
日本語辞書 by Rust, support Telegram bot, AWS Lambda and Cloudflare Workers. Support LLM and search RAG.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
73
+1 (Oct 13〜)
Last commit
Nov 2026
Created on GitHub
Jul 18, 2018
Listed
Jan 27, 2026
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | — |
| Jan 2026 | 69 |
| Feb 2026 | 69 |
| Mar 2026 | 70 |
| Apr 2026 | 70 |
| May 2026 | 70 |
| Jun 2026 | 71 |
| Jul 2026 | 72 |
| Aug 2026 | 72 |
| Sep 2026 | 72 |
| Oct 2026 | 73 |
| Nov 2026 | 73 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
koharukoharu-rs6.7kAutomated manga translation tool with LLM, written in Rust.
daachorsedaac-tools286A fast implementation of the Aho-Corasick algorithm using the compact double-array data structure in Rust.
lindera-tantivylindera71Lindera tokenizer for Tantivy.
find-simdocdaac-tools62Finding all pairs of similar documents time- and memory-efficiently
mikkekimushun110149Local search CLI for Japanese Markdown notes 👀 — BM25 full-text search (SQLite FTS5) + optional local semantic/hybrid. Single binary, no external API usage, for AI coding agents.
crawdaddaac-tools40Rust library of natural language dictionaries using character-wise double-array tries.
Resources in similar research fields
azure-search-openai-demonohanaga46In this sample, we demonstrate several approaches to creating an experience similar to ChatGPT for proprietary data using the Retrieval Augmented Generation pattern.Shared: Embeddings, search & RAG・Large language models
rag-japaneseakimfromparis10Open source RAG with Llama Index for Japanese LLM in low resource setttingShared: Embeddings, search & RAG・Large language models- llm-course-final-2026bumbuboon13kJapanese Wikipedia‑based RAG dataset for the LLM course final competition, containing ~1 million text chunks and a search index.HF datasetShared: Embeddings, search & RAG・Large language models
- JaGovFaqs-22kmatsuxr169A Japanese FAQ dataset extracted by hand from government websites, licensed CC‑BY‑4.0, intended for instruction tuning and RAG testing of large language models with high-quality Q&A pairs and source URLs provided.HF datasetShared: Embeddings, search & RAG・Large language models
- japanese-gpt-neox-smallrinna656kA 12‑layer, 768‑hidden Japanese GPT‑NeoX model trained on CC‑100, C4, and Wikipedia, compatible with Huggingface, with an optional toy prefix‑tuning weight that forces each sentence to end with a smiling‑face emoji.HF modelShared: Large language models
elasticsearchelastic78kFree and Open Source, Distributed, RESTful Search Engine.MultilingualShared: Embeddings, search & RAG