fix: remove pgvector dependency from AI knowledge retrieval

modules/ai/server/knowledge.ts

@@ -1,7 +1,7 @@
 import "server-only";
 
 import { OpenAIEmbeddings } from "@langchain/openai";
-import { and, desc, eq, isNull, or, sql } from "drizzle-orm";
+import { and, desc, eq, isNull, or } from "drizzle-orm";
 
 import { getAiRuntimeConfig } from "@/modules/ai/server/config";
 import type {
@@ -316,6 +316,29 @@ export async function deleteKnowledgeEntry(context: AuthContext, id: string): Pr
   return { success: true, data: { entry: toKnowledgeEntry(row) } };
 }
 
+function calculateCosineSimilarity(left: readonly number[], right: readonly number[]): number {
+  if (left.length === 0 || right.length === 0 || left.length !== right.length) {
+    return 0;
+  }
+
+  let dotProduct = 0;
+  let leftMagnitude = 0;
+  let rightMagnitude = 0;
+  for (let index = 0; index < left.length; index += 1) {
+    const leftValue = left[index] ?? 0;
+    const rightValue = right[index] ?? 0;
+    dotProduct += leftValue * rightValue;
+    leftMagnitude += leftValue * leftValue;
+    rightMagnitude += rightValue * rightValue;
+  }
+
+  if (leftMagnitude === 0 || rightMagnitude === 0) {
+    return 0;
+  }
+
+  return dotProduct / (Math.sqrt(leftMagnitude) * Math.sqrt(rightMagnitude));
+}
+
 export async function retrieveKnowledge(
   organizationId: string,
   query: string,
@@ -333,7 +356,6 @@ export async function retrieveKnowledge(
   }
 
   const database = getDatabase();
-  const distance = sql<number>`${aiKnowledgeChunks.embedding} <=> ${JSON.stringify(embedding)}::vector`;
   const rows = await database
     .select({
       entryId: aiKnowledgeChunks.entryId,
@@ -341,25 +363,26 @@ export async function retrieveKnowledge(
       title: aiKnowledgeChunks.sourceTitle,
       category: aiKnowledgeChunks.sourceCategory,
       content: aiKnowledgeChunks.content,
-      distance,
+      embedding: aiKnowledgeChunks.embedding,
     })
     .from(aiKnowledgeChunks)
     .innerJoin(aiKnowledgeEntries, eq(aiKnowledgeEntries.id, aiKnowledgeChunks.entryId))
-    .where(getEnabledChunkWhere(organizationId))
-    .orderBy(distance)
-    .limit(options?.limit ?? DEFAULT_RETRIEVAL_LIMIT);
+    .where(getEnabledChunkWhere(organizationId));
 
   return {
     success: true,
     data: {
-      results: rows.map((row) => ({
-        entryId: row.entryId,
-        chunkId: row.chunkId,
-        title: row.title,
-        category: row.category,
-        content: row.content,
-        score: 1 - row.distance,
-      })),
+      results: rows
+        .map((row) => ({
+          entryId: row.entryId,
+          chunkId: row.chunkId,
+          title: row.title,
+          category: row.category,
+          content: row.content,
+          score: calculateCosineSimilarity(row.embedding, embedding),
+        }))
+        .sort((left, right) => right.score - left.score)
+        .slice(0, options?.limit ?? DEFAULT_RETRIEVAL_LIMIT),
     },
   };
 }