{"adoption": {"forks": 473, "observed_at": "2026-08-28T04:08:29.834026+00:00", "stars": 3924}, "canonical_url": "https://ross.abutalabs.com/products/colbert", "card": {"archived": false, "artifact_type": "library", "description": "ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)", "domain": ["machine-learning", "deep-learning"], "enriched": true, "function": ["search-engine", "rag", "machine-learning", "deep-learning", "transformers"], "health_score": 62, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["stanford-futuredata/ColBERT"], "name": "stanford-futuredata/ColBERT", "platform": ["python"], "pushed_at": "2025-10-14T18:50:11+00:00", "repo": "stanford-futuredata/ColBERT", "stars": 3924, "tags": ["neural-search", "late-interaction", "bert", "information-retrieval", "dense-retrieval", "passage-ranking", "semantic-search", "maxsim", "plaid", "research", "search", "retrieval-augmented-generation", "natural-language-processing", "gpu"], "topics": [], "urls": [], "use_cases": ["build semantic search over a large text corpus", "retrieve relevant passages for a RAG pipeline", "rank documents by fine-grained relevance to a query", "index millions of passages for fast neural search", "improve retrieval quality beyond single-vector embeddings", "fine-tune a neural retriever on domain-specific data", "add neural retrieval to a question answering system"], "what_it_is": "ColBERT is a fast and accurate neural retrieval model that encodes passages and queries into token-level embedding matrices and scores them with contextual late interaction (MaxSim), enabling BERT-quality search over large corpora in tens of milliseconds. This repository is the reference Python implementation (ColBERTv2) with indexing and retrieval tooling, widely used for semantic search and RAG pipelines.", "when_to_avoid": ["you only need simple keyword search such as BM25 or SQL full-text without ML dependencies", "you need a managed, horizontally scalable production vector database rather than a research-grade retrieval library", "you lack GPU resources for encoding and indexing documents", "you want an off-the-shelf application instead of a Python library to integrate into your code"], "when_to_choose": ["you need high-accuracy neural retrieval where token-level late interaction outperforms single-vector dense models", "you want low query latency over large corpora using the PLAID engine", "you need a strong retriever component for RAG or open-domain QA systems", "you want to train or fine-tune a BERT-based retrieval model on your own data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/colbert", "repo": "stanford-futuredata/ColBERT", "role": "main", "score": 45}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:29.834026+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:24:44.912241+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ce4b15d905d8f4b6c272d911395f1fe8fe86a0a385373932f25fef1541bd5ef6", "fetched_at": "2026-08-28T04:08:29.834026+00:00", "kind": "readme", "missing": false, "url": "https://github.com/stanford-futuredata/ColBERT"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 47, "longevity": 100, "rhythm": 10}, "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": 2291, "days_push": 323, "days_rel": 387, "gap_med": null, "n_releases_24m": 1}, "score": 45, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}