Why decay similarity scores by age?

Pure vector similarity ignores time, so a perfectly-matching but stale document can outrank a slightly-less-similar fresh one. In domains like news, pricing, or policy, recency matters, and decay folds age into the ranking.

What does half-life mean here?

Half-life is the age at which the freshness factor drops to 0.5 in the exponential model. A 30-day half-life means a 30-day-old document keeps half its score, a 60-day-old document a quarter, and so on.

How do the three decay models differ?

Exponential decays smoothly and never reaches zero, good for gradual staleness. Linear drops to zero at a chosen cutoff age. Step keeps full score until a cutoff then applies a fixed penalty, useful when freshness is binary (in-window vs out-of-window).

Does this replace the vector search?

No. It is a re-ranking layer applied after retrieval. You run your normal similarity search, then multiply each result's score by the freshness factor here to get the final order.

Is anything sent to a server?

No. All decay math runs locally in your browser. Your ages and scores never leave the page.

Embedding Freshness Decay Calculator

Vector similarity is blind to time. In domains where freshness matters — news, prices, policies, support docs — a stale document that happens to embed close to the query can beat a newer, slightly-less-similar one. A freshness decay layer fixes that by multiplying each similarity score by a factor that shrinks with document age. This calculator lets you model that factor and see the re-ranked result before you wire it into your pipeline.

How it works

For each document you supply an age in days and a base similarity from your vector search. The tool computes a freshness factor with the model you choose and multiplies it into the score:

Exponential: factor = 0.5 ^ (age / half-life) — smooth, never zero.
Linear: factor = max(0, 1 − age / cutoff) — straight-line drop to zero at the cutoff.
Step: factor = 1 while age ≤ cutoff, otherwise a fixed penalty.

It then re-sorts the documents by the adjusted score so you can compare the original and recency-aware rankings.

Choosing a model and half-life

Match the half-life to how fast your domain goes stale: hours for breaking news, weeks for product docs, months for reference material.
Use step decay when freshness is effectively binary (inside vs outside a window).
Keep base similarities on a consistent scale (cosine 0–1 is typical) so the multiplier behaves predictably.

Tips

Apply decay as a post-retrieval re-rank, not inside the ANN search itself.
If fresh documents start dominating obviously-irrelevant matches, lengthen the half-life.
Store each document’s timestamp as metadata so age is cheap to compute at query time.