{"id":28403020,"url":"https://github.com/arc53/doc2md","last_synced_at":"2025-06-26T17:31:34.293Z","repository":{"id":264050400,"uuid":"891466860","full_name":"arc53/doc2md","owner":"arc53","description":"Convert pdf and image files into markdown","archived":false,"fork":false,"pushed_at":"2025-01-22T06:31:37.000Z","size":370,"stargazers_count":7,"open_issues_count":2,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-02T01:16:09.734Z","etag":null,"topics":["doc","doc2md","llm","visual","vllm","vlm"],"latest_commit_sha":null,"homepage":"https://doc2md.arc53.com/","language":"TypeScript","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/arc53.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":"2024-11-20T11:42:04.000Z","updated_at":"2025-02-05T21:36:47.000Z","dependencies_parsed_at":"2024-11-21T18:31:30.731Z","dependency_job_id":"e15be616-a9e5-4696-b948-2d288d86e958","html_url":"https://github.com/arc53/doc2md","commit_stats":null,"previous_names":["arc53/doc2md"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/arc53/doc2md","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arc53%2Fdoc2md","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arc53%2Fdoc2md/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arc53%2Fdoc2md/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arc53%2Fdoc2md/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/arc53","download_url":"https://codeload.github.com/arc53/doc2md/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arc53%2Fdoc2md/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262113229,"owners_count":23260983,"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":["doc","doc2md","llm","visual","vllm","vlm"],"created_at":"2025-06-01T16:36:29.022Z","updated_at":"2025-06-26T17:31:34.279Z","avatar_url":"https://github.com/arc53.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"This project helps users to convert Documents (.pdf, .png, .jpg, .jpeg) into Markdown for you ease of ingestion into LLM workflows.\n\nIt uses a public LLM endpint (doc2md) [here](https://llm.arc53.com/docs#/)\nThis endpoint simply gives images or pdfs (converted to images) to visual model and asks it to conver it into markdown.\n\nHere is a quick snippet using python to perform such task:\n```python\n# Client is your OpenAI compatible client\nmodel = 'meta-llama/Llama-3.2-11B-Vision-Instruct'\nprompt = \"Convert the following image to just the markdown text, respond only with text and description of it if relevant.\"\nmessages = [\n    {\n        \"role\": \"user\",\n        \"content\": [\n                    {\n            \"type\": \"text\",\n            \"text\": prompt,\n            },\n            {\n            \"type\": \"image_url\",\n            \"image_url\": {\n                \"url\":  f\"{base64_image}\"\n            },\n            },\n        ]\n    }\n]\nresponse = client.chat.completions.create(model=model,\n    messages=messages,\n    stream=False,\n    max_tokens=int(max_new_tokens),\n    **kwargs)\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farc53%2Fdoc2md","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farc53%2Fdoc2md","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farc53%2Fdoc2md/lists"}