{"adoption": {"forks": 236, "observed_at": "2026-08-28T04:05:14.214679+00:00", "stars": 1632}, "canonical_url": "https://ross.abutalabs.com/products/synthetic-data-kit", "card": {"archived": false, "artifact_type": "cli-tool", "description": "Tool for generating high quality Synthetic datasets", "domain": ["machine-learning", "large-language-models", "developer-tools"], "enriched": true, "function": ["data-generation", "llm-training", "etl", "cli", "nlp"], "health_score": 50, "homepage": "https://pypi.org/project/synthetic-data-kit/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["meta-llama/synthetic-data-kit"], "name": "meta-llama/synthetic-data-kit", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2025-10-28T20:10:55+00:00", "repo": "meta-llama/synthetic-data-kit", "stars": 1632, "tags": ["synthetic-data", "fine-tuning", "qa-pairs", "chain-of-thought", "llama", "vllm", "data-curation", "lance-format", "data-engineering"], "topics": ["data", "generation", "llm", "python", "synthetic"], "urls": [], "use_cases": ["generate synthetic QA pairs from pdfs for fine-tuning", "create chain-of-thought reasoning traces with an LLM", "convert documents into fine-tuning friendly chat formats", "curate synthetic datasets using LLM-as-a-judge", "prepare training data for Llama fine-tuning", "ingest pdfs, html, youtube transcripts, docx and ppt files", "export datasets to formats required by fine-tuning packages"], "what_it_is": "A Python CLI tool from Meta for generating high-quality synthetic datasets to fine-tune LLMs. It follows a four-stage pipeline (ingest, create, curate, save-as) that converts documents into QA pairs, chain-of-thought reasoning traces, and summaries in fine-tuning-friendly formats.", "when_to_avoid": ["you need general-purpose data labeling or annotation for non-LLM ML tasks", "you want a GUI or web interface rather than a CLI workflow", "you don't have access to an LLM backend for generation", "you need real-time or streaming data generation rather than batch pipelines"], "when_to_choose": ["you need structured training data in user/assistant format for LLM fine-tuning", "you want an end-to-end pipeline from raw documents to curated fine-tuning datasets", "you use vLLM or a local/external LLM endpoint and want modular dataset generation", "you want LLM-as-a-judge curation to filter low-quality examples"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/synthetic-data-kit", "repo": "meta-llama/synthetic-data-kit", "role": "main", "score": 42}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:14.214679+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:47:47.448408+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca53158cc08067edbdd32b346ca6e96549b9f6101093c526cf933fc0882a340a", "fetched_at": "2026-08-28T04:05:14.214679+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-llama/synthetic-data-kit"}, {"content_hash": "4b4e8fead74a82582158f1c6b83a2db21fc02cd116c124ae690d0931a9091212", "fetched_at": "2026-08-29T11:20:33.633588+00:00", "kind": "homepage", "missing": false, "url": "https://pypi.org/project/synthetic-data-kit/"}, {"content_hash": "6b56b0fc52c241914c67f3050925f023e5817e94f4e96a50fb778e95e7ab6825", "fetched_at": "2026-08-29T11:20:33.636330+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/synthetic-data-kit/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 49, "longevity": 37, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 524, "days_push": 309, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 42, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}