open-brainy/src/utils/distance.ts

/**
 * Distance functions for vector similarity calculations.
 *
 * Pure-JavaScript implementations using allocation-free indexed loops: a single
 * pass over the two vectors with scalar accumulators and no per-element closures
 * or intermediate objects. This is the open-core distance path (the native
 * provider owns the SIMD/quantized billion-scale path); for the small/medium
 * vectors it serves (e.g. 384-dim sentence embeddings) a tight loop keeps the
 * whole computation in registers with zero GC pressure.
 *
 * MEASURED (tests/benchmarks/distance-microbench.mjs, dim=384, N=20000, median
 * of 41): rewriting cosine from an object-accumulating `reduce` to this loop is
 * ~6x on `number[]`; euclidean ~1.4x. (`number[]` is also measurably faster than
 * `Float32Array` here — V8 widens f32→f64 on every element read — so the
 * resident representation stays `number[]`.)
 */

import { DistanceFunction, Vector } from '../coreTypes.js'

/**
 * Calculates the Euclidean (L2) distance between two vectors.
 * Lower values indicate higher similarity.
 */
export const euclideanDistance: DistanceFunction = (a: Vector, b: Vector): number => {
  if (a.length !== b.length) {
    throw new Error('Vectors must have the same dimensions')
  }

  let sum = 0
  const len = a.length
  for (let i = 0; i < len; i++) {
    const diff = a[i] - b[i]
    sum += diff * diff
  }
  return Math.sqrt(sum)
}

/**
 * Calculates the cosine distance between two vectors.
 * Lower values indicate higher similarity. Range: 0 (identical) to 2 (opposite).
 */
export const cosineDistance: DistanceFunction = (a: Vector, b: Vector): number => {
  if (a.length !== b.length) {
    throw new Error('Vectors must have the same dimensions')
  }

  let dotProduct = 0
  let normA = 0
  let normB = 0
  const len = a.length
  for (let i = 0; i < len; i++) {
    const av = a[i]
    const bv = b[i]
    dotProduct += av * bv
    normA += av * av
    normB += bv * bv
  }

  if (normA === 0 || normB === 0) {
    return 2 // Maximum distance for zero vectors
  }

  const similarity = dotProduct / (Math.sqrt(normA) * Math.sqrt(normB))
  // Convert cosine similarity (-1 to 1) to distance (0 to 2)
  return 1 - similarity
}

/**
 * Calculates the Manhattan (L1) distance between two vectors.
 * Lower values indicate higher similarity.
 */
export const manhattanDistance: DistanceFunction = (a: Vector, b: Vector): number => {
  if (a.length !== b.length) {
    throw new Error('Vectors must have the same dimensions')
  }

  let sum = 0
  const len = a.length
  for (let i = 0; i < len; i++) {
    sum += Math.abs(a[i] - b[i])
  }
  return sum
}

/**
 * Calculates the dot-product similarity between two vectors, negated to a
 * distance metric (lower is better).
 */
export const dotProductDistance: DistanceFunction = (a: Vector, b: Vector): number => {
  if (a.length !== b.length) {
    throw new Error('Vectors must have the same dimensions')
  }

  let dotProduct = 0
  const len = a.length
  for (let i = 0; i < len; i++) {
    dotProduct += a[i] * b[i]
  }
  return -dotProduct
}

/**
 * Batch distance calculation: the query vector against each candidate.
 *
 * With the distance functions now allocation-free indexed loops, this is a thin
 * map over the (monomorphic, JIT-inlined) `distanceFunction` — no worker, no
 * stringify/`new Function` reconstruction. Kept `async` for call-site
 * compatibility with the HNSW search path.
 *
 * @param queryVector The query vector to compare against all candidates.
 * @param vectors The candidate vectors.
 * @param distanceFunction The distance function to use (default: Euclidean).
 * @returns The distances, index-aligned with `vectors`.
 */
export async function calculateDistancesBatch(
  queryVector: Vector,
  vectors: Vector[],
  distanceFunction: DistanceFunction = euclideanDistance
): Promise<number[]> {
  const out = new Array<number>(vectors.length)
  for (let i = 0; i < vectors.length; i++) {
    out[i] = distanceFunction(queryVector, vectors[i])
  }
  return out
}