{"data":{"slug":"raphaelsty-cherche","name":"cherche","tagline":"Neural Search","github_url":"https://github.com/raphaelsty/cherche","owner":"raphaelsty","repo":"cherche","owner_avatar_url":"https://avatars.githubusercontent.com/u/24591024?v=4","primary_language":"Python","stars":332,"forks":14,"topics":["bm25","flashtext","information-retrieval","machine-learning","natural-language-processing","neural-networks","neural-search","nlp","question-answering","reader","retrieval","search","searching","semantic-search","vector-search"],"archived":false,"github_pushed_at":"2024-06-01T17:05:12+00:00","maintenance_label":"Dormant","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/raphaelsty-cherche","markdown_url":"https://www.graphcanon.com/tools/raphaelsty-cherche.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/raphaelsty-cherche","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=raphaelsty-cherche","description":"Neural Search","homepage_url":null,"license":"MIT","open_issues":4,"watchers":7,"ai_summary":"Cherche is a Python library focused on information retrieval tasks such as question answering and neural search, supporting both simple and semantic retrievers.","readme_excerpt":"## Installation 🤖\n\nTo install Cherche for use with a simple retriever on CPU, such as TfIdf, Flash, Lunr, Fuzz, use the following command:\n\n```sh\npip install cherche\n```\n\nTo install Cherche for use with any semantic retriever or ranker on CPU, use the following command:\n\n```sh\npip install \"cherche[cpu]\"\n```\n\nFinally, if you plan to use any semantic retriever or ranker on GPU, use the following command:\n\n```sh\npip install \"cherche[gpu]\"\n```\n\nBy following these installation instructions, you will be able to use Cherche with the appropriate requirements for your needs.","github_created_at":"2021-12-04T19:47:06+00:00","created_at":"2026-07-11T11:36:24.929413+00:00","updated_at":"2026-09-20T06:26:27.28849+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"}],"tags":[{"slug":"bm25","name":"bm25"},{"slug":"flashtext","name":"flashtext"},{"slug":"information-retrieval","name":"information retrieval"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"natural-language-processing","name":"natural language processing"},{"slug":"neural-networks","name":"neural-networks"},{"slug":"neural-search","name":"neural-search"},{"slug":"nlp","name":"nlp"}],"trust":{"provenance":{"is_fork":false,"github_id":434994455,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:26:24.744Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":840,"last_release_at":"2024-06-01T17:05:12Z","stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:36:26.348Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:26:25.878Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-20T06:26:25.878Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T06:26:25.878Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use Cherche when you need to implement neural search functionalities that go beyond traditional keyword matching. It is suitable for projects that require a deep understanding of the semantic meaning,","If you require support for both simple and semantic retrieval methods, Cherche can be a versatile choice that caters to various levels of search complexity. This is particularly useful in scenarios","For projects that utilize GPUs to accelerate computations, Cherche offers a dedicated installation option, making it an efficient choice for large-scale neural search projects."],"when_not_to_use":["Avoid Cherche if your project has strict limitations on external dependencies or if the project's scope is limited to basic keyword search capabilities only, as it includes both simple and advanced","Cherche may not be the best option if your project prioritizes using a specific technology stack, such as a particular framework for machine learning, that the library does not well integrate with","If your project strictly avoids using libraries licensed under the MIT license, you should consider other options. Cherche's MIT license might not align with the licensing requirements of other","Do not use Cherche for projects that have explicit requirements for operating environments that are not supported by Cherche, such as specific versions of Python or operating systems."],"source":"enrich:decision_facts","observed_at":"2026-09-08T04:37:52.246Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Cherche is a Python library for neural search and information retrieval tasks, supporting both simple and semantic retrievers. It is ideal for projects needing robust search functionalities enhanced with neural-based and"}]}}