{"adoption": {"forks": 105, "observed_at": "2026-08-28T04:03:28.686093+00:00", "stars": 1072}, "canonical_url": "https://ross.abutalabs.com/products/lilac", "card": {"archived": true, "artifact_type": "library", "description": "Curate better data for LLMs", "domain": ["artificial-intelligence", "large-language-models", "data-science", "machine-learning"], "enriched": true, "function": ["data-science", "etl", "search-engine", "nlp", "machine-learning", "data-visualization"], "health_score": 10, "homepage": "http://lilacml.com", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["databricks/lilac"], "name": "databricks/lilac", "platform": ["python", "self-hosted", "cross-platform"], "pushed_at": "2024-03-19T12:41:30+00:00", "repo": "databricks/lilac", "stars": 1072, "tags": ["dataset-curation", "llm-data-quality", "data-exploration", "fine-tuning-data", "pii-detection", "semantic-search", "clustering", "web-ui", "data-engineering", "web-server"], "topics": ["artificial-intelligence", "data-analysis", "dataset-analysis", "unstructured-data"], "urls": [], "use_cases": ["curate fine-tuning datasets for LLMs", "find and remove PII from training data", "deduplicate large text datasets before training", "explore and search millions of documents with semantic search", "cluster and label unstructured text data with LLMs", "monitor dataset quality changes over time", "visualize pre-training data distributions"], "what_it_is": "Lilac is an open-source tool for exploring, curating, and quality-controlling datasets used for training, fine-tuning, and monitoring LLMs. It provides both a web UI and Python API, running on-device with open-source LLMs for search, filtering, clustering, and annotation of unstructured data.", "when_to_avoid": ["you need a fully managed enterprise data platform with support guarantees", "your data is structured tabular data rather than unstructured text", "you require active development and frequent updates, as the latest release is from March 2024"], "when_to_choose": ["you need to clean and curate large unstructured text datasets for LLM training or fine-tuning", "you want an interactive UI plus Python API for dataset exploration", "you need on-device processing with open-source LLMs for data quality tasks like PII removal and deduplication"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/lilac", "repo": "databricks/lilac", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.686093+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:53:41.075383+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9f7261a876fae2d0f4350ad2d941961c7dc150fbffdc38c1a2dcdc77e051d85f", "fetched_at": "2026-08-28T04:03:28.686093+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/lilac"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 89, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1259, "days_push": 897, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}