{"adoption": {"forks": 139, "observed_at": "2026-08-28T04:03:32.850250+00:00", "stars": 1091}, "canonical_url": "https://ross.abutalabs.com/products/deekseek-ocr-dockerized-api", "card": {"archived": false, "artifact_type": "service", "description": null, "domain": ["pdf", "artificial-intelligence", "developer-tools"], "enriched": true, "function": ["ocr", "pdf", "http-server", "machine-learning"], "health_score": 49, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["Bogdanovich77/DeekSeek-OCR---Dockerized-API"], "name": "Bogdanovich77/DeekSeek-OCR---Dockerized-API", "platform": ["python", "windows"], "pushed_at": "2025-10-22T19:32:31+00:00", "repo": "Bogdanovich77/DeekSeek-OCR---Dockerized-API", "stars": 1091, "tags": ["deepseek-ocr", "pdf-to-markdown", "fastapi", "self-hosted", "document-conversion", "docker", "linux", "gpu"], "topics": [], "urls": [], "use_cases": ["convert pdf documents to markdown", "self-hosted ocr api for pdfs", "batch extract text from pdf files", "run deepseek-ocr in docker", "ocr scanned documents into markdown", "serve an ocr endpoint for my app"], "what_it_is": "A Dockerized REST API and batch processing scripts that convert PDF documents to Markdown using the DeepSeek-OCR model behind a FastAPI backend. It requires an NVIDIA GPU with at least 12GB VRAM and provides health checks plus multiple processing modes (markdown, plain OCR, custom prompts).", "when_to_avoid": ["you have no CUDA-capable GPU", "you need a lightweight CPU-only OCR solution", "you want a managed cloud OCR service"], "when_to_choose": ["you need a self-hosted OCR service with a REST API", "you have an NVIDIA GPU with 12GB+ VRAM and want Docker deployment", "you want batch conversion of PDFs to Markdown preserving structure"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deekseek-ocr-dockerized-api", "repo": "Bogdanovich77/DeekSeek-OCR---Dockerized-API", "role": "main", "score": 38}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:32.850250+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:49:05.132952+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5aa773275d7cdcd01c44abd3c03b588d31835ec8128cb06647dfeda1789336b9", "fetched_at": "2026-08-28T04:03:32.850250+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Bogdanovich77/DeekSeek-OCR---Dockerized-API"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 48, "longevity": 22, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 316, "days_push": 315, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 38, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}