{"adoption": {"forks": 236, "observed_at": "2026-08-28T04:03:47.957596+00:00", "stars": 1156}, "canonical_url": "https://ross.abutalabs.com/products/llm-driven-data-engineering", "card": {"archived": false, "artifact_type": "learning-resource", "description": "This is a public repository to go over all the LLM-driven data engineering concepts. ", "domain": ["large-language-models", "education", "tutorials"], "enriched": true, "function": ["llm-inference", "rag", "etl", "data-science"], "health_score": 20, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["DataExpert-io/llm-driven-data-engineering"], "name": "DataExpert-io/llm-driven-data-engineering", "platform": ["python", "cross-platform"], "pushed_at": "2024-10-26T21:07:27+00:00", "repo": "DataExpert-io/llm-driven-data-engineering", "stars": 1156, "tags": ["course", "llm-driven-data-engineering", "langchain", "sql-generation", "vector-database", "bootcamp", "data-engineering"], "topics": [], "urls": [], "use_cases": ["learn how to apply LLMs to data engineering workflows", "generate SQL queries automatically with LangChain", "build a RAG chatbot with a vector database", "follow a structured LLM course with lectures and labs", "practice LLM-driven data pipelines with PostgreSQL"], "what_it_is": "A public educational repository accompanying DataExpert's bootcamp course on LLM-driven data engineering concepts. It contains Python labs covering LLM usage, LangChain-based SQL generation, RAG with vector databases, and PostgreSQL setup.", "when_to_avoid": ["you need production-ready data engineering tooling", "you want a maintained library with a license and releases", "you need self-contained documentation without external lecture videos"], "when_to_choose": ["you want guided lessons and labs on combining LLMs with data engineering", "you are a student of DataExpert's bootcamp needing the companion code", "you want hands-on examples of LangChain, RAG, and vector databases"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llm-driven-data-engineering", "repo": "DataExpert-io/llm-driven-data-engineering", "role": "main", "score": 28}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:47.957596+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:32:05.155447+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0fee1e840f58ea3ae62c1da44c3c6b23766845ffd6bbcbc1db5770f04c3bbd6", "fetched_at": "2026-08-28T04:03:47.957596+00:00", "kind": "readme", "missing": false, "url": "https://github.com/DataExpert-io/llm-driven-data-engineering"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 77, "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": 1086, "days_push": 676, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 28, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}