{"id":32647544,"url":"https://github.com/jacobmarks/semantic-document-search-plugin","last_synced_at":"2026-03-27T02:17:41.657Z","repository":{"id":202553570,"uuid":"707462048","full_name":"jacobmarks/semantic-document-search-plugin","owner":"jacobmarks","description":"Semantically search through OCR text blocks with Qdrant, Sentence Transformers, and FiftyOne!","archived":false,"fork":false,"pushed_at":"2024-04-05T00:02:56.000Z","size":21,"stargazers_count":8,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-31T05:55:14.955Z","etag":null,"topics":["data-centric-ai","data-visualisation","embeddings","fiftyone","gte","huggingface","plugin","qdrant","sentence-transformers","vector-database","vector-search"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jacobmarks.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2023-10-20T00:39:54.000Z","updated_at":"2024-11-27T16:11:26.000Z","dependencies_parsed_at":"2024-04-05T01:25:36.801Z","dependency_job_id":null,"html_url":"https://github.com/jacobmarks/semantic-document-search-plugin","commit_stats":null,"previous_names":["jacobmarks/fuzzy-search-plugin"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jacobmarks/semantic-document-search-plugin","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacobmarks%2Fsemantic-document-search-plugin","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacobmarks%2Fsemantic-document-search-plugin/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacobmarks%2Fsemantic-document-search-plugin/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacobmarks%2Fsemantic-document-search-plugin/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jacobmarks","download_url":"https://codeload.github.com/jacobmarks/semantic-document-search-plugin/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacobmarks%2Fsemantic-document-search-plugin/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31009858,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-27T01:56:05.093Z","status":"online","status_checked_at":"2026-03-27T02:00:08.055Z","response_time":164,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["data-centric-ai","data-visualisation","embeddings","fiftyone","gte","huggingface","plugin","qdrant","sentence-transformers","vector-database","vector-search"],"created_at":"2025-10-31T05:55:01.363Z","updated_at":"2026-03-27T02:17:41.644Z","avatar_url":"https://github.com/jacobmarks.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Semantic Document Search Plugin\n\n![display_and_search_thesis](https://github.com/jacobmarks/semantic-document-search-plugin/assets/12500356/ac87511d-c3f9-4718-891d-89e14aef4152)\n\nThis plugin is a Python plugin that allows you to semantically search through your text blocks (from Optical Character Recognition) in your dataset.\n\nIt uses a Qdrant index, with the GTE-base model from Hugging Face's Sentence Transformers library.\n\n## Usage\n\nYou will need to have text blocks in your dataset. You can do this with the [PyTesseract OCR plugin](https://github.com/jacobmarks/pytesseract-ocr-plugin).\n\nCreate a vector index for your text blocks with the `create_semantic_document_index` operator. You can then use the `semantically_search_documents` operator to search through your text blocks.\n\nIf you have multiple detections with text blocks, you can create multiple indexes. The index is stored in Qdrant with the collection name `\u003cdataset_name\u003e_sds_\u003cfield_name\u003e`. When you use the `semantically_search_documents` operator, you can specify which index to use.\n\n## Watch On Youtube\n[![Video Thumbnail](https://img.youtube.com/vi/I0FFDCbWZcM/0.jpg)](https://www.youtube.com/watch?v=I0FFDCbWZcM\u0026list=PLuREAXoPgT0RZrUaT0UpX_HzwKkoB-S9j\u0026index=13)\n\n\n## Installation\n\nDownload the plugin with the following command:\n\n```shell\nfiftyone plugins download https://github.com/jacobmarks/semantic-document-search-plugin\n```\n\nYou will need to install the Sentence Transformers library, and the Qdrant client Python library, which can be achieved with\n\n```shell\nfiftyone plugins requirements @jacobmarks/semantic_document_search --install\n```\n\nYou will also need to have a Qdrant instance running. You can do this with Docker once you have your Docker daemon running:\n\n```shell\ndocker run -p \"6333:6333\" -p \"6334:6334\" -d qdrant/qdrant\n```\n\n## Using with PyTesseract OCR Plugin\n\nThis _semantic_ search plugin is in many ways analogous to the [keyword search plugin](https://github.com/jacobmarks/keyword-search-plugin), and is likewise designed to be used with the [PyTesseract OCR plugin](https://github.com/jacobmarks/pytesseract-ocr-plugin).\n\nYou can install the PyTesseract OCR plugin with the following command:\n\n```shell\nfiftyone plugins download https://github.com/jacobmarks/pytesseract-ocr-plugin\n```\n\n## Operators\n\n### `create_semantic_document_index`\n\n![create_index](https://github.com/jacobmarks/semantic-document-search-plugin/assets/12500356/2ac0da4a-36b6-40d9-86e3-ec61a94f050c)\n\n\n**Description**: Create a Qdrant index for the specified text field within a detections label field.\n\n### `semantically_search_documents`\n\n![search_index](https://github.com/jacobmarks/semantic-document-search-plugin/assets/12500356/1c174879-398b-414d-8891-02bccf3c6be7)\n\n**Description**: Semantically search for text in your dataset. Only labels matching your query will be shown.\n\nYou can specify the number of results to return, and the threshold for the similarity score.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacobmarks%2Fsemantic-document-search-plugin","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjacobmarks%2Fsemantic-document-search-plugin","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacobmarks%2Fsemantic-document-search-plugin/lists"}