{"id":18405773,"url":"https://github.com/vicba/movies-recommendation","last_synced_at":"2026-04-13T04:32:48.064Z","repository":{"id":232258664,"uuid":"781386833","full_name":"Vicba/movies-recommendation","owner":"Vicba","description":"Netflix clone with vector db for similar movie recommendation","archived":false,"fork":false,"pushed_at":"2024-04-13T13:54:53.000Z","size":2849,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-16T08:39:32.357Z","etag":null,"topics":["docker","flask","nextjs","python","tailwindcss","typescript"],"latest_commit_sha":null,"homepage":"https://www.loom.com/share/2cff3d786df143879fc79fadf8e35af5?sid=b1a8a110-9c76-47f4-9418-6a74a77e1a21","language":"TypeScript","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/Vicba.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":"2024-04-03T09:32:20.000Z","updated_at":"2024-04-13T11:26:02.000Z","dependencies_parsed_at":"2024-04-13T15:14:55.709Z","dependency_job_id":"455adf0c-49ff-47c1-8ae3-3895eee20a1c","html_url":"https://github.com/Vicba/movies-recommendation","commit_stats":null,"previous_names":["vicba/movies-recommendation"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Vicba/movies-recommendation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vicba%2Fmovies-recommendation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vicba%2Fmovies-recommendation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vicba%2Fmovies-recommendation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vicba%2Fmovies-recommendation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Vicba","download_url":"https://codeload.github.com/Vicba/movies-recommendation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Vicba%2Fmovies-recommendation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279010343,"owners_count":26084738,"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","status":"online","status_checked_at":"2025-10-12T02:00:06.719Z","response_time":53,"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":["docker","flask","nextjs","python","tailwindcss","typescript"],"created_at":"2024-11-06T03:04:42.934Z","updated_at":"2025-10-12T05:06:58.945Z","avatar_url":"https://github.com/Vicba.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Movie App\n\nThis is a movie app that uses 680 movies between 1990 and 2024 from TMDB stored in a vector database. The app uses a simple cosine similarity to find the most similar movies (recommendation) to a given movie.\n\n## How to run ?\n\nMake sure you have docker installed on your machine!\n\n1. Clone the repo\n\n```bash\ngit clone https://github.com/Vicba/movies-recommendation.git\n```\n\n2. Run `docker-compose up` in the root directory\n\n```bash\ndocker-compose up\n```\n\n3. Populate the database with the movies.\n\n```bash\ncurl -X GET http://localhost:5000/populate\n```\n\n4. Open `http://localhost:3000` in your browser\n5. Browse around!\n\n## Technologies\n\n- Nextjs (typescript, Tailwindcss)\n- Flask\n- Weaviate\n- Docker\n- Huggingface API\n\n## The embedding model\n\nThe embedding model used is `sentence-transformers/paraphrase-MiniLM-L6-v2` from huggingface. It has 384 dimensions.\n\nIf you want to use something else, you can change it in the `/api/build_knowledge_base/embed.py` file.\nRun the python script to generate the csv with embeddings csv in datasets folder.\n\n```bash\ncd api/build_knowledge_base\npython embed.py\n```\n\n## Learnings\n\n- Learned how to use Weaviate\n- Refresh my knowledge in nextjs \u0026 docker\n- Usign huggingface API\n- Project went super smooth with the research and pre-defined scope\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvicba%2Fmovies-recommendation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvicba%2Fmovies-recommendation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvicba%2Fmovies-recommendation/lists"}