{"id":17662569,"url":"https://github.com/npatta01/search-engine-workshop","last_synced_at":"2025-06-20T18:37:36.525Z","repository":{"id":62608710,"uuid":"519902685","full_name":"npatta01/search-engine-workshop","owner":"npatta01","description":"Slides and notebook for the workshop on building a search system","archived":false,"fork":false,"pushed_at":"2024-03-17T22:06:49.000Z","size":36880,"stargazers_count":22,"open_issues_count":1,"forks_count":9,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-06-19T09:12:06.601Z","etag":null,"topics":["deep-learning","nlp-machine-learning","search"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/npatta01.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,"publiccode":null,"codemeta":null}},"created_at":"2022-07-31T22:43:41.000Z","updated_at":"2024-06-12T06:54:27.000Z","dependencies_parsed_at":"2024-10-23T21:31:35.581Z","dependency_job_id":null,"html_url":"https://github.com/npatta01/search-engine-workshop","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/npatta01/search-engine-workshop","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/npatta01%2Fsearch-engine-workshop","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/npatta01%2Fsearch-engine-workshop/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/npatta01%2Fsearch-engine-workshop/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/npatta01%2Fsearch-engine-workshop/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/npatta01","download_url":"https://codeload.github.com/npatta01/search-engine-workshop/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/npatta01%2Fsearch-engine-workshop/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":260998548,"owners_count":23095136,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["deep-learning","nlp-machine-learning","search"],"created_at":"2024-10-23T18:22:55.757Z","updated_at":"2025-06-20T18:37:31.504Z","avatar_url":"https://github.com/npatta01.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Search Engine Workshop\n\n\n## About\n\nHandson workshop for building a semantic search engine.\n\n\n\n\n## Setup \n\nIf you came to this repo, during a workshop visit this custom [jupyter hub](http://hub.np.training) with all the dependencies already set up.\n\nThe repo is located at [npatta01/search-engine-workshop](https://github.com/npatta01/search-engine-workshop)\n\nTo use this repo outside a workshop, please use Binder\n[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/npatta01/search-engine-workshop/main)\n\n## Content (Notebooks)\n\n\n**Data Fetching**\n\n[setup notebook](notebooks/00_a_setup_dataset.ipynb)        \n[stats notebook](notebooks/00_b_setup_stats.ipynb)     \n[sample image notebook](notebooks/00_c_sample_images.ipynb)\n\n\nNotebooks to download unsplash dataset and save as hugging face dataset format\n\n\n**Non Deep Learning Retrieval**\n\nBM25 retrieval with elastic search: [notebook](notebooks/01_bm25_elastic.ipynb)\n\n\n**Deep Learning Retrieval (text)**\n\n\nText Deep Learning retrieval: [Link](notebooks/02_dense_retriever.ipynb)\n\n\n**Deep Learning Retrieval (image)**\n\n\nClip Retrieval: [Link](notebooks/03_clip_embed.ipynb)\n\n**ANN**\n\nShows how to speed up Deep Learning retrieval by exploring different ANN indexes\n[Link](notebooks/04_ann.ipynb) \n\n\n\n\n## Slides\n\n[PyData Seattle 2022](assets/slides_pydataseattle2023.pdf)\n\n[PyData NYC 2022](assets/slides_pydatanyc2022.pdf)\n\n\n[ODSC 2022](assets/slides_odsc2022.pdf) \n\n\n## Contact\n\nFor help or feedback, please reach out to :\n\n- [Nidhin Pattaniyil](https://www.linkedin.com/in/nidhinpattaniyil/)   \n- [Ravi Yadav](https://www.linkedin.com/in/ravi-kumar-yadav-535b268/)   \n- [Mustafa Zengin](https://www.linkedin.com/in/mustafazengin/)   \n\n\n\n\n\n## Acknowledgments\n\nThis workshop uses Unsplash Lite Dataset 1.2.0 [link](unsplash.com/data)\n\nThe hands on portion of the workshop was made possible due to [JupyterHub Helm Chart](https://github.com/jupyterhub/helm-chart)\n\n## Changelog\n\n**v1.1**\n- setup for PyDataNYC\n- replaced stackoverflow data with unsplash data\n\n**v1.0**\n- setup for ODSC\n- used stackoverflow data","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnpatta01%2Fsearch-engine-workshop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnpatta01%2Fsearch-engine-workshop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnpatta01%2Fsearch-engine-workshop/lists"}