{"id":51139630,"url":"https://github.com/philippe2803/contentmap","last_synced_at":"2026-06-25T21:04:24.064Z","repository":{"id":216133087,"uuid":"740559411","full_name":"philippe2803/contentmap","owner":"philippe2803","description":"Build a RAG dataset for your domain in just a few lines of codes, using your XML sitemap","archived":false,"fork":false,"pushed_at":"2024-08-24T10:20:52.000Z","size":197,"stargazers_count":29,"open_issues_count":2,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-08-25T10:56:17.983Z","etag":null,"topics":["python","rag","sqlite"],"latest_commit_sha":null,"homepage":"https://philippeoger.com/pages/can-we-rag-the-whole-web","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/philippe2803.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","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":"2024-01-08T15:38:37.000Z","updated_at":"2024-08-25T10:56:17.984Z","dependencies_parsed_at":"2024-02-26T21:25:06.316Z","dependency_job_id":"e0e93b60-3c15-4307-a147-e694495c462d","html_url":"https://github.com/philippe2803/contentmap","commit_stats":null,"previous_names":["philippe2803/contentmap"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/philippe2803/contentmap","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philippe2803%2Fcontentmap","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philippe2803%2Fcontentmap/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philippe2803%2Fcontentmap/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philippe2803%2Fcontentmap/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/philippe2803","download_url":"https://codeload.github.com/philippe2803/contentmap/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philippe2803%2Fcontentmap/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34792247,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-25T02:00:05.521Z","response_time":101,"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":["python","rag","sqlite"],"created_at":"2026-06-25T21:04:23.461Z","updated_at":"2026-06-25T21:04:24.057Z","avatar_url":"https://github.com/philippe2803.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Content map\n\nA way to share content from a specific domain using SQLite as an alternative to \nRSS feeds. The purpose of this library is to simply create a dataset for all the\ncontent on your website, using the XML sitemap as a starting point.  \n\nPossibility to include vector search similarity features in the dataset very easily.\n\nArticle that explains the rationale behind this type of datasets [here](https://philippeoger.com/pages/can-we-rag-the-whole-web/).\n\n\n## Installation\n\n```bash\n\npip install contentmap\n\n```\n\n## Quickstart\n\nTo build your contentmap.db with vector search capabilities and containing all \nyour content using your XML sitemap as a starting point, you only need to write the\nfollowing: \n\n```python\nfrom contentmap.sitemap import SitemapToContentDatabase\n\ndatabase = SitemapToContentDatabase(\n    sitemap_sources=[\"https://yourblog.com/sitemap.xml\"],\n    concurrency=10,\n    include_vss=True\n)\ndatabase.build()\n\n```\n\nThis will automatically create the SQLite database file, with vector search \ncapabilities (piggybacking on sqlite-vss integration on Langchain).\n\nThanks to @medoror for contributing.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphilippe2803%2Fcontentmap","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fphilippe2803%2Fcontentmap","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphilippe2803%2Fcontentmap/lists"}