{"id":17527031,"url":"https://github.com/tabsl/KI-PDF-Organizer","last_synced_at":"2026-05-28T23:30:17.915Z","repository":{"id":206716498,"uuid":"717538966","full_name":"tabsl/ocr-scan-and-rename-by-ai","owner":"tabsl","description":"Read files (pdf/png/jpg) with OCR and rename using AI.","archived":false,"fork":false,"pushed_at":"2023-11-12T08:01:05.000Z","size":8,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2023-11-12T20:27:09.700Z","etag":null,"topics":["chatgpt","huggingface","jpg","llm","lmstudio","localai","ocr","pdf","png","rename-files","rename-script","scan-files","scanner","tool"],"latest_commit_sha":null,"homepage":"","language":"Shell","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/tabsl.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":"2023-11-11T19:17:17.000Z","updated_at":"2023-11-12T08:10:18.000Z","dependencies_parsed_at":null,"dependency_job_id":"dfd0b226-37b3-469e-8054-4c92004580b5","html_url":"https://github.com/tabsl/ocr-scan-and-rename-by-ai","commit_stats":null,"previous_names":["tabsl/ocr-scan-and-rename-by-ai"],"tags_count":0,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tabsl%2Focr-scan-and-rename-by-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tabsl%2Focr-scan-and-rename-by-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tabsl%2Focr-scan-and-rename-by-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tabsl%2Focr-scan-and-rename-by-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tabsl","download_url":"https://codeload.github.com/tabsl/ocr-scan-and-rename-by-ai/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240156777,"owners_count":19756835,"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":["chatgpt","huggingface","jpg","llm","lmstudio","localai","ocr","pdf","png","rename-files","rename-script","scan-files","scanner","tool"],"created_at":"2024-10-20T15:03:00.282Z","updated_at":"2026-05-28T23:30:17.867Z","avatar_url":"https://github.com/tabsl.png","language":"Shell","funding_links":[],"categories":["Shell"],"sub_categories":[],"readme":"# Dateien mit OCR auslesen und Dateinamen anhand KI umbenennen\n\nDieses Script ermöglicht das Auslesen (PDF/JPG/PNG) von Text mittels OCR. Dieser Text wird an eine lokale KI gesendet und aufbereitert. Danach wird (im besten Fall ;-)) ein sinnvoller Dateiname zurückgegeben. Abschließend wir die Datei umbennant und in den `done`-Order verschoben.\n\n## Anwendung\n`./scan.sh .` ausführen (Parameter gibt Verzeichnis an, aus welchem die Dateien eingelesen werden sollen)\n\n```\n./scan 11-11-2023 0002 35.pdf\nStarte OCR-Erkennung ...\nOCR erfolgreich\nStarte KI-Anfrage ...\nContinentale Versicherung Erhöhung ( ContinentaleVersicherung\\_Erhöhung.txt )\n'./scan 11-11-2023 0002 35.pdf' wurde erfolgreich zu './done/Continentale Versicherung Erhöhung.pdf' umbenannt und verschoben\n\n./scan 11-11-2023 0002 7.pdf\nStarte OCR-Erkennung ...\nOCR erfolgreich\nStarte KI-Anfrage ...\nDatenschutzerklärung Finanzberater ( Datenschutzerklärung\\_Finanzberater.txt )\n'./scan 11-11-2023 0002 7.pdf' wurde erfolgreich zu './done/Datenschutzerklärung Finanzberater.pdf' umbenannt und verschoben\n\n...\n```\n\n## Installation (macOS)\n1. Repo klonen: `git clone https://github.com/tabsl/ocr-scan-and-rename-by-ai.git`\n1. Homebrew installieren: https://brew.sh\n2. Poppler installieren: `brew install poppler`\n3. Tesseract installieren: `brew install tesseract`\n4. Tesseract DE-Langpack installieren: `brew install tesseract-lang `\n5. LM-Studio installieren: https://lmstudio.ai\n6. LLM über LM-Sudio downloaden: https://huggingface.co/TheBloke/vicuna-13B-v1.5-16K-GGUF/blob/main/vicuna-13b-v1.5-16k.Q4_K_M.gguf\n\n## Konfiguration\n1. `chmod +x ./scan.sh`\n2. LM-Studio (Local Inference Server) mit entsprechendem LLM starten\n\n\n---\n\n\n# Read files with OCR and rename using AI\n\nThis script enables reading text (PDF/JPG/PNG) using OCR. The text is sent to a local AI and processed. Then, in the best case ;-), a meaningful filename is returned. Finally, the file is renamed and moved to the `done` folder.\n\n## Application\nRun `./scan.sh .` (the parameter specifies the directory from which the files should be read)\n\n```\n./scan 11-11-2023 0002 35.pdf\nStarting OCR detection ...\nOCR successful\nStarting AI request ...\nContinental Insurance Increase ( ContinentalVersicherung_Erhöhung.txt )\n'./scan 11-11-2023 0002 35.pdf' was successfully renamed to './done/Continental Insurance Increase.pdf' and moved\n\n./scan 11-11-2023 0002 7.pdf\nStarting OCR detection ...\nOCR successful\nStarting AI request ...\nData Protection Declaration Financial Advisor ( Datenschutzerklärung_Finanzberater.txt )\n'./scan 11-11-2023 0002 7.pdf' was successfully renamed to './done/Data Protection Declaration Financial Advisor.pdf' and moved\n\n...\n```\n\n## Installation (macOS)\n1. Clone repo: `git clone https://github.com/tabsl/ocr-scan-and-rename-by-ai.git`\n2. Install Homebrew: https://brew.sh\n3. Install Poppler: `brew install poppler`\n4. Install Tesseract: `brew install tesseract`\n5. Install Tesseract DE language pack: `brew install tesseract-lang`\n6. Install LM-Studio: https://lmstudio.ai\n7. Download LLM via LM-Studio: https://huggingface.co/TheBloke/vicuna-13B-v1.5-16K-GGUF/blob/main/vicuna-13b-v1.5-16k.Q4_K_M.gguf\n\n## Configuration\n1. `chmod +x ./scan.sh`\n2. Start LM-Studio (Local Inference Server) with the respective LLM\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftabsl%2FKI-PDF-Organizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftabsl%2FKI-PDF-Organizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftabsl%2FKI-PDF-Organizer/lists"}