search_vector

Returns the top-<code>n</code> matches from an embedding matrix for one or more query vectors.
Subject-first: <code>embeddings</code> (haystack) then <code>query</code> (needle), pipe-friendly.

A lightweight toolkit for text retrieval and NLP with a consistent and
predictable API organized around four actions: fetching, reading,
processing, and searching. Functions cover the full pipeline from web
data acquisition to text processing and indexing. Multiple search
strategies are supported including regex, BM25 keyword ranking, cosine
similarity, and dictionary matching. Pipe-friendly with no heavy
dependencies and all outputs are plain data frames. Also useful as a
building block for retrieval-augmented generation pipelines and
autonomous agent workflows.

Jason Timm

textpress

A Lightweight and Versatile NLP Toolkit

search_vector function

<dl><dt>embeddings</dt>
<dd>A numeric or sparse matrix of embeddings (rows = searchable units).</dd>
<dt>query</dt>
<dd>A character (row name in <code>embeddings</code>), a numeric vector (single query),
or a numeric matrix (multiple queries).</dd>
<dt>n</dt>
<dd>Number of results to return per query (default 10).</dd></dl>

Arguments

Vector search by cosine similarity — search_vector

<dl>

<dt>embeddings</dt>
<dd>A numeric or sparse matrix of embeddings (rows = searchable units).</dd>


<dt>query</dt>
<dd>A character (row name in <code>embeddings</code>), a numeric vector (single query),
or a numeric matrix (multiple queries).</dd>


<dt>n</dt>
<dd>Number of results to return per query (default 10).</dd>

</dl>

search_vector: Vector search by cosine similarity

Description

Usage

Value

Arguments