK,UAAU,OAAO,OAAK,EAAE,QAAQ,eAAe,GAAG;AAC3E,QAAI,YAAY,WAAW,EAAG,QAAO,CAAC;AAGtC,UAAM,SAAkC,EAAE,GAAG,KAAK,QAAQ,mBAAmB,WAAW;AAKxF,UAAM,iBAAiB,oBAAI,IAA6C;AACxE,eAAW,QAAQ,KAAK,WAAW;AACjC,UAAI,CAAC,KAAK,aAAa,MAAM,MAAM,EAAG;AACtC,UAAI,OAAO;AACX,iBAAW,KAAK,aAAa;AAC3B,cAAM,QAAQ,iBAAiB,EAAE,QAAQ,KAAK,MAAM;AACpD,YAAI,QAAQ,KAAM,QAAO;AAAA,MAC3B;AACA,YAAM,OAAO,eAAe,IAAI,KAAK,QAAQ,UAAU;AACvD,UAAI,CAAC,QAAQ,OAAO,KAAK,OAAO;AAC9B,uBAAe,IAAI,KAAK,QAAQ,YAAY,EAAE,GAAG,MAAM,OAAO,KAAK,CAAC;AAAA,MACtE;AAAA,IACF;AAEA,QAAI,SAAS,CAAC,GAAG,eAAe,OAAO,CAAC;AACxC,QAAI,KAAK,mBAAmB,QAAW;AACrC,YAAM,YAAY,KAAK;AACvB,eAAS,OAAO,OAAO,OAAK,EAAE,SAAS,SAAS;AAAA,IAClD;AACA,WAAO,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AACvC,WAAO,OAAO,MAAM,GAAG,KAAK,KAAK,EAAE,IAAI,OAAK,KAAK,SAAS,CAAC,CAAC;AAAA,EAC9D;AAAA,EAEQ,aAAa,GAAgB,QAA0C;AAC7E,QAAI,CAAC,OAAQ,QAAO;AACpB,UAAM,IAAI;AACV,QAAI,EAAE,cAAc,EAAE,QAAQ,eAAe,OAAO,EAAE,UAAU,EAAG,QAAO;AAC1E,QAAI,EAAE,qBAAqB,EAAE,QAAQ,eAAe,OAAO,EAAE,iBAAiB,EAAG,QAAO;AACxF,QAAI,EAAE,cAAc,EAAE,QAAQ,eAAe,EAAE,WAAY,QAAO;AAClE,QAAI,EAAE,eAAe,EAAE,YAAY,SAAS,GAAG;AAC7C,YAAM,SAAS,EAAE,QAAQ,eAAe,CAAC;AACzC,UAAI,CAAC,EAAE,YAAY,KAAK,OAAK,OAAO,SAAS,CAAC,CAAC,EAAG,QAAO;AAAA,IAC3D;AACA,QAAI,EAAE,sBAAsB,EAAE,mBAAmB,SAAS,GAAG;AAC3D,YAAM,SAAS,EAAE,QAAQ,eAAe,CAAC;AACzC,UAAI,EAAE,mBAAmB,KAAK,OAAK,OAAO,SAAS,CAAC,CAAC,EAAG,QAAO;AAAA,IACjE;AACA,WAAO;AAAA,EACT;AAAA,EAEQ,OAAO,QAAuB,WAAqB,MAA2C;AACpG,UAAM,WAAW,OAAO,OAAO,OAAK,KAAK,aAAa,GAAG,KAAK,MAAM,CAAC;AAErE,UAAM,SAAS,SAAS,IAAI,QAAM;AAAA,MAChC,GAAG;AAAA,MACH,OAAO,iBAAiB,WAAW,EAAE,MAAM;AAAA,IAC7C,EAAE;AAEF,WAAO,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AAEvC,QAAI,KAAK,mBAAmB,QAAW;AACrC,YAAM,YAAY,KAAK;AACvB,aAAO,OACJ,OAAO,OAAK,EAAE,SAAS,SAAS,EAChC,MAAM,GAAG,KAAK,KAAK,EACnB,IAAI,OAAK,KAAK,SAAS,CAAC,CAAC;AAAA,IAC9B;AAEA,WAAO,OAAO,MAAM,GAAG,KAAK,KAAK,EAAE,IAAI,OAAK,KAAK,SAAS,CAAC,CAAC;AAAA,EAC9D;AAAA,EAEQ,SAAS,GAAwD;AACvE,WAAO;AAAA,MACL,IAAI,EAAE;AAAA,MACN,OAAO,EAAE;AAAA,MACT,YAAY,EAAE,QAAQ;AAAA,MACtB,cAAc,EAAE,QAAQ;AAAA,MACxB,MAAM,EAAE,QAAQ;AAAA,MAChB,aAAa,EAAE,QAAQ;AAAA,IACzB;AAAA,EACF;AACF;;;ACxNA,eAAsB,kBAAkB,QAAiD;AACvF,MAAI;AAEJ,MAAI,OAAO,SAAS,UAAU;AAC5B,UAAM,EAAE,mBAAAA,mBAAkB,IAAI,MAAM,OAAO,sBAAU;AACrD,YAAQ,IAAIA,mBAAkB;AAAA,MAC5B,MAAM,OAAO,QAAQ;AAAA,MACrB,MAAM,OAAO,QAAQ;AAAA,MACrB,YAAY,OAAO;AAAA,IACrB,CAAC;AAAA,EACH,OAAO;AACL,YAAQ,IAAI,kBAAkB;AAAA,EAChC;AAEA,QAAM,MAAM,QAAQ;AACpB,SAAO;AACT;;;AClBA,eAAsB,wBAAwB,QAAqD;AACjG,MAAI,OAAO,SAAS,UAAU;AAC5B,UAAM,EAAE,yBAAAC,yBAAwB,IAAI,MAAM,OAAO,sBAAU;AAC3D,QAAI,CAAC,OAAO,OAAQ,OAAM,IAAI,MAAM,kDAAkD;AACtF,WAAO,IAAIA,yBAAwB;AAAA,MACjC,QAAQ,OAAO;AAAA,MACf,OAAO,OAAO;AAAA,MACd,UAAU,OAAO;AAAA,IACnB,CAAC;AAAA,EACH;AAEA,MAAI,OAAO,SAAS,UAAU;AAC5B,UAAM,EAAE,yBAAAC,yBAAwB,IAAI,MAAM,OAAO,sBAAU;AAC3D,WAAO,IAAIA,yBAAwB;AAAA,MACjC,OAAO,OAAO;AAAA,MACd,SAAS,OAAO;AAAA,IAClB,CAAC;AAAA,EACH;AAEA,QAAM,IAAI,MAAM,oCAAoC,OAAO,IAAI,EAAE;AACnE;;;ACtBO,IAAM,0BAA0C;AAAA,EACrD,WAAW;AAAA,EACX,SAAS;AACX;AAKA,SAAS,eAAe,MAAsB;AAC5C,SAAO,KAAK,KAAK,KAAK,SAAS,CAAC;AAClC;AASO,SAAS,UAAU,MAAc,SAAyB,yBAAmC;AAClG,MAAI,KAAK,WAAW,EAAG,QAAO,CAAC;AAC/B,QAAM,cAAc,eAAe,IAAI;AACvC,MAAI,eAAe,OAAO,WAAW;AACnC,WAAO,CAAC,IAAI;AAAA,EACd;AAEA,QAAM,aAAa,OAAO,YAAY;AACtC,QAAM,eAAe,OAAO,UAAU;AACtC,QAAM,SAAmB,CAAC;AAC1B,MAAI,QAAQ;AAEZ,SAAO,QAAQ,KAAK,QAAQ;AAC1B,QAAI,MAAM,KAAK,IAAI,QAAQ,YAAY,KAAK,MAAM;AAGlD,QAAI,MAAM,KAAK,QAAQ;AACrB,YAAM,YAAY,KAAK,YAAY,QAAQ,GAAG;AAC9C,UAAI,YAAY,QAAQ,aAAa,GAAG;AACtC,cAAM;AAAA,MACR,OAAO;AAEL,cAAM,gBAAgB,KAAK,YAAY,MAAM,GAAG;AAChD,YAAI,gBAAgB,QAAQ,aAAa,GAAG;AAC1C,gBAAM,gBAAgB;AAAA,QACxB,OAAO;AAEL,gBAAM,YAAY,KAAK,YAAY,KAAK,GAAG;AAC3C,cAAI,YAAY,QAAQ,aAAa,GAAG;AACtC,kBAAM;AAAA,UACR;AAAA,QACF;AAAA,MACF;AAAA,IACF;AAEA,WAAO,KAAK,KAAK,MAAM,OAAO,GAAG,EAAE,KAAK,CAAC;AACzC,UAAM,YAAY,MAAM;AACxB,YAAQ,YAAY,QAAQ,YAAY;AACxC,QAAI,SAAS,KAAK,OAAQ;AAAA,EAC5B;AAEA,SAAO,OAAO,OAAO,OAAK,EAAE,SAAS,CAAC;AACxC;","names":["QdrantVectorStore","VoyageEmbeddingProvider","OllamaEmbeddingProvider"]}

package/dist/qdrant-A765QRQF.js

@@ -0,0 +1,7 @@
+import {
+  QdrantVectorStore
+} from "./chunk-VFNOQC4M.js";
+export {
+  QdrantVectorStore
+};
+//# sourceMappingURL=qdrant-A765QRQF.js.map

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@semiont/vectors",
-  "version": "0.5.11",
+  "version": "0.5.13",
   "engines": {
     "node": ">=24.0.0"
   },
@@ -25,7 +25,7 @@
   },
   "dependencies": {
     "@qdrant/js-client-rest": "^1.18.0",
-    "@semiont/core": "0.5.11"
+    "@semiont/core": "0.5.13"
   },
   "devDependencies": {
     "@vitest/coverage-v8": "^4.1.8",
@@ -33,7 +33,7 @@
     "rollup-plugin-dts": "^6.4.1",
     "tsup": "^8.5.1",
     "typescript": "^6.0.2",
-    "vitest": "^4.1.8"
+    "vitest": "^4.1.10"
   },
   "files": [
     "dist",

package/dist/chunk-TYDOHCBS.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/store/qdrant.ts"],"sourcesContent":["/**\n * Qdrant VectorStore Implementation\n *\n * Uses the Qdrant REST API via @qdrant/js-client-rest.\n * Manages two collections: 'resources' and 'annotations'.\n */\n\nimport { createHash } from 'crypto';\nimport type { QdrantClient, Schemas } from '@qdrant/js-client-rest';\nimport type { ResourceId, AnnotationId } from '@semiont/core';\nimport type { VectorStore, EmbeddingChunk, AnnotationPayload, VectorSearchResult, SearchOptions } from './interface';\n\n/**\n * Generate a deterministic UUID v5-style ID from an arbitrary string.\n * Qdrant requires point IDs to be UUIDs or unsigned integers.\n */\nfunction toQdrantId(input: string): string {\n  const hex = createHash('md5').update(input).digest('hex');\n  return `${hex.slice(0, 8)}-${hex.slice(8, 12)}-${hex.slice(12, 16)}-${hex.slice(16, 20)}-${hex.slice(20, 32)}`;\n}\n\nexport interface QdrantConfig {\n  host: string;\n  port: number;\n  dimensions: number;\n}\n\nexport class QdrantVectorStore implements VectorStore {\n  private client: QdrantClient | null = null;\n  private config: QdrantConfig;\n\n  constructor(config: QdrantConfig) {\n    this.config = config;\n  }\n\n  private get qdrant(): QdrantClient {\n    if (!this.client) throw new Error('QdrantVectorStore is not connected');\n    return this.client;\n  }\n\n  async connect(): Promise<void> {\n    const { QdrantClient } = await import('@qdrant/js-client-rest');\n    this.client = new QdrantClient({\n      host: this.config.host,\n      port: this.config.port,\n    });\n\n    // Ensure collections exist\n    await this.ensureCollection('resources', this.config.dimensions);\n    await this.ensureCollection('annotations', this.config.dimensions);\n    // Payload indexes so filtered operations scale:\n    //  - entityTypes: the excludeEntityTypes recall filter.\n    //  - resourceId: searchByResource's by-resource scroll + self-exclusion, and\n    //    the per-resource delete paths (deleteResourceVectors /\n    //    deleteAnnotationVectorsForResource).\n    await this.ensurePayloadIndex('resources', 'entityTypes');\n    await this.ensurePayloadIndex('resources', 'resourceId');\n    await this.ensurePayloadIndex('annotations', 'resourceId');\n  }\n\n  async disconnect(): Promise<void> {\n    this.client = null;\n  }\n\n  async clearAll(): Promise<void> {\n    try { await this.qdrant.deleteCollection('resources'); } catch { /* may not exist */ }\n    try { await this.qdrant.deleteCollection('annotations'); } catch { /* may not exist */ }\n    await this.ensureCollection('resources', this.config.dimensions);\n    await this.ensureCollection('annotations', this.config.dimensions);\n  }\n\n  isConnected(): boolean {\n    return this.client !== null;\n  }\n\n  private async ensureCollection(name: string, dimensions: number): Promise<void> {\n    try {\n      await this.qdrant.getCollection(name);\n    } catch {\n      await this.qdrant.createCollection(name, {\n        vectors: { size: dimensions, distance: 'Cosine' },\n      });\n    }\n  }\n\n  /**\n   * Idempotently create a keyword payload index. Qdrant accepts a repeat call\n   * for an already-indexed field, so this runs safely on every connect and\n   * back-fills the index on collections created before the field was indexed.\n   */\n  private async ensurePayloadIndex(collection: string, field: string): Promise<void> {\n    try {\n      await this.qdrant.createPayloadIndex(collection, { field_name: field, field_schema: 'keyword' });\n    } catch { /* already indexed, or created concurrently */ }\n  }\n\n  async upsertResourceVectors(resourceId: ResourceId, chunks: EmbeddingChunk[], contentChecksum: string, entityTypes: string[]): Promise<void> {\n    // Replace semantics: purge existing chunks first, or a resource that\n    // shrinks leaves orphan points at the higher chunk indices.\n    await this.deleteResourceVectors(resourceId);\n    if (chunks.length === 0) return;\n\n    const points = chunks.map((chunk) => ({\n      id: toQdrantId(`${resourceId}-${chunk.chunkIndex}`),\n      vector: chunk.embedding,\n      payload: {\n        resourceId: String(resourceId),\n        chunkIndex: chunk.chunkIndex,\n        text: chunk.text,\n        contentChecksum,\n        entityTypes,\n      },\n    }));\n\n    await this.qdrant.upsert('resources', { points });\n  }\n\n  async upsertAnnotationVector(\n    annotationId: AnnotationId,\n    embedding: number[],\n    payload: AnnotationPayload\n  ): Promise<void> {\n    await this.qdrant.upsert('annotations', {\n      points: [{\n        id: toQdrantId(String(annotationId)),\n        vector: embedding,\n        payload: {\n          annotationId: String(payload.annotationId),\n          resourceId: String(payload.resourceId),\n          motivation: payload.motivation,\n          entityTypes: payload.entityTypes,\n          text: payload.exactText,\n        },\n      }],\n    });\n  }\n\n  async deleteResourceVectors(resourceId: ResourceId): Promise<void> {\n    await this.qdrant.delete('resources', {\n      filter: {\n        must: [{ key: 'resourceId', match: { value: String(resourceId) } }],\n      },\n    });\n  }\n\n  async deleteAnnotationVector(annotationId: AnnotationId): Promise<void> {\n    await this.qdrant.delete('annotations', {\n      points: [toQdrantId(String(annotationId))],\n    });\n  }\n\n  async deleteAnnotationVectorsForResource(resourceId: ResourceId): Promise<void> {\n    await this.qdrant.delete('annotations', {\n      filter: {\n        must: [{ key: 'resourceId', match: { value: String(resourceId) } }],\n      },\n    });\n  }\n\n  async count(): Promise<number> {\n    const [resources, annotations] = await Promise.all([\n      this.qdrant.count('resources', { exact: true }),\n      this.qdrant.count('annotations', { exact: true }),\n    ]);\n    return resources.count + annotations.count;\n  }\n\n  async listResourceChecksums(): Promise<Map<string, string | undefined>> {\n    const checksums = new Map<string, string | undefined>();\n    let offset: Schemas['ScrollRequest']['offset'] = undefined;\n    do {\n      const page = await this.qdrant.scroll('resources', {\n        limit: 1000,\n        offset,\n        with_payload: ['resourceId', 'contentChecksum'],\n        with_vector: false,\n      });\n      for (const point of page.points) {\n        const rid = point.payload?.resourceId;\n        if (typeof rid !== 'string' || checksums.has(rid)) continue;\n        const checksum = point.payload?.contentChecksum;\n        checksums.set(rid, typeof checksum === 'string' ? checksum : undefined);\n      }\n      offset = page.next_page_offset ?? undefined;\n    } while (offset !== undefined && offset !== null);\n    return checksums;\n  }\n\n  async listAnnotationIds(): Promise<Set<string>> {\n    return this.scrollPayloadField('annotations', 'annotationId');\n  }\n\n  /** Collect the distinct values of one payload field across a collection. */\n  private async scrollPayloadField(collection: string, field: string): Promise<Set<string>> {\n    const values = new Set<string>();\n    let offset: Schemas['ScrollRequest']['offset'] = undefined;\n    do {\n      const page = await this.qdrant.scroll(collection, {\n        limit: 1000,\n        offset,\n        with_payload: [field],\n        with_vector: false,\n      });\n      for (const point of page.points) {\n        const value = point.payload?.[field];\n        if (typeof value === 'string') values.add(value);\n      }\n      offset = page.next_page_offset ?? undefined;\n    } while (offset !== undefined && offset !== null);\n    return values;\n  }\n\n  async searchResources(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    return this.search('resources', embedding, opts);\n  }\n\n  async searchAnnotations(embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    return this.search('annotations', embedding, opts);\n  }\n\n  async searchByResource(resourceId: ResourceId, opts: SearchOptions): Promise<VectorSearchResult[]> {\n    // Fetch the resource's stored chunk vectors (page through all of them so a\n    // long resource isn't silently truncated).\n    const queryVectors: number[][] = [];\n    let offset: Schemas['ScrollRequest']['offset'] = undefined;\n    do {\n      const page = await this.qdrant.scroll('resources', {\n        filter: { must: [{ key: 'resourceId', match: { value: String(resourceId) } }] },\n        with_vector: true,\n        with_payload: false,\n        limit: 256,\n        offset,\n      });\n      for (const point of page.points) {\n        if (Array.isArray(point.vector)) queryVectors.push(point.vector as number[]);\n      }\n      offset = page.next_page_offset ?? undefined;\n    } while (offset !== undefined && offset !== null);\n\n    if (queryVectors.length === 0) return [];\n\n    // Self-exclude the source; carry the caller's filter (e.g. excludeEntityTypes).\n    const filter = this.buildFilter({ ...opts.filter, excludeResourceId: resourceId });\n\n    // One batched search per query chunk (single round-trip), top-`limit` each;\n    // over-fetch beyond `limit` is unnecessary because the max-sim merge only\n    // needs a target in some chunk's top-K to surface.\n    const searches = queryVectors.map((vector) => ({\n      vector,\n      limit: opts.limit,\n      score_threshold: opts.scoreThreshold,\n      filter: filter ?? undefined,\n      with_payload: true,\n    }));\n    const batches = await this.qdrant.searchBatch('resources', { searches });\n\n    // Max-sim merge: dedup by resourceId, keep the best (query-chunk × target-chunk)\n    // score and the best-matching target chunk's payload.\n    const bestByResource = new Map<string, { id: string; score: number; payload: Record<string, unknown> }>();\n    for (const batch of batches) {\n      for (const r of batch) {\n        const payload = r.payload ?? {};\n        const tid = String(payload.resourceId);\n        const prev = bestByResource.get(tid);\n        if (!prev || r.score > prev.score) {\n          bestByResource.set(tid, { id: String(r.id), score: r.score, payload });\n        }\n      }\n    }\n\n    return [...bestByResource.values()]\n      .sort((a, b) => b.score - a.score)\n      .slice(0, opts.limit)\n      .map((m) => ({\n        id: m.id,\n        score: m.score,\n        resourceId: m.payload.resourceId as ResourceId,\n        annotationId: m.payload.annotationId as AnnotationId | undefined,\n        text: m.payload.text as string,\n        entityTypes: m.payload.entityTypes as string[] | undefined,\n      }));\n  }\n\n  private async search(collection: string, embedding: number[], opts: SearchOptions): Promise<VectorSearchResult[]> {\n    const filter = this.buildFilter(opts.filter);\n\n    const results = await this.qdrant.search(collection, {\n      vector: embedding,\n      limit: opts.limit,\n      score_threshold: opts.scoreThreshold,\n      filter: filter ?? undefined,\n      with_payload: true,\n    });\n\n    return results.map((r) => {\n      const payload = r.payload ?? {};\n      return {\n        id: String(r.id),\n        score: r.score,\n        resourceId: payload.resourceId as ResourceId,\n        annotationId: payload.annotationId as AnnotationId | undefined,\n        text: payload.text as string,\n        entityTypes: payload.entityTypes as string[] | undefined,\n      };\n    });\n  }\n\n  private buildFilter(filter?: SearchOptions['filter']): Schemas['Filter'] | null {\n    if (!filter) return null;\n\n    const must: Schemas['FieldCondition'][] = [];\n\n    if (filter.entityTypes && filter.entityTypes.length > 0) {\n      // any-of: match payloads whose `entityTypes` array contains at least one\n      // of the requested types. Matches the memory store's `some(t => ...)`\n      // semantics; pushing one `must` clause per type would mean all-of.\n      must.push({ key: 'entityTypes', match: { any: filter.entityTypes } });\n    }\n\n    if (filter.resourceId) {\n      must.push({ key: 'resourceId', match: { value: String(filter.resourceId) } });\n    }\n\n    if (filter.motivation) {\n      must.push({ key: 'motivation', match: { value: filter.motivation } });\n    }\n\n    const must_not: Schemas['FieldCondition'][] = [];\n\n    if (filter.excludeResourceId) {\n      must_not.push({ key: 'resourceId', match: { value: String(filter.excludeResourceId) } });\n    }\n\n    if (filter.excludeEntityTypes && filter.excludeEntityTypes.length > 0) {\n      // any-of exclusion: drop points whose entityTypes contain any of these.\n      must_not.push({ key: 'entityTypes', match: { any: filter.excludeEntityTypes } });\n    }\n\n    if (must.length === 0 && must_not.length === 0) return null;\n\n    return {\n      ...(must.length > 0 ? { must } : {}),\n      ...(must_not.length > 0 ? { must_not } : {}),\n    };\n  }\n}\n"],"mappings":";AAOA,SAAS,kBAAkB;AAS3B,SAAS,WAAW,OAAuB;AACzC,QAAM,MAAM,WAAW,KAAK,EAAE,OAAO,KAAK,EAAE,OAAO,KAAK;AACxD,SAAO,GAAG,IAAI,MAAM,GAAG,CAAC,CAAC,IAAI,IAAI,MAAM,GAAG,EAAE,CAAC,IAAI,IAAI,MAAM,IAAI,EAAE,CAAC,IAAI,IAAI,MAAM,IAAI,EAAE,CAAC,IAAI,IAAI,MAAM,IAAI,EAAE,CAAC;AAC9G;AAQO,IAAM,oBAAN,MAA+C;AAAA,EAC5C,SAA8B;AAAA,EAC9B;AAAA,EAER,YAAY,QAAsB;AAChC,SAAK,SAAS;AAAA,EAChB;AAAA,EAEA,IAAY,SAAuB;AACjC,QAAI,CAAC,KAAK,OAAQ,OAAM,IAAI,MAAM,oCAAoC;AACtE,WAAO,KAAK;AAAA,EACd;AAAA,EAEA,MAAM,UAAyB;AAC7B,UAAM,EAAE,aAAa,IAAI,MAAM,OAAO,wBAAwB;AAC9D,SAAK,SAAS,IAAI,aAAa;AAAA,MAC7B,MAAM,KAAK,OAAO;AAAA,MAClB,MAAM,KAAK,OAAO;AAAA,IACpB,CAAC;AAGD,UAAM,KAAK,iBAAiB,aAAa,KAAK,OAAO,UAAU;AAC/D,UAAM,KAAK,iBAAiB,eAAe,KAAK,OAAO,UAAU;AAMjE,UAAM,KAAK,mBAAmB,aAAa,aAAa;AACxD,UAAM,KAAK,mBAAmB,aAAa,YAAY;AACvD,UAAM,KAAK,mBAAmB,eAAe,YAAY;AAAA,EAC3D;AAAA,EAEA,MAAM,aAA4B;AAChC,SAAK,SAAS;AAAA,EAChB;AAAA,EAEA,MAAM,WAA0B;AAC9B,QAAI;AAAE,YAAM,KAAK,OAAO,iBAAiB,WAAW;AAAA,IAAG,QAAQ;AAAA,IAAsB;AACrF,QAAI;AAAE,YAAM,KAAK,OAAO,iBAAiB,aAAa;AAAA,IAAG,QAAQ;AAAA,IAAsB;AACvF,UAAM,KAAK,iBAAiB,aAAa,KAAK,OAAO,UAAU;AAC/D,UAAM,KAAK,iBAAiB,eAAe,KAAK,OAAO,UAAU;AAAA,EACnE;AAAA,EAEA,cAAuB;AACrB,WAAO,KAAK,WAAW;AAAA,EACzB;AAAA,EAEA,MAAc,iBAAiB,MAAc,YAAmC;AAC9E,QAAI;AACF,YAAM,KAAK,OAAO,cAAc,IAAI;AAAA,IACtC,QAAQ;AACN,YAAM,KAAK,OAAO,iBAAiB,MAAM;AAAA,QACvC,SAAS,EAAE,MAAM,YAAY,UAAU,SAAS;AAAA,MAClD,CAAC;AAAA,IACH;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAc,mBAAmB,YAAoB,OAA8B;AACjF,QAAI;AACF,YAAM,KAAK,OAAO,mBAAmB,YAAY,EAAE,YAAY,OAAO,cAAc,UAAU,CAAC;AAAA,IACjG,QAAQ;AAAA,IAAiD;AAAA,EAC3D;AAAA,EAEA,MAAM,sBAAsB,YAAwB,QAA0B,iBAAyB,aAAsC;AAG3I,UAAM,KAAK,sBAAsB,UAAU;AAC3C,QAAI,OAAO,WAAW,EAAG;AAEzB,UAAM,SAAS,OAAO,IAAI,CAAC,WAAW;AAAA,MACpC,IAAI,WAAW,GAAG,UAAU,IAAI,MAAM,UAAU,EAAE;AAAA,MAClD,QAAQ,MAAM;AAAA,MACd,SAAS;AAAA,QACP,YAAY,OAAO,UAAU;AAAA,QAC7B,YAAY,MAAM;AAAA,QAClB,MAAM,MAAM;AAAA,QACZ;AAAA,QACA;AAAA,MACF;AAAA,IACF,EAAE;AAEF,UAAM,KAAK,OAAO,OAAO,aAAa,EAAE,OAAO,CAAC;AAAA,EAClD;AAAA,EAEA,MAAM,uBACJ,cACA,WACA,SACe;AACf,UAAM,KAAK,OAAO,OAAO,eAAe;AAAA,MACtC,QAAQ,CAAC;AAAA,QACP,IAAI,WAAW,OAAO,YAAY,CAAC;AAAA,QACnC,QAAQ;AAAA,QACR,SAAS;AAAA,UACP,cAAc,OAAO,QAAQ,YAAY;AAAA,UACzC,YAAY,OAAO,QAAQ,UAAU;AAAA,UACrC,YAAY,QAAQ;AAAA,UACpB,aAAa,QAAQ;AAAA,UACrB,MAAM,QAAQ;AAAA,QAChB;AAAA,MACF,CAAC;AAAA,IACH,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,sBAAsB,YAAuC;AACjE,UAAM,KAAK,OAAO,OAAO,aAAa;AAAA,MACpC,QAAQ;AAAA,QACN,MAAM,CAAC,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,UAAU,EAAE,EAAE,CAAC;AAAA,MACpE;AAAA,IACF,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,uBAAuB,cAA2C;AACtE,UAAM,KAAK,OAAO,OAAO,eAAe;AAAA,MACtC,QAAQ,CAAC,WAAW,OAAO,YAAY,CAAC,CAAC;AAAA,IAC3C,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,mCAAmC,YAAuC;AAC9E,UAAM,KAAK,OAAO,OAAO,eAAe;AAAA,MACtC,QAAQ;AAAA,QACN,MAAM,CAAC,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,UAAU,EAAE,EAAE,CAAC;AAAA,MACpE;AAAA,IACF,CAAC;AAAA,EACH;AAAA,EAEA,MAAM,QAAyB;AAC7B,UAAM,CAAC,WAAW,WAAW,IAAI,MAAM,QAAQ,IAAI;AAAA,MACjD,KAAK,OAAO,MAAM,aAAa,EAAE,OAAO,KAAK,CAAC;AAAA,MAC9C,KAAK,OAAO,MAAM,eAAe,EAAE,OAAO,KAAK,CAAC;AAAA,IAClD,CAAC;AACD,WAAO,UAAU,QAAQ,YAAY;AAAA,EACvC;AAAA,EAEA,MAAM,wBAAkE;AACtE,UAAM,YAAY,oBAAI,IAAgC;AACtD,QAAI,SAA6C;AACjD,OAAG;AACD,YAAM,OAAO,MAAM,KAAK,OAAO,OAAO,aAAa;AAAA,QACjD,OAAO;AAAA,QACP;AAAA,QACA,cAAc,CAAC,cAAc,iBAAiB;AAAA,QAC9C,aAAa;AAAA,MACf,CAAC;AACD,iBAAW,SAAS,KAAK,QAAQ;AAC/B,cAAM,MAAM,MAAM,SAAS;AAC3B,YAAI,OAAO,QAAQ,YAAY,UAAU,IAAI,GAAG,EAAG;AACnD,cAAM,WAAW,MAAM,SAAS;AAChC,kBAAU,IAAI,KAAK,OAAO,aAAa,WAAW,WAAW,MAAS;AAAA,MACxE;AACA,eAAS,KAAK,oBAAoB;AAAA,IACpC,SAAS,WAAW,UAAa,WAAW;AAC5C,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,oBAA0C;AAC9C,WAAO,KAAK,mBAAmB,eAAe,cAAc;AAAA,EAC9D;AAAA;AAAA,EAGA,MAAc,mBAAmB,YAAoB,OAAqC;AACxF,UAAM,SAAS,oBAAI,IAAY;AAC/B,QAAI,SAA6C;AACjD,OAAG;AACD,YAAM,OAAO,MAAM,KAAK,OAAO,OAAO,YAAY;AAAA,QAChD,OAAO;AAAA,QACP;AAAA,QACA,cAAc,CAAC,KAAK;AAAA,QACpB,aAAa;AAAA,MACf,CAAC;AACD,iBAAW,SAAS,KAAK,QAAQ;AAC/B,cAAM,QAAQ,MAAM,UAAU,KAAK;AACnC,YAAI,OAAO,UAAU,SAAU,QAAO,IAAI,KAAK;AAAA,MACjD;AACA,eAAS,KAAK,oBAAoB;AAAA,IACpC,SAAS,WAAW,UAAa,WAAW;AAC5C,WAAO;AAAA,EACT;AAAA,EAEA,MAAM,gBAAgB,WAAqB,MAAoD;AAC7F,WAAO,KAAK,OAAO,aAAa,WAAW,IAAI;AAAA,EACjD;AAAA,EAEA,MAAM,kBAAkB,WAAqB,MAAoD;AAC/F,WAAO,KAAK,OAAO,eAAe,WAAW,IAAI;AAAA,EACnD;AAAA,EAEA,MAAM,iBAAiB,YAAwB,MAAoD;AAGjG,UAAM,eAA2B,CAAC;AAClC,QAAI,SAA6C;AACjD,OAAG;AACD,YAAM,OAAO,MAAM,KAAK,OAAO,OAAO,aAAa;AAAA,QACjD,QAAQ,EAAE,MAAM,CAAC,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,UAAU,EAAE,EAAE,CAAC,EAAE;AAAA,QAC9E,aAAa;AAAA,QACb,cAAc;AAAA,QACd,OAAO;AAAA,QACP;AAAA,MACF,CAAC;AACD,iBAAW,SAAS,KAAK,QAAQ;AAC/B,YAAI,MAAM,QAAQ,MAAM,MAAM,EAAG,cAAa,KAAK,MAAM,MAAkB;AAAA,MAC7E;AACA,eAAS,KAAK,oBAAoB;AAAA,IACpC,SAAS,WAAW,UAAa,WAAW;AAE5C,QAAI,aAAa,WAAW,EAAG,QAAO,CAAC;AAGvC,UAAM,SAAS,KAAK,YAAY,EAAE,GAAG,KAAK,QAAQ,mBAAmB,WAAW,CAAC;AAKjF,UAAM,WAAW,aAAa,IAAI,CAAC,YAAY;AAAA,MAC7C;AAAA,MACA,OAAO,KAAK;AAAA,MACZ,iBAAiB,KAAK;AAAA,MACtB,QAAQ,UAAU;AAAA,MAClB,cAAc;AAAA,IAChB,EAAE;AACF,UAAM,UAAU,MAAM,KAAK,OAAO,YAAY,aAAa,EAAE,SAAS,CAAC;AAIvE,UAAM,iBAAiB,oBAAI,IAA6E;AACxG,eAAW,SAAS,SAAS;AAC3B,iBAAW,KAAK,OAAO;AACrB,cAAM,UAAU,EAAE,WAAW,CAAC;AAC9B,cAAM,MAAM,OAAO,QAAQ,UAAU;AACrC,cAAM,OAAO,eAAe,IAAI,GAAG;AACnC,YAAI,CAAC,QAAQ,EAAE,QAAQ,KAAK,OAAO;AACjC,yBAAe,IAAI,KAAK,EAAE,IAAI,OAAO,EAAE,EAAE,GAAG,OAAO,EAAE,OAAO,QAAQ,CAAC;AAAA,QACvE;AAAA,MACF;AAAA,IACF;AAEA,WAAO,CAAC,GAAG,eAAe,OAAO,CAAC,EAC/B,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK,EAChC,MAAM,GAAG,KAAK,KAAK,EACnB,IAAI,CAAC,OAAO;AAAA,MACX,IAAI,EAAE;AAAA,MACN,OAAO,EAAE;AAAA,MACT,YAAY,EAAE,QAAQ;AAAA,MACtB,cAAc,EAAE,QAAQ;AAAA,MACxB,MAAM,EAAE,QAAQ;AAAA,MAChB,aAAa,EAAE,QAAQ;AAAA,IACzB,EAAE;AAAA,EACN;AAAA,EAEA,MAAc,OAAO,YAAoB,WAAqB,MAAoD;AAChH,UAAM,SAAS,KAAK,YAAY,KAAK,MAAM;AAE3C,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,YAAY;AAAA,MACnD,QAAQ;AAAA,MACR,OAAO,KAAK;AAAA,MACZ,iBAAiB,KAAK;AAAA,MACtB,QAAQ,UAAU;AAAA,MAClB,cAAc;AAAA,IAChB,CAAC;AAED,WAAO,QAAQ,IAAI,CAAC,MAAM;AACxB,YAAM,UAAU,EAAE,WAAW,CAAC;AAC9B,aAAO;AAAA,QACL,IAAI,OAAO,EAAE,EAAE;AAAA,QACf,OAAO,EAAE;AAAA,QACT,YAAY,QAAQ;AAAA,QACpB,cAAc,QAAQ;AAAA,QACtB,MAAM,QAAQ;AAAA,QACd,aAAa,QAAQ;AAAA,MACvB;AAAA,IACF,CAAC;AAAA,EACH;AAAA,EAEQ,YAAY,QAA4D;AAC9E,QAAI,CAAC,OAAQ,QAAO;AAEpB,UAAM,OAAoC,CAAC;AAE3C,QAAI,OAAO,eAAe,OAAO,YAAY,SAAS,GAAG;AAIvD,WAAK,KAAK,EAAE,KAAK,eAAe,OAAO,EAAE,KAAK,OAAO,YAAY,EAAE,CAAC;AAAA,IACtE;AAEA,QAAI,OAAO,YAAY;AACrB,WAAK,KAAK,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,OAAO,UAAU,EAAE,EAAE,CAAC;AAAA,IAC9E;AAEA,QAAI,OAAO,YAAY;AACrB,WAAK,KAAK,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,WAAW,EAAE,CAAC;AAAA,IACtE;AAEA,UAAM,WAAwC,CAAC;AAE/C,QAAI,OAAO,mBAAmB;AAC5B,eAAS,KAAK,EAAE,KAAK,cAAc,OAAO,EAAE,OAAO,OAAO,OAAO,iBAAiB,EAAE,EAAE,CAAC;AAAA,IACzF;AAEA,QAAI,OAAO,sBAAsB,OAAO,mBAAmB,SAAS,GAAG;AAErE,eAAS,KAAK,EAAE,KAAK,eAAe,OAAO,EAAE,KAAK,OAAO,mBAAmB,EAAE,CAAC;AAAA,IACjF;AAEA,QAAI,KAAK,WAAW,KAAK,SAAS,WAAW,EAAG,QAAO;AAEvD,WAAO;AAAA,MACL,GAAI,KAAK,SAAS,IAAI,EAAE,KAAK,IAAI,CAAC;AAAA,MAClC,GAAI,SAAS,SAAS,IAAI,EAAE,SAAS,IAAI,CAAC;AAAA,IAC5C;AAAA,EACF;AACF;","names":[]}

package/dist/qdrant-R7IW5NII.js

@@ -1,7 +0,0 @@
-import {
-  QdrantVectorStore
-} from "./chunk-TYDOHCBS.js";
-export {
-  QdrantVectorStore
-};
-//# sourceMappingURL=qdrant-R7IW5NII.js.map