@futdevpro/nts-dynamo 1.14.64 → 1.14.67

package/src/_modules/local-vector-search/_services/lvs-vector-pool.control-service.spec.ts

@@ -0,0 +1,393 @@
+import { LVS_Search_Mode } from '../_enums/lvs-search-mode.enum';
+import { LVS_SearchResult } from '../_models/lvs-search-result.interface';
+import { LVS_VectorPool_ControlService } from './lvs-vector-pool.control-service';
+
+describe('| LVS_VectorPool_ControlService', () => {
+  let vectorPool: LVS_VectorPool_ControlService;
+
+  beforeEach(() => {
+    vectorPool = new LVS_VectorPool_ControlService();
+  });
+
+  describe('| Constructor/Initialization', () => {
+    it('| should initialize with empty pools', () => {
+      const all: Map<string, number[]> = vectorPool.getAll();
+      expect(all.size).toBe(0);
+    });
+  });
+
+  describe('| addVector', () => {
+    it('| should add a valid vector to the pool', () => {
+      const id: string = 'vector1';
+      const vector: number[] = [1, 2, 3];
+
+      vectorPool.addVector(id, vector);
+
+      const all: Map<string, number[]> = vectorPool.getAll();
+      expect(all.size).toBe(1);
+      expect(all.has(id)).toBeTrue();
+      expect(all.get(id)).toEqual(vector);
+    });
+
+    it('| should add multiple vectors to the pool', () => {
+      vectorPool.addVector('vector1', [1, 2, 3]);
+      vectorPool.addVector('vector2', [4, 5, 6]);
+      vectorPool.addVector('vector3', [7, 8, 9]);
+
+      const all: Map<string, number[]> = vectorPool.getAll();
+      expect(all.size).toBe(3);
+    });
+
+    it('| should throw error when ID is empty string', () => {
+      expect(() => {
+        vectorPool.addVector('', [1, 2, 3]);
+      }).toThrowError('Vector ID is required');
+    });
+
+    it('| should throw error when vector is empty array', () => {
+      expect(() => {
+        vectorPool.addVector('vector1', []);
+      }).toThrowError('Vector must be a non-empty array');
+    });
+
+    it('| should throw error when vector is not an array', () => {
+      expect(() => {
+        vectorPool.addVector('vector1', null as any);
+      }).toThrowError('Vector must be a non-empty array');
+    });
+
+    it('| should throw error when vector contains non-finite number', () => {
+      expect(() => {
+        vectorPool.addVector('vector1', [1, 2, Infinity]);
+      }).toThrowError('Vector must contain only finite numbers at index 2');
+    });
+
+    it('| should throw error when vector contains NaN', () => {
+      expect(() => {
+        vectorPool.addVector('vector1', [1, 2, NaN]);
+      }).toThrowError('Vector must contain only finite numbers at index 2');
+    });
+
+    it('| should store normalized vector internally', () => {
+      const id: string = 'vector1';
+      const vector: number[] = [3, 4]; // Magnitude = 5, normalized = [0.6, 0.8]
+
+      vectorPool.addVector(id, vector);
+
+      // Verify original vector is stored
+      const all: Map<string, number[]> = vectorPool.getAll();
+      expect(all.get(id)).toEqual(vector);
+    });
+  });
+
+  describe('| removeVector', () => {
+    it('| should remove an existing vector from the pool', () => {
+      vectorPool.addVector('vector1', [1, 2, 3]);
+      vectorPool.addVector('vector2', [4, 5, 6]);
+
+      vectorPool.removeVector('vector1');
+
+      const all: Map<string, number[]> = vectorPool.getAll();
+      expect(all.size).toBe(1);
+      expect(all.has('vector1')).toBeFalse();
+      expect(all.has('vector2')).toBeTrue();
+    });
+
+    it('| should not throw when removing non-existent vector', () => {
+      expect(() => {
+        vectorPool.removeVector('non-existent');
+      }).not.toThrow();
+    });
+
+    it('| should remove vector from both pools', () => {
+      vectorPool.addVector('vector1', [1, 2, 3]);
+      vectorPool.removeVector('vector1');
+
+      const all: Map<string, number[]> = vectorPool.getAll();
+      expect(all.size).toBe(0);
+    });
+  });
+
+  describe('| updateVector', () => {
+    it('| should update an existing vector', () => {
+      vectorPool.addVector('vector1', [1, 2, 3]);
+      const newVector: number[] = [4, 5, 6];
+
+      vectorPool.updateVector('vector1', newVector);
+
+      const all: Map<string, number[]> = vectorPool.getAll();
+      expect(all.get('vector1')).toEqual(newVector);
+    });
+
+    it('| should throw error when updating non-existent vector', () => {
+      expect(() => {
+        vectorPool.updateVector('non-existent', [1, 2, 3]);
+      }).toThrowError('Vector with ID "non-existent" does not exist');
+    });
+  });
+
+  describe('| clearPool', () => {
+    it('| should clear a populated pool', () => {
+      vectorPool.addVector('vector1', [1, 2, 3]);
+      vectorPool.addVector('vector2', [4, 5, 6]);
+      vectorPool.addVector('vector3', [7, 8, 9]);
+
+      vectorPool.clearPool();
+
+      const all: Map<string, number[]> = vectorPool.getAll();
+      expect(all.size).toBe(0);
+    });
+
+    it('| should not throw when clearing empty pool', () => {
+      expect(() => {
+        vectorPool.clearPool();
+      }).not.toThrow();
+    });
+  });
+
+  describe('| getAll', () => {
+    it('| should return a copy of the pool, not a reference', () => {
+      vectorPool.addVector('vector1', [1, 2, 3]);
+      const all1: Map<string, number[]> = vectorPool.getAll();
+      const all2: Map<string, number[]> = vectorPool.getAll();
+
+      expect(all1).not.toBe(all2);
+      expect(all1.size).toBe(all2.size);
+    });
+
+    it('| should return empty map when pool is empty', () => {
+      const all: Map<string, number[]> = vectorPool.getAll();
+      expect(all.size).toBe(0);
+    });
+  });
+
+  describe('| cosineSimilarity (static)', () => {
+    it('| should return 1 for identical vectors', () => {
+      const vector: number[] = [1, 2, 3];
+      const similarity: number = LVS_VectorPool_ControlService.cosineSimilarity(vector, vector);
+      expect(similarity).toBeCloseTo(1, 10);
+    });
+
+    it('| should return approximately 0 for orthogonal vectors', () => {
+      const vector1: number[] = [1, 0, 0];
+      const vector2: number[] = [0, 1, 0];
+      const similarity: number = 
+        LVS_VectorPool_ControlService.cosineSimilarity(vector1, vector2);
+      expect(similarity).toBeCloseTo(0, 10);
+    });
+
+    it('| should throw error for vectors with different dimensions', () => {
+      const vector1: number[] = [1, 2, 3];
+      const vector2: number[] = [1, 2];
+
+      expect(() => {
+        LVS_VectorPool_ControlService.cosineSimilarity(vector1, vector2);
+      }).toThrowError('Vectors must have the same dimension. Got 3 and 2');
+    });
+
+    it('| should calculate correct cosine similarity for known vectors', () => {
+      // Two vectors pointing in similar direction
+      const vector1: number[] = [1, 1, 0];
+      const vector2: number[] = [1, 0, 0];
+      // Normalized: [1/√2, 1/√2, 0] and [1, 0, 0]
+      // Dot product: 1/√2 ≈ 0.707
+      const similarity: number = 
+        LVS_VectorPool_ControlService.cosineSimilarity(vector1, vector2);
+      expect(similarity).toBeCloseTo(1 / Math.sqrt(2), 10);
+    });
+
+    it('| should handle zero vector', () => {
+      const vector1: number[] = [0, 0, 0];
+      const vector2: number[] = [1, 2, 3];
+      const similarity: number = 
+        LVS_VectorPool_ControlService.cosineSimilarity(vector1, vector2);
+      expect(similarity).toBeCloseTo(0, 10);
+    });
+  });
+
+  describe('| l2Distance (static)', () => {
+    it('| should return 0 for identical vectors', () => {
+      const vector: number[] = [1, 2, 3];
+      const distance: number = LVS_VectorPool_ControlService.l2Distance(vector, vector);
+      expect(distance).toBe(0);
+    });
+
+    it('| should throw error for vectors with different dimensions', () => {
+      const vector1: number[] = [1, 2, 3];
+      const vector2: number[] = [1, 2];
+
+      expect(() => {
+        LVS_VectorPool_ControlService.l2Distance(vector1, vector2);
+      }).toThrowError('Vectors must have the same dimension. Got 3 and 2');
+    });
+
+    it('| should calculate correct L2 distance for known vectors', () => {
+      const vector1: number[] = [0, 0, 0];
+      const vector2: number[] = [3, 4, 0];
+      // Distance = √(3² + 4² + 0²) = √25 = 5
+      const distance: number = LVS_VectorPool_ControlService.l2Distance(vector1, vector2);
+      expect(distance).toBe(5);
+    });
+
+    it('| should calculate correct L2 distance for 1D vectors', () => {
+      const vector1: number[] = [5];
+      const vector2: number[] = [2];
+      const distance: number = LVS_VectorPool_ControlService.l2Distance(vector1, vector2);
+      expect(distance).toBe(3);
+    });
+  });
+
+  describe('| search', () => {
+    beforeEach(() => {
+      // Add test vectors
+      vectorPool.addVector('vec1', [1, 0, 0]);
+      vectorPool.addVector('vec2', [0, 1, 0]);
+      vectorPool.addVector('vec3', [0, 0, 1]);
+      vectorPool.addVector('vec4', [1, 1, 0]);
+    });
+
+    it('| should return empty array for empty pool', () => {
+      const emptyPool: LVS_VectorPool_ControlService = new LVS_VectorPool_ControlService();
+      const results: LVS_SearchResult[] = emptyPool.search([1, 0, 0], 3, LVS_Search_Mode.cosineSimilarity);
+      expect(results.length).toBe(0);
+    });
+
+    it('| should return results in descending order for cosine similarity', () => {
+      const query: number[] = [1, 0, 0];
+      const results: LVS_SearchResult[] = vectorPool.search(
+        query, 
+        4, 
+        LVS_Search_Mode.cosineSimilarity
+      );
+
+      expect(results.length).toBe(4);
+      // vec1 should be most similar (identical)
+      expect(results[0].id).toBe('vec1');
+      expect(results[0].score).toBeCloseTo(1, 10);
+      // Results should be in descending order
+      for (let i: number = 0; i < results.length - 1; i++) {
+        expect(results[i].score).toBeGreaterThanOrEqual(results[i + 1].score);
+      }
+    });
+
+    it('| should return results in ascending order for L2 distance', () => {
+      const query: number[] = [1, 0, 0];
+      const results: LVS_SearchResult[] = vectorPool.search(
+        query, 
+        4, 
+        LVS_Search_Mode.l2Distance
+      );
+
+      expect(results.length).toBe(4);
+      // vec1 should be closest (distance = 0)
+      expect(results[0].id).toBe('vec1');
+      expect(results[0].score).toBe(0);
+      // Results should be in ascending order
+      for (let i: number = 0; i < results.length - 1; i++) {
+        expect(results[i].score).toBeLessThanOrEqual(results[i + 1].score);
+      }
+    });
+
+    it('| should limit results to top-K when k < pool size', () => {
+      const query: number[] = [1, 0, 0];
+      const results: LVS_SearchResult[] = vectorPool.search(
+        query, 
+        2, 
+        LVS_Search_Mode.cosineSimilarity
+      );
+
+      expect(results.length).toBe(2);
+    });
+
+    it('| should return all results when k > pool size', () => {
+      const query: number[] = [1, 0, 0];
+      const results: LVS_SearchResult[] = vectorPool.search(
+        query, 
+        10, 
+        LVS_Search_Mode.cosineSimilarity
+      );
+
+      expect(results.length).toBe(4);
+    });
+
+    it('| should return all results when k = pool size', () => {
+      const query: number[] = [1, 0, 0];
+      const results: LVS_SearchResult[] = vectorPool.search(
+        query, 
+        4, 
+        LVS_Search_Mode.cosineSimilarity
+      );
+
+      expect(results.length).toBe(4);
+    });
+
+    it('| should throw error for dimension mismatch', () => {
+      const query: number[] = [1, 0]; // 2D query, pool has 3D vectors
+
+      expect(() => {
+        vectorPool.search(query, 3, LVS_Search_Mode.cosineSimilarity);
+      }).toThrowError('Query vector dimension (2) does not match pool vector dimension (3)');
+    });
+
+    it('| should throw error for empty query vector', () => {
+      expect(() => {
+        vectorPool.search([], 3, LVS_Search_Mode.cosineSimilarity);
+      }).toThrowError('Query vector must be a non-empty array');
+    });
+
+    it('| should throw error for non-array query', () => {
+      expect(() => {
+        vectorPool.search(null as any, 3, LVS_Search_Mode.cosineSimilarity);
+      }).toThrowError('Query vector must be a non-empty array');
+    });
+
+    it('| should throw error for k = 0', () => {
+      expect(() => {
+        vectorPool.search([1, 0, 0], 0, LVS_Search_Mode.cosineSimilarity);
+      }).toThrowError('k must be a positive number');
+    });
+
+    it('| should throw error for negative k', () => {
+      expect(() => {
+        vectorPool.search([1, 0, 0], -1, LVS_Search_Mode.cosineSimilarity);
+      }).toThrowError('k must be a positive number');
+    });
+
+    it('| should throw error for unknown search mode', () => {
+      expect(() => {
+        vectorPool.search([1, 0, 0], 3, 'unknown-mode' as LVS_Search_Mode);
+      }).toThrowError('Unknown search mode: unknown-mode');
+    });
+
+    it('| should return correct scores for cosine similarity', () => {
+      const query: number[] = [1, 0, 0];
+      const results: LVS_SearchResult[] = vectorPool.search(
+        query, 
+        4, 
+        LVS_Search_Mode.cosineSimilarity
+      );
+
+      // vec1 should have score = 1 (identical)
+      const vec1Result: LVS_SearchResult | undefined = 
+        results.find((r: LVS_SearchResult) => r.id === 'vec1');
+      expect(vec1Result).toBeDefined();
+      expect(vec1Result!.score).toBeCloseTo(1, 10);
+    });
+
+    it('| should return correct scores for L2 distance', () => {
+      const query: number[] = [1, 0, 0];
+      const results: LVS_SearchResult[] = vectorPool.search(
+        query, 
+        4, 
+        LVS_Search_Mode.l2Distance
+      );
+
+      // vec1 should have score = 0 (identical)
+      const vec1Result: LVS_SearchResult | undefined = 
+        results.find((r: LVS_SearchResult) => r.id === 'vec1');
+      expect(vec1Result).toBeDefined();
+      expect(vec1Result!.score).toBe(0);
+    });
+  });
+});
+

package/src/_modules/local-vector-search/_services/lvs-vector-pool.control-service.ts

@@ -0,0 +1,220 @@
+import { LVS_Search_Mode } from '../_enums/lvs-search-mode.enum';
+import { LVS_SearchResult } from '../_models/lvs-search-result.interface';
+
+/**
+ * Vektor pool kezelő utility class
+ * Instance-based class, amely in-memory vektor pool-t kezel és vektor hasonlósági számításokat végez
+ * Minden instance saját vektor pool-t tart fenn
+ */
+export class LVS_VectorPool_ControlService {
+  /**
+   * In-memory vektor pool tárolás
+   * Key: vektor ID, Value: vektor értékek
+   */
+  private vectorPool: Map<string, number[]> = new Map<string, number[]>();
+
+  /**
+   * Normalizált vektor pool tárolás (L2 normalizált másolatok)
+   * Key: vektor ID, Value: L2 normalizált vektor értékek
+   */
+  private normalizedVectorPool: Map<string, number[]> = new Map<string, number[]>();
+
+  /**
+   * Hozzáad egy vektort a pool-hoz
+   * Opcionálisan L2 normalizált másolatot is tárol
+   */
+  addVector(id: string, vector: number[]): void {
+    if (!id) {
+      throw new Error('Vector ID is required');
+    }
+
+    if (!Array.isArray(vector) || vector.length === 0) {
+      throw new Error('Vector must be a non-empty array');
+    }
+
+    // Validáljuk, hogy a vektor számokból áll
+    for (let i: number = 0; i < vector.length; i++) {
+      if (typeof vector[i] !== 'number' || !isFinite(vector[i])) {
+        throw new Error(`Vector must contain only finite numbers at index ${i}`);
+      }
+    }
+
+    // Tároljuk az eredeti vektort
+    this.vectorPool.set(id, vector);
+
+    // L2 normalizált másolatot is tárolunk a cosine similarity számításokhoz
+    const normalized: number[] = LVS_VectorPool_ControlService.l2Normalize(vector);
+    this.normalizedVectorPool.set(id, normalized);
+  }
+
+  /**
+   * Eltávolít egy vektort a pool-ból
+   */
+  removeVector(id: string): void {
+    this.vectorPool.delete(id);
+    this.normalizedVectorPool.delete(id);
+  }
+
+  /**
+   * Frissít egy vektort a pool-ban
+   */
+  updateVector(id: string, vector: number[]): void {
+    if (!this.vectorPool.has(id)) {
+      throw new Error(`Vector with ID "${id}" does not exist`);
+    }
+
+    this.addVector(id, vector);
+  }
+
+  /**
+   * Törli az összes vektort a pool-ból
+   */
+  clearPool(): void {
+    this.vectorPool.clear();
+    this.normalizedVectorPool.clear();
+  }
+
+  /**
+   * Visszaadja az összes vektort a pool-ból
+   * Debugging és export céljára
+   */
+  getAll(): Map<string, number[]> {
+    return new Map<string, number[]>(this.vectorPool);
+  }
+
+  /**
+   * L2 normalizálás egy vektorra
+   * A vektor hosszát 1-re normalizálja
+   * Statikus metódus, mivel nincs szüksége instance state-re
+   */
+  private static l2Normalize(vector: number[]): number[] {
+    const magnitude: number = Math.sqrt(
+      vector.reduce((sum: number, value: number) => sum + value * value, 0)
+    );
+
+    if (magnitude === 0) {
+      // Ha a vektor nullvektor, akkor nullvektort adunk vissza
+      return new Array<number>(vector.length).fill(0);
+    }
+
+    return vector.map((value: number) => value / magnitude);
+  }
+
+  /**
+   * Cosine similarity számítás két vektor között
+   * Normalizált vektorokat használ a számításhoz
+   * Eredmény: 0 és 1 közötti érték, ahol 1 a legnagyobb hasonlóság
+   * Statikus metódus, mivel nincs szüksége instance state-re
+   */
+  static cosineSimilarity(a: number[], b: number[]): number {
+    if (a.length !== b.length) {
+      throw new Error(
+        `Vectors must have the same dimension. Got ${a.length} and ${b.length}`
+      );
+    }
+
+    // Normalizáljuk a vektorokat
+    const normalizedA: number[] = this.l2Normalize(a);
+    const normalizedB: number[] = this.l2Normalize(b);
+
+    // Dot product számítása
+    let dotProduct: number = 0;
+    for (let i: number = 0; i < normalizedA.length; i++) {
+      dotProduct += normalizedA[i] * normalizedB[i];
+    }
+
+    // Cosine similarity = dot product of normalized vectors
+    // Mivel a vektorok normalizáltak, ez egyenlő a cosine similarity-vel
+    return dotProduct;
+  }
+
+  /**
+   * L2 distance (Euklideszi távolság) számítás két vektor között
+   * Eredmény: 0 vagy pozitív érték, ahol 0 a legkisebb távolság
+   * Statikus metódus, mivel nincs szüksége instance state-re
+   */
+  static l2Distance(a: number[], b: number[]): number {
+    if (a.length !== b.length) {
+      throw new Error(
+        `Vectors must have the same dimension. Got ${a.length} and ${b.length}`
+      );
+    }
+
+    // L2 distance = sqrt(sum((a[i] - b[i])^2))
+    let sumSquaredDiff: number = 0;
+    for (let i: number = 0; i < a.length; i++) {
+      const diff: number = a[i] - b[i];
+      sumSquaredDiff += diff * diff;
+    }
+
+    return Math.sqrt(sumSquaredDiff);
+  }
+
+  /**
+   * Vektor keresés a pool-ban
+   * Brute-force megközelítés (lineáris keresés)
+   * 
+   * @param query A keresési query vektor
+   * @param k A visszaadandó találatok száma (top-K)
+   * @param mode A keresési mód (cosine similarity vagy L2 distance)
+   * @returns A top-K találatok ID-val és score-rel, megfelelő sorrendben
+   */
+  search(
+    query: number[],
+    k: number,
+    mode: LVS_Search_Mode
+  ): LVS_SearchResult[] {
+    if (!Array.isArray(query) || query.length === 0) {
+      throw new Error('Query vector must be a non-empty array');
+    }
+
+    if (k <= 0) {
+      throw new Error('k must be a positive number');
+    }
+
+    if (this.vectorPool.size === 0) {
+      return [];
+    }
+
+    // Validáljuk, hogy minden vektor ugyanolyan dimenziójú-e
+    const firstVector: number[] | undefined = Array.from(this.vectorPool.values())[0];
+    if (firstVector && firstVector.length !== query.length) {
+      throw new Error(
+        `Query vector dimension (${query.length}) does not match pool vector ` +
+        `dimension (${firstVector.length})`
+      );
+    }
+
+    // Számoljuk ki a hasonlóságot/távolságot minden vektorra
+    const results: LVS_SearchResult[] = [];
+
+    for (const [id, vector] of this.vectorPool.entries()) {
+      let score: number;
+
+      if (mode === LVS_Search_Mode.cosineSimilarity) {
+        // Cosine similarity: nagyobb érték = jobb hasonlóság
+        score = LVS_VectorPool_ControlService.cosineSimilarity(query, vector);
+      } else if (mode === LVS_Search_Mode.l2Distance) {
+        // L2 distance: kisebb érték = jobb hasonlóság
+        score = LVS_VectorPool_ControlService.l2Distance(query, vector);
+      } else {
+        throw new Error(`Unknown search mode: ${mode}`);
+      }
+
+      results.push({ id, score });
+    }
+
+    // Rendezzük az eredményeket
+    if (mode === LVS_Search_Mode.cosineSimilarity) {
+      // Cosine similarity: csökkenő sorrend (legnagyobb hasonlóság először)
+      results.sort((a: LVS_SearchResult, b: LVS_SearchResult) => b.score - a.score);
+    } else {
+      // L2 distance: növekvő sorrend (legkisebb távolság először)
+      results.sort((a: LVS_SearchResult, b: LVS_SearchResult) => a.score - b.score);
+    }
+
+    // Visszaadjuk a top-K találatot
+    return results.slice(0, k);
+  }
+}
+

package/src/_modules/local-vector-search/index.ts

@@ -0,0 +1,12 @@
+
+
+// ENUMS
+export * from './_enums/lvs-search-mode.enum';
+
+// INTERFACES
+export * from './_models/lvs-search-result.interface';
+
+// SERVICES
+export * from './_services/lvs-doc-chunk-data.service';
+export * from './_services/lvs-local-vector-search.data-service';
+export * from './_services/lvs-vector-pool.control-service';

package/src/_services/base/data.service.ts

@@ -804,10 +804,8 @@ export class DyNTS_DataService<T extends DyFM_Metadata> {
     return data;
   }
 
-  async patchData(data?: T): Promise<T> {
+  async patchData(data?: Partial<T>): Promise<T> {
     try {
-      data = this.ensureData(data);
-
       if (!data._id) {
         throw new DyFM_Error({ 
           ...this._getDefaultErrorSettings(
@@ -828,6 +826,17 @@ export class DyNTS_DataService<T extends DyFM_Metadata> {
         });
       }
 
+      for (const key in this.depSettings) {
+        if (data[key] && data[key] !== dataExists[key]) {
+          throw new DyFM_Error({ 
+            ...this._getDefaultErrorSettings(
+              'patchData',
+              new Error(`Cannot patch data: dependency data mismatch! (${this.dataParams.dataName})`)
+            ),
+          });
+        }
+      }
+
       DyFM_Object.cleanAssign(dataExists, data);
       
       await this.validateForSave(dataExists);