A pure Python trie data structure implementation.
A retry layer for HTTPX.
Static memory-efficient and fast Trie-like structures for Python.
Provides a country field for Django models.
SQL-based prefix tree inspired by pygtrie and python-diskcache
Build trie-based regular expressions from large word lists
pyahocorasick is a fast and memory efficient library for exact or approximate multi-pattern string search. With the ``ahocorasick.Automaton`` class, you can find multiple key string occurrences at once in some input text. You can use it as a plain dict-like Trie or convert a Trie to an automaton for efficient Aho-Corasick search. And pickle to disk for easy reuse of large automatons. Implemented in C and tested on Python 3.6+. Works on Linux, macOS and Windows. BSD-3-Cause license.
Retriever combining unstructured similarity and structured document traversal.
LangChain retriever for traversing document graphs on top of vector-based similarity search.
llama-index retrievers bm25 integration
Store/search CIDR prefixes in a trie structure.
Super-fast, efficiently stored Trie for Python.
A pure Python implementation of the trie data structure.
An AWS Labs Model Context Protocol (MCP) server for Bedrock Knowledge Base Retrieval
Python Logger plugin to send logs to Logentries
Efficient Trie-based regex unions for blacklist/whitelist filtering and one-pass mapping-based string replacing
A modern RAG ingestion pipeline from Nvidia
A log of what was already attempted in this repo, and why it didn't work.
Discover and retrieve water data from U.S. federal hydrologic web services.
High-level API for asynchronous requests with persistent caching.
List of existing countries and currencies
Asynchronous Python client for LaMetric TIME devices.
A Bayesian optimization research toolbox built on TensorFlow
Decorator for retrying exec a method
A python library for cardiac geometries
Registry for managing CSS and JS
A django model & fixture containing all data from the countries table of Geonames.org
A library containing retrieval related components in Gen AI applications.
Type-safe offline data for 250 countries, 5,327 states, and 156,169 cities, plus 14,058 county equivalents, with Pydantic models and lazy loading.
HanLP: Han Language Processing
Radix tree implementation
Judy array and digital trie engine for Python (clean-room Rust implementation)
Simple tools to define world locations from a set of topological faces and set algebra
Return useful information for every country in the ISO 3166 standard.
Symetrie Hexapod implementation for CGSE
Installable MCP server for the Retrieval API: academic-paper search + journal memory + ACE playbook + semantic code search
Python client for the Context Surfaces API — manage context surfaces and invoke MCP tools. Includes an optional CLI (ctxctl).
RTR Role Type Retrieval — RRF-heuristic DTD semantic-capable retriever for opencode (dual ONNX ensemble, CPU-first)
Fast multi-model retrieval runtime: ONNX and GGUF embeddings, reranking, and a declarative model contract
i18n for ISO 3166-1 country codes. We support Alpha-2, Alpha-3 and Numeric codes
llama-index retrievers bedrock integration
Nutrient SDK native libraries
Nutrient SDK Python bindings for document processing
Fast mutable UTF-8 trie exposed as a Python extension module
A module using prefix trees to store/search nucleotides sequences