create cosine similarity method

api/database.ts

@@ -35,4 +35,13 @@ export class DataBase {
       console.error(AppError.dbConnectionError, error);
     }
   }
+
+  async disconnect() {
+    try {
+      await this.client.end();
+      console.log("Disconnected from the database.");
+    } catch (err) {
+      console.error(AppError.dbDisconnectError, err);
+    }
+  }
 }

api/error.ts

@@ -2,4 +2,5 @@ export const AppError = {
   VectorCreationError: "Error creating pg vector extension",
   CreateDocumentError: (document: string) => `Unable to create document, with query ${document}`,
   dbConnectionError: "Error connecting to the database:",
+  dbDisconnectError: "Error disconnecting from the database:",
 };

api/query.ts

@@ -1,10 +1,35 @@
 export const dbQuery = {
   CREATE_VECTOR: "CREATE EXTENSION IF NOT EXISTS vector;",
   CREATE_TABLE: `
-      CREATE TABLE IF NOT EXISTS documents (
-        id bigserial PRIMARY KEY,
-        content text,
-        embedding vector(1536)
-      );
-    `,
+    CREATE TABLE IF NOT EXISTS documents (
+      id bigserial PRIMARY KEY,
+      content text,
+      embedding vector(1536)
+    );
+  `,
+  CREATE_MATCH_DOCUMENTS_TABLES: `
+    create or replace function match_documents (
+      query_embedding vector(1536),
+      match_threshold float,
+      match_count int
+    )
+    returns table (
+      id bigint,
+      content text,
+      similarity float
+    )
+    language sql stable
+    as $$
+      select
+        documents.id,
+        documents.content,
+        1 - (documents.embedding <=> query_embedding) as similarity
+      from documents
+      where documents.embedding <=> query_embedding < 1 - match_threshold
+      order by documents.embedding <=> query_embedding
+      limit match_count;
+    $$;
+  `,
+  CREATE_INDEX: `CREATE INDEX ON documents USING ivfflat (embedding vector_cosine_ops)
+          WITH (lists = 100);`,
 };

api/services/document-service.ts

@@ -0,0 +1 @@
+export class DocumentService {}

api/services/embed-service.ts

@@ -1 +1,33 @@
-export class Embed {}
+export class EmbeddingService {
+  generateEmbeddings() {}
+
+  /**
+   * Calculates the cosine similarity between two vectors.
+   * @param vecA - The first vector.
+   * @param vecB - The second vector.
+   * @returns The cosine similarity between the two vectors.
+   * @throws Error if the lengths of the vectors are not equal.
+   */
+  cosineSimilarity(vecA: number[], vecB: number[]) {
+    let dotProduct = 0;
+    let magnitudeA = 0;
+    let magnitudeB = 0;
+    if (vecA.length !== vecB.length) {
+      throw Error("Both vectors must be of the same length");
+    }
+    for (let i = 0; i < vecA.length; i++) {
+      dotProduct += vecA[i] * vecB[i];
+      magnitudeA += Math.pow(vecA[i], 2);
+      magnitudeB += Math.pow(vecB[i], 2);
+    }
+
+    magnitudeA = Math.sqrt(magnitudeA);
+    magnitudeB = Math.sqrt(magnitudeB);
+
+    if (magnitudeA !== 0 && magnitudeB !== 0) {
+      return dotProduct / (magnitudeA * magnitudeB);
+    } else {
+      return null;
+    }
+  }
+}