(add! idx id v)(add! idx id v metadata)Adds or replaces id with vector v. Metadata is stored outside hnswlib.
Adds or replaces id with vector v. Metadata is stored outside hnswlib.
(add-batch! idx items)Adds each {:id .. :vector .. :metadata ..} item and returns the count added.
Adds each {:id .. :vector .. :metadata ..} item and returns the count added.
(get-item idx id)Returns {:id .. :vector float[] .. :metadata ..} for id, or nil.
Returns {:id .. :vector float[] .. :metadata ..} for id, or nil.
(index opts)Creates an embedded vector index handle.
:type is :hnsw by default. :exact uses exhaustive exact search, O(n) per query, with no tuning knobs; it is useful as ground truth or for small corpora. :ef trades recall for speed during search; higher values improve recall.
Creates an embedded vector index handle. :type is :hnsw by default. :exact uses exhaustive exact search, O(n) per query, with no tuning knobs; it is useful as ground truth or for small corpora. :ef trades recall for speed during search; higher values improve recall.
(load-index path)Loads an index handle from path, a directory containing index.bin and meta.edn.
:type in meta.edn selects :hnsw or :exact. Legacy saves without :type load as :hnsw. :exact uses exhaustive exact search, O(n) per query, with no tuning knobs; it is useful as ground truth or for small corpora.
Loads an index handle from path, a directory containing index.bin and meta.edn. :type in meta.edn selects :hnsw or :exact. Legacy saves without :type load as :hnsw. :exact uses exhaustive exact search, O(n) per query, with no tuning knobs; it is useful as ground truth or for small corpora.
(remove! idx id)Removes id from the index. Returns true when an item was removed.
Removes id from the index. Returns true when an item was removed.
(save idx path)Persists idx into path, a directory created when absent. Returns path.
Persists idx into path, a directory created when absent. Returns path.
(search idx query-vec k)(search idx query-vec k {:keys [filter] :as opts})Returns nearest results best-first.
For :cosine and :dot, :score is a similarity where higher is better. For :euclidean, :score is L2 distance where lower is better.
With opts, :filter is a predicate over the result map
({:id .. :score .. :metadata ..}); only results satisfying it are
returned, still k best-first. Filtering is implemented by over-fetching
candidates from the index and growing the candidate set (doubling, up to
the full index) until k matches are found, so a highly selective filter
on a large index costs proportionally more. Exact indexes fetch the full
index size when filtering because exact search is already exhaustive.
Returns nearest results best-first.
For :cosine and :dot, :score is a similarity where higher is better. For
:euclidean, :score is L2 distance where lower is better.
With opts, `:filter` is a predicate over the result map
(`{:id .. :score .. :metadata ..}`); only results satisfying it are
returned, still k best-first. Filtering is implemented by over-fetching
candidates from the index and growing the candidate set (doubling, up to
the full index) until k matches are found, so a highly selective filter
on a large index costs proportionally more. Exact indexes fetch the full
index size when filtering because exact search is already exhaustive.(size idx)Returns the number of indexed items.
Returns the number of indexed items.
cljdoc builds & hosts documentation for Clojure/Script libraries
| Ctrl+k | Jump to recent docs |
| ← | Move to previous article |
| → | Move to next article |
| Ctrl+/ | Jump to the search field |