{"id":24313529,"url":"https://github.com/dwqs/ollama-ocr","last_synced_at":"2025-10-20T10:30:09.326Z","repository":{"id":270583448,"uuid":"910812408","full_name":"dwqs/ollama-ocr","owner":"dwqs","description":"A powerful OCR (Optical Character Recognition) package that uses state-of-the-art vision language models","archived":false,"fork":false,"pushed_at":"2025-01-01T14:59:43.000Z","size":66,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-01T15:29:27.828Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Vue","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dwqs.png","metadata":{"files":{"readme":"README.md","changelog":null,"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}},"created_at":"2025-01-01T14:04:45.000Z","updated_at":"2025-01-01T14:59:47.000Z","dependencies_parsed_at":"2025-01-01T15:29:58.828Z","dependency_job_id":"f84f7ea9-19f2-4dc3-9683-d6953f075762","html_url":"https://github.com/dwqs/ollama-ocr","commit_stats":null,"previous_names":["dwqs/ollama-ocr"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dwqs%2Follama-ocr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dwqs%2Follama-ocr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dwqs%2Follama-ocr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dwqs%2Follama-ocr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dwqs","download_url":"https://codeload.github.com/dwqs/ollama-ocr/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":234338058,"owners_count":18816449,"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":[],"created_at":"2025-01-17T09:01:55.700Z","updated_at":"2025-09-26T19:31:12.124Z","avatar_url":"https://github.com/dwqs.png","language":"Vue","funding_links":[],"categories":["Vue"],"sub_categories":[],"readme":"\u003e inspired by [imanoop7/Ollama-OCR](https://github.com/imanoop7/Ollama-OCR)\n\n## Ollama OCR for web\n\nA powerful OCR (Optical Character Recognition) package that uses state-of-the-art vision language models through Ollama to extract text from images.\n\n## Supported Models\n\n- **LLaVA**: A multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding, achieving impressive chat capabilities mimicking spirits of the multimodal GPT-4. (LLaVa model can generate wrong output sometimes)\n- **Llama 3.2 Vision**: Instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image\n- **MiniCPM-V 2.6**: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone\n\n## Quick Start\n\n#### Prerequisites\n\n1. Install [Ollama](https://ollama.com/)\n2. Pull the required models:\n\n```sh\nollama pull llama3.2-vision:11b\nollama pull llava:13b\nollama pull minicpm-v:8b\n```\n\nThen run following command:\n\n```sh\ngit clone git@github.com:dwqs/ollama-ocr.git\ncd ollama-ocr\nyarn or npm i\nyarn dev or npm run dev\n```\n\n## Docker Supports\n\n**you can run the demo from docker**: `debounce/ollama-ocr`\n\n## Examples\n\n#### Input Image1\n\n![input-image](https://image-static.segmentfault.com/149/814/1498143911-677575ecd6977_fix732)\n\n#### Output Markdown\n\n![output-markdown.png](https://image-static.segmentfault.com/338/339/3383395719-67757691e9b37_fix732)\n\n#### Input Image2\n\n![input-image](https://image-static.segmentfault.com/257/222/2572220334-677579c2747c7_fix732)\n\n#### Output JSON\n\n![output-json.png](https://image-static.segmentfault.com/104/188/1041885248-677579f517f02_fix732)\n\n## Output Format Details\n\n- **Markdown Format**: The output is a markdown string containing the extracted text from the image.\n- **Text Format**: The output is a plain text string containing the extracted text from the image.\n- **JSON Format**: The output is a JSON object containing the extracted text from the image.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdwqs%2Follama-ocr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdwqs%2Follama-ocr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdwqs%2Follama-ocr/lists"}