{"adoption": {"forks": 139, "observed_at": "2026-08-28T04:05:25.856114+00:00", "stars": 1712}, "canonical_url": "https://ross.abutalabs.com/products/llm2vec", "card": {"archived": false, "artifact_type": "library", "description": "Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'", "domain": ["large-language-models", "machine-learning"], "enriched": true, "function": ["machine-learning", "llm-training", "rag", "nlp"], "health_score": 76, "homepage": "https://mcgill-nlp.github.io/llm2vec/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["McGill-NLP/llm2vec"], "name": "McGill-NLP/llm2vec", "platform": ["python"], "pushed_at": "2026-04-04T14:53:36+00:00", "repo": "McGill-NLP/llm2vec", "stars": 1712, "tags": ["text-embeddings", "sentence-embeddings", "contrastive-learning", "huggingface", "research", "natural-language-processing", "retrieval-augmented-generation", "gpu"], "topics": [], "urls": [], "use_cases": ["convert an LLM into a text embedding model", "generate sentence embeddings for semantic search", "build embeddings for RAG retrieval", "fine-tune a decoder-only LLM as a text encoder", "evaluate embeddings on MTEB benchmarks"], "what_it_is": "LLM2Vec is a Python library that converts decoder-only large language models into powerful text encoders via bidirectional attention, masked next token prediction, and unsupervised contrastive learning. It wraps HuggingFace models for sequence encoding and pooling, and ships pretrained checkpoints on HuggingFace.", "when_to_avoid": ["you need a lightweight embedding model for CPU-only deployment", "you only need off-the-shelf embeddings without GPU training", "your stack does not support HuggingFace transformers and flash-attention"], "when_to_choose": ["you want state-of-the-art text embeddings derived from open LLMs", "you need custom embedding models fine-tuned on your domain", "you want bidirectional encoders without training from scratch"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/llm2vec", "repo": "McGill-NLP/llm2vec", "role": "main", "score": 49}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.856114+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:34:45.973308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4f71585a5e90e20005765986553b8171a55caeea4c8196710cc4ba131074a211", "fetched_at": "2026-08-28T04:05:25.856114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/McGill-NLP/llm2vec"}, {"content_hash": "ad183eef78ddfd7dc65c7532c623956b5ab3097fb75a251cb07d589123963a46", "fetched_at": "2026-08-29T11:10:46.684131+00:00", "kind": "homepage", "missing": false, "url": "https://mcgill-nlp.github.io/llm2vec/"}, {"content_hash": "1f2071ca9cf932b1bd1074580c766d68d58b0f58508768e3140b1d7f39f618f7", "fetched_at": "2026-08-29T11:10:46.686440+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/llm2vec/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 75, "longevity": 63, "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": 882, "days_push": 151, "days_rel": 586, "gap_med": null, "n_releases_24m": 1}, "score": 49, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}