Full Text Search Python Packages

usearch

Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

flashrank

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

walrus

Lightweight Python utilities for working with Redis

whoosh-reloaded

Whoosh is a fast, featureful full-text indexing and searching library implemented in pure Python.

sqlalchemy-paradedb

The official SQLAlchemy integration for ParadeDB

apexbase

A High-performance HTAP embedded database. A reliable work partner.

infino

Embedded retrieval library built on Parquet. Fast, efficient, and scalable.

whoosh3

Fast, pure-Python full-text indexing and search. Actively maintained continuation of Whoosh / whoosh-reloaded. Install: pip install whoosh3

uqa

Embeddable Rust query engine unifying relational, full-text, vector, graph, and probabilistic retrieval under one typed algebra.

nxsearch

nxsearch: a full-text search engine

markdown-memory

MCP server that hands coding agents the one Markdown section that answers the question, not the whole file. Local hybrid search: BM25 keywords + ONNX embeddings in SQLite. No API keys, no network.

gist-search

The fastest CLI and agent-first code search tool, built on indexed trigram search with aggressive literal-match optimizations

mdcx

Convert a document collection to verified Markdown, package it into a single encrypted archive with its search index and provenance, and serve it to agents over the Model Context Protocol. Python 3.11+, Apache-2.0.

usearch-iscc

Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

sifts

Simple full text & vector search engine Python library

purrdf

PurRDF — one RDF 1.2 engine, one behavior, in Rust, Python, WebAssembly and C. Deterministic BM25 full-text search, exact GeoSPARQL 1.1 and embedding kNN answered from SPARQL, in-process, over one dataset: the three jobs a triple store usually kept PostgreSQL beside it for. Plus native codecs, RDFC-1.0, SHACL, ShEx, entailment and GTS transport.

django-paradedb

The official Django integration for ParadeDB

nlp4j-local-search

nlp4j-local-search

django-icv-search

Pluggable search for Django: swappable backends (Meilisearch, PostgreSQL, OpenSearch, Solr, Typesense, Vespa), auto-indexing, analytics, and merchandising

mem-mesh

Persistent memory for AI agents — hybrid vector + FTS5 search

twlaw

以本機 SQLite 查詢全國法規資料庫，支援中文全文檢索與章節層級重建 · Taiwan laws & regulations, queryable offline

kevy

kevy — a pure-Rust, zero-dependency, Redis-compatible serving engine: declared indexes, CJK full-text + vector search, views, CDC feeds, replication & failover, MCP

satchel-reader

A local-first reading queue: saves the real article text, not just the link, and makes it genuinely offline-searchable.

docsagent-mcp-zotero

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, local docs on the road). Native C++ search core: BM25 + passage ranking in ~15 ms. MCP server for Claude, Cursor, Cline & any MCP client.