{"adoption": {"forks": 164, "observed_at": "2026-08-28T04:05:31.047330+00:00", "stars": 1749}, "canonical_url": "https://ross.abutalabs.com/products/llm-sherpa", "card": {"archived": false, "artifact_type": "library", "description": "Developer APIs to Accelerate LLM Projects", "domain": ["pdf", "large-language-models", "developer-tools"], "enriched": true, "function": ["parser", "pdf", "ocr", "rag", "llm-inference", "sdk"], "health_score": 27, "homepage": "https://www.nlmatics.com", "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["nlmatics/llmsherpa", "nlmatics/nlm-ingestor"], "name": "LLM Sherpa", "platform": ["python", "self-hosted", "cross-platform"], "pushed_at": "2024-10-18T17:42:37+00:00", "repo": "nlmatics/llmsherpa", "stars": 1749, "tags": ["pdf-parsing", "layout-aware-chunking", "document-ingestion", "layoutpdfreader", "smart-chunking", "retrieval-augmented-generation", "natural-language-processing", "docker"], "topics": [], "urls": [], "use_cases": ["parse pdfs preserving layout structure for rag", "chunk pdf documents intelligently for vector indexing", "extract sections headings tables and lists from pdfs", "self-host a document ingestion server for llm apps", "convert docx pptx html files to structured text for llms", "remove repeated headers footers and watermarks from pdf text"], "what_it_is": "LLM Sherpa is a Python client library providing APIs for layout-aware PDF and document parsing to feed LLM applications, backed by the open-source nlm-ingestor service. It extracts hierarchical structure such as sections, paragraphs, tables, and lists from PDFs, DOCX, PPTX, HTML, and other formats to enable smart chunking for RAG pipelines.", "when_to_avoid": ["you only need plain text extraction without layout information", "you need OCR for scanned pdfs without a text layer", "you need a fully managed cloud parsing service"], "when_to_choose": ["you need layout-aware pdf parsing with section hierarchy for rag pipelines", "you want to self-host a document ingestion service supporting multiple file formats", "you need smart chunking that respects paragraphs tables and nested lists"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/nlmatics/llmsherpa", "repo": "nlmatics/llmsherpa", "role": "sdk", "score": 18}, {"path": "/repos/nlmatics/nlm-ingestor", "repo": "nlmatics/nlm-ingestor", "role": "backend", "score": 22}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:31.047330+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:28:45.949540+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d23a612211a3e55638eccebbfebd5cb0b3a707a04083c82d37cdf5445cd58ed4", "fetched_at": "2026-08-28T04:05:31.047330+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nlmatics/llmsherpa"}, {"content_hash": "c9ca875ef47578236c5857a06ebdaf959cce1546a1bb8640be247c479f4c8063", "fetched_at": "2026-08-29T11:06:40.762292+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llmsherpa/json"}, {"content_hash": "91b2e15ff7a78abc72edb6c50fa6d4081c686b7451d68c8d3dff1367acb83e0f", "fetched_at": "2026-08-29T11:06:40.764314+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/nlm-ingestor/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 75, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1056, "days_push": 684, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 18, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}