{"data":{"slug":"xlang-ai-instructor-embedding","name":"instructor-embedding","tagline":"One Embedder, Any Task Instruction-Finetuned Text Embeddings","github_url":"https://github.com/xlang-ai/instructor-embedding","owner":"xlang-ai","repo":"instructor-embedding","owner_avatar_url":"https://avatars.githubusercontent.com/u/128829376?v=4","primary_language":"Python","stars":2023,"forks":156,"topics":["embeddings","information-retrieval","language-model","prompt-retrieval","text-classification","text-clustering","text-embedding","text-evaluation","text-reranking","text-semantic-similarity"],"archived":false,"github_pushed_at":"2025-01-15T22:09:40+00:00","maintenance_label":"Dormant","stars_delta_30d":-1,"url":"https://www.graphcanon.com/tools/xlang-ai-instructor-embedding","markdown_url":"https://www.graphcanon.com/tools/xlang-ai-instructor-embedding.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/xlang-ai-instructor-embedding","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=xlang-ai-instructor-embedding","description":"[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings","homepage_url":null,"license":"Apache-2.0","open_issues":37,"watchers":16,"ai_summary":"Provides instruction-finetuned text embeddings for various natural language processing tasks including information retrieval and text evaluation.","readme_excerpt":"## Installation\nIt is very easy to use INSTRUCTOR for any text embeddings. You can easily try it out in [Colab notebook](https://colab.research.google.com/drive/1P7ivNLMosHyG7XOHmoh7CoqpXryKy3Qt?usp=sharing). In your local machine, we recommend to first create a virtual environment:\n```bash\nconda env create -n instructor python=3.7\ngit clone https://github.com/HKUNLP/instructor-embedding\npip install -r requirements.txt\n```\nThat will create the environment `instructor` we used. To use the embedding tool, first install the `InstructorEmbedding` package from PyPI\n```bash\npip install InstructorEmbedding\n```\nor directly install it from our code\n```bash\npip install -e .\n```\n\n---\n\n## Getting Started\n\nFirst download a pretrained model (See [model list](#model-list) for a full list of available models)\n\n```python\nfrom InstructorEmbedding import INSTRUCTOR\nmodel = INSTRUCTOR('hkunlp/instructor-large')\n```\n\nThen provide the sentence and customized instruction to the model.\n```python","github_created_at":"2022-12-17T22:00:17+00:00","created_at":"2026-07-11T11:29:46.038024+00:00","updated_at":"2026-08-22T06:01:25.430445+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"instruction-tuning","name":"instruction-tuning"},{"slug":"nlp","name":"nlp"},{"slug":"prompt-retrieval","name":"prompt-retrieval"},{"slug":"semantic-similarity","name":"semantic-similarity"},{"slug":"text-classification","name":"text-classification"},{"slug":"text-clustering","name":"text-clustering"},{"slug":"text-embedding","name":"text-embedding"}],"trust":{"provenance":{"is_fork":false,"github_id":579494713,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-22T06:01:24.646Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":583,"last_release_at":null,"stars_delta_30d":-1,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:29:47.443Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-22T06:01:25.093Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-22T06:01:25.093Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-22T06:01:25.093Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["For tasks requiring contextual understanding through instructions, like interactive systems","In information retrieval scenarios where relevance and context matter"],"when_not_to_use":["When simple keyword matching or non-contextual semantic analysis is sufficient","If the application requires embeddings trained on very specific domain data not covered by generic instruction-finetuning"],"source":"enrich:decision_facts","observed_at":"2026-07-14T21:10:04.240Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"instructor-embedding: ACL 2023 solution for generating instruction-finetuned text embeddings suitable for various NLP applications."}]}}