
This is a practical Agentic RAG system MVP that accurately automatically determines the expertise granularity (fine/coarse) of questions related to construction technology standards at 96% and selects the optimal RAG system (ColBERT/Naive). Four RAG systems were built targeting the technical standards of river sand control dams published in November 2025, and accuracy and speed were compared for 200 questions with different granularity of expertise.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
1
±0 (Oct 13〜)
Last commit
Nov 2025
Created on GitHub
Nov 8, 2025
Listed
Feb 17, 2026
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | — |
| Jan 2026 | — |
| Feb 2026 | 1 |
| Mar 2026 | 1 |
| Apr 2026 | 1 |
| May 2026 | 1 |
| Jun 2026 | 1 |
| Jul 2026 | 1 |
| Aug 2026 | 1 |
| Sep 2026 | 1 |
| Oct 2026 | 1 |
| Nov 2026 | 1 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
ja.text8Hironsan113Japanese text8 corpus for word embedding.
JapaneseWordSimilarityDatasettmu-nlp103Japanese Word Similarity Dataset
jqarahotchpotch45JQaRA: Japanese Question Answering with Retrieval Augmentation - 検索拡張(RAG)評価のための日本語Q&Aデータセット
asdcmegagonlabs25Accommodation Search Dialog Corpus (宿泊施設探索対話コーパス)
TwitterCorpustmu-nlp21Capital Japanese Twitter Corpus
aozorasearchmyokoym21The full-text search system for Aozora Bunko by Groonga. 青空文庫全文検索ライブラリ兼Webアプリ。
Resources in similar research fields
- RAG-Evaluation-Dataset-JAallganize246Provides a Japanese RAG benchmark across five industry domains—finance, telecom, manufacturing, public, retail—by publishing datasets, an automatic evaluation framework, and comparative results for models such as Claude 3.5‑Sonnet, GPT‑4o, and others.HF datasetShared: Annotation and Dataset Development
- financial-lakehouseYoshi-Dai5kA gated, non‑commercial derivative dataset of EDINET XBRL financial data that prohibits redistribution, AI training, and commercial use, requiring manual approval for access.HF datasetShared: Annotation and Dataset Development
- Nemotron-Personas-Japannvidia5kNemotron‑Personas‑Japan is an open‑source, CC BY 4.0 dataset of high‑quality, synthetically generated Japanese personas—incorporating name, gender, age, background, marital status, education, occupation and location—grounded in real‑world demographic, geographic and personality distributions, engineered with probabilistic graphical models and GPT‑OSS‑120B to enhance diversity, reduce bias, prevent model collapse, assist sovereign AI development, and support commercial use.HF datasetShared: Annotation and Dataset Development
- mc4-jaizumi-lab2kDataset card for the Japanese MC4 dataset (mc4-ja).HF datasetShared: Annotation and Dataset Development
- RyokoAI_Syosetu711Kbotp2kSyosetu711K is a Japanese dataset of ~711,700 novels scraped from 小説家になろう on March 26‑27 2023, providing full text and metadata (title, author, NCode, synopsis, etc.) for unsupervised text generation and classification tasks.HF datasetShared: Annotation and Dataset Development
- Japanese-Eroge-Voice-V2NandemoGHS1kJapanese‑Eroge‑Voice‑V2 offers 2,657 hours of anonymized 1,033,142 eroge audio–transcription pairs (mostly female, NSFW), MIT‑licensed for academic research.HF datasetShared: Annotation and Dataset Development