{"id":48926353,"url":"https://github.com/tochukaso/chat-bot","last_synced_at":"2026-04-17T07:02:40.488Z","repository":{"id":249494782,"uuid":"801811275","full_name":"tochukaso/chat-bot","owner":"tochukaso","description":"Experiments to improve Chat Bot accuracy using RAGs","archived":false,"fork":false,"pushed_at":"2024-08-04T08:01:37.000Z","size":21106,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-08-04T10:48:01.094Z","etag":null,"topics":["chatbot","python3","rag"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tochukaso.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-17T00:51:11.000Z","updated_at":"2024-08-04T08:01:40.000Z","dependencies_parsed_at":"2024-08-03T10:56:16.026Z","dependency_job_id":null,"html_url":"https://github.com/tochukaso/chat-bot","commit_stats":null,"previous_names":["tochukaso/chat-bot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/tochukaso/chat-bot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tochukaso%2Fchat-bot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tochukaso%2Fchat-bot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tochukaso%2Fchat-bot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tochukaso%2Fchat-bot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tochukaso","download_url":"https://codeload.github.com/tochukaso/chat-bot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tochukaso%2Fchat-bot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31918838,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T18:22:33.417Z","status":"online","status_checked_at":"2026-04-17T02:00:06.879Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chatbot","python3","rag"],"created_at":"2026-04-17T07:02:40.330Z","updated_at":"2026-04-17T07:02:40.480Z","avatar_url":"https://github.com/tochukaso.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# chat-bot\n\nこのプロジェクトは、RAGの精度向上を実験するためのサンプルアプリケーションです。\n\nWikipediaの情報を元にRAGの精度向上方法を検討します。\n\n\u003cdetails\u003e\n\u003csummary\u003eWikipediaデータ\u003c/summary\u003e\n\nWikipediaのデータダンプを取得したところ、圧縮状態で3.7GB,解凍後は15.8GBとなり、ローカル環境ではデータを扱うのが難しいため、\n野球に関連する[データを個別取得](https://ja.wikipedia.org/wiki/%E7%89%B9%E5%88%A5:%E3%83%87%E3%83%BC%E3%82%BF%E6%9B%B8%E3%81%8D%E5%87%BA%E3%81%97)しました。\n\n取得したデータは12MBほどで、プロ野球、メジャーリーグ、WBC、甲子園、など野球に関連する内容から、神話、土地情報、歴史、など様々な情報が含まれています。\n\n\u003c/details\u003e\n\n## General Requirement\n\n- [Python 3.12.4](https://www.python.org/downloads/release/python-3124/)\n- [Node.js](https://nodejs.org/) (v18.16.0 以上推奨)\n- [npm](https://www.npmjs.com/) (v9.5.1 以上推奨)\n\n# 検証結果\n\n検証に使用したAPI\n\n- GPT-4o mini\n- text-embedding-3-large\n\n1999年の夏の甲子園の決勝戦について解説してもらいます。\n\n[1999年の夏の甲子園](https://ja.wikipedia.org/wiki/%E7%AC%AC81%E5%9B%9E%E5%85%A8%E5%9B%BD%E9%AB%98%E7%AD%89%E5%AD%A6%E6%A0%A1%E9%87%8E%E7%90%83%E9%81%B8%E6%89%8B%E6%A8%A9%E5%A4%A7%E4%BC%9A)の決勝戦は 8/21 岡山理大付属高校　対 桐生第一高校です。\n\n試合は 1 - 14 で桐生第一高校が勝利しました。\n甲子園のキャッチフレーズは「君がいる甲子園が好き」らしいです。\n\n## RAGを使わずに単純に質問した場合\n\n![no rag](/images/no_rag.png)\n1998年の夏の甲子園の解説と思わせながら、架空の結果を出力しています。\n\n## RAGを使って参考情報を追加して質問した場合\n\n![rag_1](/images/rag_1.png)\n\n1998年の夏の決勝戦のことを解説しています。\n\nPL学園帯横浜延長17回 というタイトルの記事が最も類似度が高かったのですが、それでも **.0203** と非常に低い値でした。\n\nここからはRAGの精度を向上するためにできることをやっていきます。\n\n## Wikipediaの情報を要約したものをベクトルデータにしてRAGを構築した場合\n\n\n\n## Front end\n\n### 起動方法\n\nfront-end ディレクトリに移動して、以下のコマンドを実行してください。\n\n``` sh\nnpm start\n```\n\nFront end は [http://localhost:3000](http://localhost:3000) でアクセスできます。\n\nREADME は [こちら](front-end/README.md)\n\n## Back end\n\nREADME は [こちら](back-end/README.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftochukaso%2Fchat-bot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftochukaso%2Fchat-bot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftochukaso%2Fchat-bot/lists"}