{"_id":"@drumnistnakano/ai-ocr-markdown-convertor","name":"@drumnistnakano/ai-ocr-markdown-convertor","dist-tags":{"latest":"0.1.2"},"versions":{"0.1.2":{"name":"@drumnistnakano/ai-ocr-markdown-convertor","version":"0.1.2","description":"AI powered OCR and document conversion tool that converts various file formats to Markdown","main":"dist/index.js","bin":{"ai-ocr-convert":"dist/cli.js"},"scripts":{"build":"tsc","start":"node dist/cli.js","dev":"ts-node src/cli.ts","prepublishOnly":"npm run build"},"keywords":["ai","ocr","markdown","converter","document","pdf","excel","word","powerpoint","openai","gpt-4o"],"author":{"name":"Yoshiyuki Nakano"},"license":"MIT","repository":{"type":"git","url":"git+https://github.com/drumnistnakano/ai-ocr-markdown-convertor.git"},"homepage":"https://github.com/drumnistnakano/ai-ocr-markdown-convertor","bugs":{"url":"https://github.com/drumnistnakano/ai-ocr-markdown-convertor/issues"},"dependencies":{"chalk":"^4.1.2","date-fns":"^4.1.0","dotenv":"^16.3.1","glob":"^10.3.10","zerox":"^1.1.6"},"devDependencies":{"@types/glob":"^8.1.0","@types/node":"^20.10.5","ts-node":"^10.9.2","typescript":"^5.3.3"},"engines":{"node":">=20.0.0"},"_id":"@drumnistnakano/ai-ocr-markdown-convertor@0.1.2","gitHead":"eb57475e6e18477303064449dc75742a35e09e62","types":"./dist/index.d.ts","_nodeVersion":"20.18.3","_npmVersion":"10.8.2","dist":{"integrity":"sha512-QZPnEoOrnTR0cw76v5oqiuCsY2c2PIx9GvWSM/uT99ovkkE9wD5ANZq3Z8nDnG0wD2CK40K0jJwbn8SLNJ28bg==","shasum":"69d1ae16a7f174bd81b1ddebc33de8223ca022c3","tarball":"https://registry.npmjs.org/@drumnistnakano/ai-ocr-markdown-convertor/-/ai-ocr-markdown-convertor-0.1.2.tgz","fileCount":11,"unpackedSize":27218,"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/@drumnistnakano%2fai-ocr-markdown-convertor@0.1.2","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQD2Ho2MagZNt8zZZRjb24YFWW0h/70HBXslJYrQFURDdgIhAOeGvGSyeEV8/pVy+7QuMtEKUMPe/DshexO4cQD0RGuu"}]},"_npmUser":{"name":"drumnistnakano","email":"drumnist.nakano@gmail.com"},"directories":{},"maintainers":[{"name":"drumnistnakano","email":"drumnist.nakano@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/ai-ocr-markdown-convertor_0.1.2_1742222971242_0.9309536692818738"},"_hasShrinkwrap":false}},"time":{"created":"2025-03-17T14:49:31.124Z","0.1.2":"2025-03-17T14:49:31.439Z","modified":"2025-03-17T14:49:31.849Z"},"maintainers":[{"name":"drumnistnakano","email":"drumnist.nakano@gmail.com"}],"description":"AI powered OCR and document conversion tool that converts various file formats to Markdown","homepage":"https://github.com/drumnistnakano/ai-ocr-markdown-convertor","keywords":["ai","ocr","markdown","converter","document","pdf","excel","word","powerpoint","openai","gpt-4o"],"repository":{"type":"git","url":"git+https://github.com/drumnistnakano/ai-ocr-markdown-convertor.git"},"author":{"name":"Yoshiyuki Nakano"},"bugs":{"url":"https://github.com/drumnistnakano/ai-ocr-markdown-convertor/issues"},"license":"MIT","readme":"# AI OCR Markdown Convertor\n\nAI を活用してさまざまな形式のドキュメントを Markdown に変換するツール。\n\n## 特徴\n\n- 複数のファイル形式をサポート（PDF、Word、Excel、など）\n- OpenAI の GPT-4 Vision モデルを使用\n- ドキュメントの構造を保持した Markdown 変換\n- 日本語を含む多言語対応\n\n## インストール\n\n### 必要条件\n\n- Node.js 20 以上\n- OpenAI API Key\n\n### インストール方法\n\n```bash\n# npmからグローバルにインストール\nnpm install -g ai-ocr-markdown-convertor\n\n# または、スコープ付きパッケージの場合\nnpm install -g @drumnistnakano/ai-ocr-markdown-convertor\n\n# または、リポジトリからクローンして使用する場合\ngit clone https://github.com/yourusername/ai-ocr-markdown-convertor.git\ncd ai-ocr-markdown-convertor\nnpm install\nnpm run build\nnpm link\n```\n\n## 使用方法\n\n### API キーの設定\n\n以下のいずれかの方法で OpenAI API キーを設定してください：\n\n1. 環境変数として設定\n\n```bash\nexport OPENAI_API_KEY=your_api_key\n```\n\n2. プロジェクトルートに`.env`ファイルを作成\n\n```\nOPENAI_API_KEY=your_api_key\n```\n\n### コマンド実行\n\n```bash\n# 指定したディレクトリ内のファイルを変換\nai-ocr-convert /path/to/input/directory\n```\n\n変換されたファイルは、入力ディレクトリと同じ階層に日付付きのディレクトリ（例：`input_directory_20240317123456`）として出力されます。元のディレクトリ構造が保持されるため、たとえば `/path/to/input/directory/folder1/document.pdf` は `/path/to/input_directory_20240317123456/folder1/document.md` として出力されます。\n\n## サポートされているファイル形式\n\n- PDF (`.pdf`)\n- Microsoft Word (`.doc`, `.docx`)\n- Microsoft Excel (`.xls`, `.xlsx`)\n- OpenDocument (`.odt`, `.ott`)\n- Rich Text Format (`.rtf`)\n- Plain Text (`.txt`)\n- HTML (`.html`, `.htm`)\n- XML (`.xml`)\n- CSV (`.csv`)\n- TSV (`.tsv`)\n- Microsoft PowerPoint (`.ppt`, `.pptx`)\n- OpenDocument Presentation (`.odp`, `.otp`)\n","readmeFilename":"README.md","_rev":"1-0713a32aa57383176cd6333652559110"}