fix: parse pgvector embeddings before cosine rescoring

recipes/x-to-brain.md

@@ -11,10 +11,10 @@ secrets:
     where: https://developer.x.com/en/portal/dashboard — create a project + app, copy the Bearer Token from "Keys and tokens"
 health_checks:
   - type: http
-    url: "https://api.x.com/2/users/me"
+    url: "https://api.x.com/2/users/by/username/X"
     auth: bearer
     auth_token: "$X_BEARER_TOKEN"
-    label: "X API"
+    label: "X API bearer auth"
 setup_time: 15 min
 cost_estimate: "$0-200/mo (Free tier: 1 app, read-only. Basic: $200/mo for search + higher limits)"
 ---

src/core/postgres-engine.ts

@@ -17,7 +17,7 @@ import type {
 } from './types.ts';
 import { GBrainError } from './types.ts';
 import * as db from './db.ts';
-import { validateSlug, contentHash, rowToPage, rowToChunk, rowToSearchResult } from './utils.ts';
+import { validateSlug, contentHash, parseEmbedding, rowToPage, rowToChunk, rowToSearchResult } from './utils.ts';
 
 export class PostgresEngine implements BrainEngine {
   private _sql: ReturnType<typeof postgres> | null = null;
@@ -275,7 +275,8 @@ export class PostgresEngine implements BrainEngine {
     `;
     const result = new Map<number, Float32Array>();
     for (const row of rows) {
-      if (row.embedding) result.set(row.id as number, row.embedding as Float32Array);
+      const embedding = parseEmbedding(row.embedding);
+      if (embedding) result.set(row.id as number, embedding);
     }
     return result;
   }

src/core/utils.ts

@@ -1,6 +1,26 @@
 import { createHash } from 'crypto';
 import type { Page, PageInput, PageType, Chunk, SearchResult } from './types.ts';
 
+export function parseEmbedding(value: unknown): Float32Array | null {
+  if (!value) return null;
+
+  if (value instanceof Float32Array) return value;
+
+  if (Array.isArray(value)) {
+    return new Float32Array(value.map(Number));
+  }
+
+  if (typeof value === 'string') {
+    const trimmed = value.trim();
+    if (!trimmed.startsWith('[') || !trimmed.endsWith(']')) return null;
+    const body = trimmed.slice(1, -1).trim();
+    if (!body) return new Float32Array();
+    return new Float32Array(body.split(',').map(part => Number(part.trim())));
+  }
+
+  return null;
+}
+
 /**
  * Validate and normalize a slug. Slugs are lowercased repo-relative paths.
  * Rejects empty slugs, path traversal (..), and leading /.
@@ -50,7 +70,7 @@ export function rowToChunk(row: Record<string, unknown>, includeEmbedding = fals
     chunk_index: row.chunk_index as number,
     chunk_text: row.chunk_text as string,
     chunk_source: row.chunk_source as 'compiled_truth' | 'timeline',
-    embedding: includeEmbedding && row.embedding ? row.embedding as Float32Array : null,
+    embedding: includeEmbedding ? parseEmbedding(row.embedding) : null,
     model: row.model as string,
     token_count: row.token_count as number | null,
     embedded_at: row.embedded_at ? new Date(row.embedded_at as string) : null,

test/utils.test.ts

@@ -1,5 +1,5 @@
 import { describe, test, expect } from 'bun:test';
-import { validateSlug, contentHash, rowToPage, rowToChunk, rowToSearchResult } from '../src/core/utils.ts';
+import { validateSlug, contentHash, parseEmbedding, rowToPage, rowToChunk, rowToSearchResult } from '../src/core/utils.ts';
 
 describe('validateSlug', () => {
   test('accepts valid slugs', () => {
@@ -98,6 +98,40 @@ describe('rowToChunk', () => {
     }, true);
     expect(chunk.embedding).not.toBeNull();
   });
+
+  test('parses pgvector string embeddings when requested', () => {
+    const chunk = rowToChunk({
+      id: 1, page_id: 1, chunk_index: 0, chunk_text: 'text',
+      chunk_source: 'compiled_truth', embedding: '[0.1, 0.2, 0.3]',
+      model: 'test', token_count: 5, embedded_at: '2024-01-01',
+    }, true);
+    expect(chunk.embedding).toBeInstanceOf(Float32Array);
+    expect(Array.from(chunk.embedding || [])).toHaveLength(3);
+    expect(chunk.embedding?.[0]).toBeCloseTo(0.1, 6);
+    expect(chunk.embedding?.[1]).toBeCloseTo(0.2, 6);
+    expect(chunk.embedding?.[2]).toBeCloseTo(0.3, 6);
+  });
+});
+
+describe('parseEmbedding', () => {
+  test('returns Float32Array unchanged', () => {
+    const emb = new Float32Array([0.1, 0.2]);
+    expect(parseEmbedding(emb)).toBe(emb);
+  });
+
+  test('parses pgvector text into Float32Array', () => {
+    const parsed = parseEmbedding('[0.1, 0.2, 0.3]');
+    expect(parsed).toBeInstanceOf(Float32Array);
+    expect(Array.from(parsed || [])).toHaveLength(3);
+    expect(parsed?.[0]).toBeCloseTo(0.1, 6);
+    expect(parsed?.[1]).toBeCloseTo(0.2, 6);
+    expect(parsed?.[2]).toBeCloseTo(0.3, 6);
+  });
+
+  test('returns null for unsupported embedding values', () => {
+    expect(parseEmbedding(null)).toBeNull();
+    expect(parseEmbedding('not-a-vector')).toBeNull();
+  });
 });
 
 describe('rowToSearchResult', () => {