This repository has no description
1import pg from "pg";
2import { readFileSync } from "node:fs";
3function conn() {
4 if (process.env.DB_CONNECTION_STRING) return process.env.DB_CONNECTION_STRING;
5 for (const p of ["../.env", ".env"]) { try { const m = readFileSync(p, "utf8").match(/^\s*DB_CONNECTION_STRING\s*=\s*(.+)$/m); if (m) return m[1].trim(); } catch {} }
6}
7const pool = new pg.Pool({ connectionString: conn(), ssl: { rejectUnauthorized: false }, max: 3 });
8
9console.log("=== embedded rows: dims + L2 norm ===");
10console.table((await pool.query(`
11 select repo_name, embedding_model,
12 vector_dims(embedding) as dims,
13 round(sqrt((select sum(x*x) from unnest(embedding::real[]) x))::numeric, 5) as l2_norm
14 from tangled_readmes where embedding is not null
15 order by embedded_at desc limit 5`)).rows);
16
17console.log("\n=== nearest-neighbor sanity (cosine) for one embedded repo ===");
18const seed = (await pool.query(`select repo_did, repo_name from tangled_readmes where embedding is not null limit 1`)).rows[0];
19if (seed) {
20 console.log(`seed: ${seed.repo_name} (${seed.repo_did})`);
21 const nn = await pool.query(`
22 select repo_name, round((embedding <=> (select embedding from tangled_readmes where repo_did=$1))::numeric, 4) as cosine_dist
23 from tangled_readmes
24 where embedding is not null and repo_did <> $1
25 order by embedding <=> (select embedding from tangled_readmes where repo_did=$1)
26 limit 5`, [seed.repo_did]);
27 console.table(nn.rows);
28}
29await pool.end();