{"adoption": {"forks": 2203, "observed_at": "2026-08-28T04:11:35.420777+00:00", "stars": 23855}, "canonical_url": "https://ross.abutalabs.com/products/deepseek-ocr", "card": {"archived": false, "artifact_type": "library", "description": "Contexts Optical Compression", "domain": ["artificial-intelligence", "machine-learning", "deep-learning", "large-language-models", "computer-vision", "image-processing"], "enriched": true, "function": ["ocr", "machine-learning", "llm-inference", "image-processing", "computer-vision", "transformers"], "health_score": 59, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["deepseek-ai/DeepSeek-OCR"], "name": "deepseek-ai/DeepSeek-OCR", "platform": ["python"], "pushed_at": "2026-01-27T03:45:14+00:00", "repo": "deepseek-ai/DeepSeek-OCR", "stars": 23855, "tags": ["vision-language-model", "vision-encoder", "optical-context-compression", "context-compression", "model-weights", "inference-code", "vllm", "huggingface", "multimodal", "research-model", "deepseek", "mit-license", "natural-language-processing", "gpu", "linux"], "topics": [], "urls": [], "use_cases": ["extract text from scanned documents or images with an open-source OCR model", "compress long text contexts into images to extend LLM effective context", "run document understanding with a vision-language model", "serve an OCR model at scale with vLLM", "experiment with optical context compression research from the paper", "parse layouts, tables, and text from PDFs or screenshots"], "what_it_is": "DeepSeek-OCR is an open vision-language model from DeepSeek AI that researches 'contexts optical compression' - encoding long text contexts as images through a vision encoder feeding an LLM decoder. The repository ships model weights, inference code for both Transformers and vLLM, and an accompanying arXiv paper.", "when_to_avoid": ["you need a lightweight CPU-only OCR utility - this requires CUDA GPUs, flash-attention, and a heavy PyTorch/vLLM stack", "you want the newest iteration - DeepSeek-OCR2 was announced in January 2026 as the successor", "you need a turnkey OCR SaaS with preprocessing, batching UI, and export pipelines"], "when_to_choose": ["you need high-accuracy open-weights OCR or document parsing with GPU acceleration", "you want to reproduce or build on the contexts-optical-compression research", "you want a DeepSeek vision model with official upstream vLLM support"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/deepseek-ocr", "repo": "deepseek-ai/DeepSeek-OCR", "role": "main", "score": 45}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:35.420777+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:56:19.476607+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4ce77cdea6158ed70579cf2ee6840017ad16112000760ae096a1733bd4360d70", "fetched_at": "2026-08-28T04:11:35.420777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/deepseek-ai/DeepSeek-OCR"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 64, "longevity": 22, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 320, "days_push": 218, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 45, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}