{"id":124997,"url":"https://github.com/Dicklesworthstone/llm_aided_ocr","last_synced_at":"2026-08-21T23:31:31.457Z","repository":{"id":184078803,"uuid":"671266493","full_name":"Dicklesworthstone/llm_aided_ocr","owner":"Dicklesworthstone","description":"Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs","archived":false,"fork":false,"pushed_at":"2026-08-03T04:19:28.000Z","size":1458,"stargazers_count":2989,"open_issues_count":0,"forks_count":214,"subscribers_count":22,"default_branch":"main","last_synced_at":"2026-08-19T22:34:38.697Z","etag":null,"topics":["ai-assist","llama2","llm","ocr","ocr-correction","tesseract"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Dicklesworthstone.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"claude":null,"gemini":null,"cursor":null,"copilot":null,"dco":null,"cla":null,"disclosure":null}},"created_at":"2023-07-26T23:54:37.000Z","updated_at":"2026-08-18T11:43:05.000Z","dependencies_parsed_at":"2026-08-05T15:51:45.660Z","dependency_job_id":null,"html_url":"https://github.com/Dicklesworthstone/llm_aided_ocr","commit_stats":{"total_commits":50,"total_committers":4,"mean_commits":12.5,"dds":"0.18000000000000005","last_synced_commit":"c79f6b709a8db62903f55647bec4816823b86b9e"},"previous_names":["dicklesworthstone/llama2_aided_tesseract","dicklesworthstone/llm_aided_ocr"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Dicklesworthstone/llm_aided_ocr","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dicklesworthstone%2Fllm_aided_ocr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dicklesworthstone%2Fllm_aided_ocr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dicklesworthstone%2Fllm_aided_ocr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dicklesworthstone%2Fllm_aided_ocr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Dicklesworthstone","download_url":"https://codeload.github.com/Dicklesworthstone/llm_aided_ocr/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dicklesworthstone%2Fllm_aided_ocr/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36793915,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-06T04:43:03.162Z","status":"online","status_checked_at":"2026-08-20T02:00:06.210Z","response_time":54,"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"}},"owner":{"login":"Dicklesworthstone","name":"Jeff Emanuel","uuid":"35050222","kind":"user","description":"Building in NY","email":"","website":"https://www.jeffreyemanuel.com/","location":null,"twitter":"doodlestein","company":null,"icon_url":"https://avatars.githubusercontent.com/u/35050222?u=c715075cd36c39b7605d0b21dabf70b679ea71f1\u0026v=4","repositories_count":1,"last_synced_at":"2026-08-21T00:43:22.530Z","metadata":{"has_sponsors_listing":true,"funding":null},"html_url":"https://github.com/Dicklesworthstone","funding_links":["https://github.com/sponsors/Dicklesworthstone"],"total_stars":null,"followers":3169,"following":29,"created_at":"2023-07-18T19:49:00.177Z","updated_at":"2026-08-21T00:43:22.541Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Dicklesworthstone","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Dicklesworthstone/repositories"},"packages":[],"commits":{"id":1641881,"full_name":"Dicklesworthstone/llm_aided_ocr","default_branch":"main","total_commits":62,"total_committers":3,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":20.666666666666668,"dds":0.032258064516129004,"past_year_total_commits":10,"past_year_total_committers":1,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":10.0,"past_year_dds":0.0,"last_synced_at":"2026-08-19T22:41:39.125Z","last_synced_commit":"dcde819dd27a04dd11d3cf098ad8bc0916068595","created_at":"2024-08-07T17:38:27.097Z","updated_at":"2026-08-19T22:41:37.348Z","committers":[{"name":"Jeff Emanuel","email":"35050222+Dicklesworthstone","login":"Dicklesworthstone","count":60},{"name":"Your Name","email":"you@example.com","login":"invalid-email-address","count":1},{"name":"Backendmagier","email":"158162798+Backendmagier","login":"Backendmagier","count":1}],"past_year_committers":[{"name":"Dicklesworthstone","email":"jeff141421@gmail.com","login":"Dicklesworthstone","count":10}],"commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dicklesworthstone%2Fllm_aided_ocr/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-08-20T00:00:10.776Z","repositories_count":6761849,"commits_count":979769091,"contributors_count":41305806,"owners_count":1361331,"committers_count":3355821,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues":{"table":{"full_name":"Dicklesworthstone/llm_aided_ocr","html_url":"https://github.com/Dicklesworthstone/llm_aided_ocr","last_synced_at":"2026-08-20T23:07:20.699Z","status":null,"issues_count":12,"pull_requests_count":9,"avg_time_to_close_issue":5068.0,"avg_time_to_close_pull_request":33686.0,"issues_closed_count":1,"pull_requests_closed_count":5,"pull_request_authors_count":5,"issue_authors_count":10,"avg_comments_per_issue":0.16666666666666666,"avg_comments_per_pull_request":0.8888888888888888,"merged_pull_requests_count":4,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":1,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":119592.0,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":1,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":2.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2024-08-09T22:00:51.862Z","updated_at":"2026-08-20T23:07:20.699Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dicklesworthstone%2Fllm_aided_ocr","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/Dicklesworthstone%2Fllm_aided_ocr/issues","issue_labels_count":{"table":{}},"pull_request_labels_count":{"table":{}},"issue_author_associations_count":{"table":{"NONE":11,"CONTRIBUTOR":1}},"pull_request_author_associations_count":{"table":{"NONE":8,"CONTRIBUTOR":1}},"issue_authors":{"table":{"SouravaBehera":3,"chenzebiaohub":1,"TVqj3237":1,"tcurdt":1,"heiheiheibj":1,"huongyj":1,"echo-mo":1,"li-yan-study":1,"Backendmagier":1,"lemassykoi":1}},"pull_request_authors":{"table":{"GuoMonth":2,"sanchitram1":2,"hotwa":2,"Backendmagier":2,"milahu":1}},"host":{"table":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2026-08-21T00:00:06.664Z","repositories_count":16213438,"issues_count":41826228,"pull_requests_count":133353320,"authors_count":11489888,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"}},"past_year_issue_labels_count":{"table":{}},"past_year_pull_request_labels_count":{"table":{}},"past_year_issue_author_associations_count":{"table":{}},"past_year_pull_request_author_associations_count":{"table":{"NONE":1}},"past_year_issue_authors":{"table":{}},"past_year_pull_request_authors":{"table":{"milahu":1}},"maintainers":[],"active_maintainers":[]}},"events":{"total":{"PullRequestEvent":2,"ForkEvent":64,"IssuesEvent":8,"WatchEvent":661,"IssueCommentEvent":12,"PushEvent":8,"CreateEvent":1},"last_year":{"PullRequestEvent":1,"ForkEvent":8,"IssuesEvent":5,"WatchEvent":71,"IssueCommentEvent":5,"PushEvent":6,"CreateEvent":1}},"keywords":["ai-assist","llama2","llm","ocr","ocr-correction","tesseract"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2023-07-27T01:38:50.703Z","updated_at":"2023-07-27T01:38:50.703Z","repository_link":"https://github.com/Dicklesworthstone/llm_aided_ocr/blob/main/requirements.txt","dependencies":[{"id":12072884440,"package_name":"pandas","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":12072884441,"package_name":"opencv-python","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":12072884442,"package_name":"pytesseract","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":12072884443,"package_name":"llama-cpp-python","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":12072884444,"package_name":"pdf2image","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":12072884445,"package_name":"pillow","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"docker","filepath":"docker/Dockerfile","sha":null,"kind":"manifest","created_at":"2026-08-05T15:51:45.488Z","updated_at":"2026-08-05T15:51:45.488Z","repository_link":"https://github.com/Dicklesworthstone/llm_aided_ocr/blob/main/docker/Dockerfile","dependencies":[{"id":25888867771,"package_name":"nvidia/cuda","ecosystem":"docker","requirements":"${TAG_VERSION}-cudnn8-devel-ubuntu22.04","direct":true,"kind":"build","optional":false}]},{"ecosystem":"docker","filepath":"docker/docker-compose.yml","sha":null,"kind":"manifest","created_at":"2026-08-05T15:51:45.592Z","updated_at":"2026-08-05T15:51:45.592Z","repository_link":"https://github.com/Dicklesworthstone/llm_aided_ocr/blob/main/docker/docker-compose.yml","dependencies":[{"id":25888867774,"package_name":"hotwa/llm_aided_ocr","ecosystem":"docker","requirements":"latest","direct":true,"kind":"runtime","optional":false}]}],"score":9.101306450952046,"created_at":"2024-07-25T15:26:24.074Z","updated_at":"2026-08-21T23:31:31.457Z","avatar_url":"https://github.com/Dicklesworthstone.png","language":"Python","codemeta":null,"publiccode":null,"project_url":"https://summary.ecosyste.ms/api/v1/projects/124997","html_url":"https://summary.ecosyste.ms/projects/124997"}