功能演示 | CBETA x AI 語意搜尋 公開測試

[AI‑Powered Semantic Search — public beta]

cbss

CBETA Online「語意搜尋」功能開放測試!

法鼓文理學院結合 OpenAI API 與 RAG(Retrieval‑Augmented Generation)技術,首次將生成式 AI 應用於 CBETA 資料庫,為線上版 CBETA Online 帶來不同的經文檢索體驗。

與傳統關鍵詞搜尋不同,您只需輸入一行問題或主題,系統即以語意向量比對,找出最相關段落,整合重點、引經據典,並提出延伸議題。所對比的經文依相關度排序,連接 CBETA Online 原文。

搜尋範例:

  • 請問龍樹菩薩大約是在佛教哪個時期?
  • 找出與月亮和兔子相關的故事
  • 佛陀有教人如何瘦身或增進健康嗎?
  • 如何修行佛法獲得解脫

目前可鎖定「阿含」、「律」等 23 部類;未來或可另指定藏經、叢書等。詳見下方〈操作引導〉。

歡迎試用並回饋寶貴意見!

P.S.: 更多詳情,請線上參與 5/22 (四) 2025 法鼓數典專案春季成果發表會,CBETA 執行長洪振洲教授將親自分享本實驗與後續規劃。

^頁首


CBETA Online now offers a public beta of its experimental feature Semantic Search!

Developed by the Dharma Drum Institute of Liberal Arts using OpenAI API and Retrieval Augmented Generation (RAG) technology, this marks the team’s first attempt to integrate generative AI into the CBETA database.

Unlike traditional keyword search, one simply enters a question or topic. The engine compares the topic to vectorised CBETA texts, retrieves the most relevant passages, and generates an overview with references and related questions. Text references are also ranked by relevance and link to the texts in CBETA Online.

Try searching (Chinese input and output):

  • 請問龍樹菩薩大約是在佛教哪個時期 (When did Nāgārjuna live)
  • 找出與月亮和兔子相關的故事 (Stories that link the moon and a rabbit)
  • 佛陀有教人如何瘦身或增進健康嗎 (Did the Buddha teach ways to lose weight or become healthier)
  • 如何修行佛法獲得解脫 (How to practise Dharma for liberation)

At the moment one may filter by thematic groups (e.g., ĀgamaVinaya), with more options—canons, series, and beyond—planned soon. See Quick Guide below for details.

We invite you to explore this feature and would love to hear from you!

P.S.:  For a deeper dive, join us online on Thursday, May 22 for the 2025 Spring Showcase of Dharma Drum Digital Archive Projects (法鼓數典專案春季成果發表會). Prof. Jenjou Hung, CBETA CEO, will share firsthand updates on this experiment and its future roadmap. 

^TOP


操作引導 Quick Guide

1. 開啟「語意搜尋Launch Semantic Search

在 CBETA Online 首頁點選 「語意搜尋」。

From CBETA Online homepage, click “Semantic Search”.

2. 輸入問題 Enter a query

在搜尋框輸入主題,按 Search。

Type a question or topic into the search bar and hit Search.

(選用) 設定搜尋範圍:點 Filter,勾選部類後再搜尋,以聚焦資料。

(Optional) Set Search Scope: for a more focused experience, click Filter and select thematic group(s) before searching.

3. 搜尋結果 Result

綜合說明:AI 整合前 20 筆相關經文的重點。

Summary: AI synthesizes key points from the 20 most relevant passages.

相關經文:列出段落、顯示相關度,並連結原文。

Related Texts: Lists each excerpt, shows its relevance score, and links directly to the original text on CBETA Online.

相關問題:可延伸探索的議題。

Next Question: Suggest related topics for further exploration.

4. 意見回饋 Feedbackimage

點一下右下角的意見回饋泡泡,讓我們知道您的使用心得!

Click the feedback bubble in the bottom-right corner and let us know how it worked for you!

^TOP