{"id":20314741,"url":"https://github.com/mazzasaverio/pipeline-docs-data-extractor","last_synced_at":"2025-08-13T18:34:36.495Z","repository":{"id":215496964,"uuid":"739079995","full_name":"mazzasaverio/pipeline-docs-data-extractor","owner":"mazzasaverio","description":"(Let's build a) Robust pipeline for extracting structured data from various documents","archived":false,"fork":false,"pushed_at":"2024-05-04T14:06:37.000Z","size":91,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-05-04T20:53:38.538Z","etag":null,"topics":["airflow","data-engineer","data-engineering","etl-pipeline","large-language-models","pdf-text-extraction","unstructured"],"latest_commit_sha":null,"homepage":"","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/mazzasaverio.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":"2024-01-04T18:13:54.000Z","updated_at":"2024-05-04T14:06:40.000Z","dependencies_parsed_at":"2024-01-14T14:37:07.101Z","dependency_job_id":"eac11583-a64a-47da-a0c2-abe69e523c6b","html_url":"https://github.com/mazzasaverio/pipeline-docs-data-extractor","commit_stats":{"total_commits":29,"total_committers":2,"mean_commits":14.5,"dds":0.03448275862068961,"last_synced_commit":"2d5499bd1cbee98625e1970a2b0e7a21f7cacd09"},"previous_names":["mazzasaverio/clean-text","mazzasaverio/etl-texts","mazzasaverio/pipeline-docs-data-extractor"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mazzasaverio%2Fpipeline-docs-data-extractor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mazzasaverio%2Fpipeline-docs-data-extractor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mazzasaverio%2Fpipeline-docs-data-extractor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mazzasaverio%2Fpipeline-docs-data-extractor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mazzasaverio","download_url":"https://codeload.github.com/mazzasaverio/pipeline-docs-data-extractor/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224668362,"owners_count":17349967,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["airflow","data-engineer","data-engineering","etl-pipeline","large-language-models","pdf-text-extraction","unstructured"],"created_at":"2024-11-14T18:16:32.587Z","updated_at":"2024-11-14T18:16:32.848Z","avatar_url":"https://github.com/mazzasaverio.png","language":"Python","readme":null,"funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmazzasaverio%2Fpipeline-docs-data-extractor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmazzasaverio%2Fpipeline-docs-data-extractor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmazzasaverio%2Fpipeline-docs-data-extractor/lists"}