# xlang-ai/instructor-embedding

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Repository: https://github.com/xlang-ai/instructor-embedding
Canonical: https://ross.abutalabs.com/products/instructor-embedding
Language: Python
License: Apache-2.0
License Family: permissive
Topics: embeddings, information-retrieval, language-model, text-classification, text-clustering, text-embedding, text-evaluation, text-semantic-similarity, prompt-retrieval, text-reranking
Last push: 2025-01-15T22:09:40+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 1, release rhythm 35, longevity 96
- inputs: {"age_days": 1355, "days_push": 595, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2023, forks 156 (observed 2026-08-28T04:06:06.505561+00:00)

## What it is
INSTRUCTOR is an instruction-finetuned text embedding model and Python library that generates task-tailored embeddings by simply providing a task instruction, without finetuning. It supports classification, retrieval, clustering, semantic similarity, and reranking across diverse domains.

## Use cases
- generate text embeddings for custom tasks
- compute semantic similarity between sentences
- build semantic search and information retrieval
- cluster documents by meaning
- rerank search results
- embed texts for RAG pipelines

## When to choose
- you need one embedding model adaptable to many tasks via instructions
- you want strong open-source sentence embeddings without finetuning
- you need embeddings for retrieval, clustering, or classification

## When to avoid
- you need the fastest or smallest embedding model
- you prefer closed-source commercial embedding APIs
- you need multimodal (image) embeddings

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, search-engine, rag
- domain: machine-learning, large-language-models
- platform: python
- tags: text-embeddings, instruction-tuned, semantic-similarity, information-retrieval, sentence-embeddings, mteb, natural-language-processing, search

## Member repositories
- xlang-ai/instructor-embedding (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:06.505561+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:00:03.955127+00:00, confidence not recorded.
  - readme: https://github.com/xlang-ai/instructor-embedding (fetched 2026-08-28T04:06:06.505561+00:00, sha b9a794aefd68)
- Data as of 2026-08-30T08:39:29.467469+00:00.