keywords: ~~~,~~~,~~~, main_text: # 1. 機械学習 ~~~~~~~~~~~” “search_vector”, [<search_textをベクトル化した結果>]} {“seach_text”: “purpose: ~~~~~~~, keywords: ~~~,~~~,~~~, main_text: ## 1.1 教師あり学習~~~~~~~~~~~” “search_vector”, [<search_textをベクトル化した結果>]} {“seach_text”: “purpose: ~~~~~~~, keywords: ~~~,~~~,~~~, main_text: ~~~~~~~~~~~” “search_vector”, [<search_textをベクトル化した結果>]} {“seach_text”: “purpose: ~~~~~~~, keywords: ~~~,~~~,~~~, main_text: ## 1.2 教師なし学習 ~~~~~~~~~~~” “search_vector”, [<search_textをベクトル化した結果>]} {“seach_text”: “purpose: ~~~~~~~, keywords: ~~~,~~~,~~~, main_text: # 1. 機械学習 ~~~~~~~~~~~” “search_vector”, [<search_textをベクトル化した結果>]} 5 6 {“chunk”: “# 1. 機械学習 ~~~~~~~~~~”, “keywords”: [“~~~”, “~~~”, …], “purpose”: ”~~~~~~~~~~~~~~”, “questions” [“~~~~~”, “~~~~~”, …] } {“chunk”: “## 1.1 教師あり学習~~~~~~~~”, “keywords”: [“~~~”, “~~~”, …], “purpose”: ”~~~~~~~~~~~~~~”, “questions” [“~~~~~”, “~~~~~”, …] } {“chunk”: “~~~~~~~~~~~~~~~~~~~~~”, “keywords”: [“~~~”, “~~~”, …], “purpose”: ”~~~~~~~~~~~~~~”, “questions” [“~~~~~”, “~~~~~”, …] } {“chunk”: “## 1.2 教師なし学習~~~~~~~”, “keywords”: [“~~~”, “~~~”, …], “purpose”: ”~~~~~~~~~~~~~~”, “questions” [“~~~~~”, “~~~~~”, …] } {“chunk”: “~~~~~~~~~~~~~~~~~~~~~”, “keywords”: [“~~~”, “~~~”, …], “purpose”: ”~~~~~~~~~~~~~~”, “questions” [“~~~~~”, “~~~~~”, …] } 4 Embedding 情報を結合して search_textに 登録時はURLなど メタ情報なども足す