106 lines
2.8 KiB
TypeScript
106 lines
2.8 KiB
TypeScript
import { Database } from "jsr:@db/sqlite";
|
|
import {
|
|
assert,
|
|
assertEquals,
|
|
} from "https://deno.land/std@0.224.0/testing/asserts.ts";
|
|
|
|
/**
|
|
* Proof of Concept: Embedded Vector Database (Gen 2)
|
|
*
|
|
* Demonstrates the concept of fuzzy semantic retrieval using an actual
|
|
* SQLite database. While we are not loading a C extension like `sqlite-vec`
|
|
* directly here to keep the PoC universally executable without native build
|
|
* dependencies, we simulate it via SQL and User Defined Functions (UDF)
|
|
* provided by Deno's `jsr:@db/sqlite`.
|
|
*/
|
|
|
|
// A simple mock for cosine similarity of 1D arrays
|
|
function cosineSimilarity(vecA: number[], vecB: number[]): number {
|
|
let dotProduct = 0;
|
|
let normA = 0;
|
|
let normB = 0;
|
|
for (let i = 0; i < vecA.length; i++) {
|
|
dotProduct += vecA[i] * vecB[i];
|
|
normA += vecA[i] ** 2;
|
|
normB += vecB[i] ** 2;
|
|
}
|
|
if (normA === 0 || normB === 0) return 0;
|
|
return dotProduct / (Math.sqrt(normA) * Math.sqrt(normB));
|
|
}
|
|
|
|
if (import.meta.main) {
|
|
console.log("Running Embedded Vector Database PoC (Gen 2) tests...");
|
|
|
|
try {
|
|
const db = new Database(":memory:");
|
|
|
|
// Create a user-defined function in SQLite to perform vector similarity!
|
|
db.function("vec_distance", (aStr: string, bStr: string) => {
|
|
const vecA = JSON.parse(aStr) as number[];
|
|
const vecB = JSON.parse(bStr) as number[];
|
|
return cosineSimilarity(vecA, vecB);
|
|
});
|
|
|
|
db.exec(`
|
|
CREATE TABLE documents (
|
|
id TEXT PRIMARY KEY,
|
|
text TEXT,
|
|
vector TEXT
|
|
);
|
|
`);
|
|
|
|
const insert = db.prepare(
|
|
"INSERT INTO documents (id, text, vector) VALUES (?, ?, ?)",
|
|
);
|
|
|
|
insert.run(
|
|
"docs-1",
|
|
"How to run the server",
|
|
JSON.stringify([0.8, 0.1, 0.1, 0.0]),
|
|
);
|
|
insert.run(
|
|
"docs-2",
|
|
"Database connection logic",
|
|
JSON.stringify([0.1, 0.9, 0.2, 0.1]),
|
|
);
|
|
insert.run(
|
|
"telemetry-1",
|
|
"Server latency spikes",
|
|
JSON.stringify([0.2, 0.1, 0.9, 0.3]),
|
|
);
|
|
insert.finalize();
|
|
|
|
// Query representing "I have a slow server issue"
|
|
const queryVectorStr = JSON.stringify([0.3, 0.0, 0.9, 0.2]);
|
|
|
|
console.log("Querying Vector DB...");
|
|
|
|
const results = db.prepare(`
|
|
SELECT id, text, vec_distance(vector, ?) as score
|
|
FROM documents
|
|
ORDER BY score DESC
|
|
`).all(queryVectorStr) as { id: string; text: string; score: number }[];
|
|
|
|
console.log(
|
|
"Top result:",
|
|
results[0].text,
|
|
`(Score: ${results[0].score.toFixed(2)})`,
|
|
);
|
|
|
|
assert(
|
|
results[0].score > 0.8,
|
|
"The telemetry doc should be the highest match",
|
|
);
|
|
assertEquals(results[0].id, "telemetry-1");
|
|
|
|
console.log(
|
|
"✅ Embedded Vector DB PoC (Gen 2) successful: Real SQLite fuzzy semantic match via UDF.",
|
|
);
|
|
|
|
db.close();
|
|
} catch (err) {
|
|
console.error("❌ Embedded Vector DB PoC (Gen 2) failed:", err);
|
|
Deno.exit(1);
|
|
}
|
|
}
|