{"id":29486406,"url":"https://github.com/adityaexp/comicfinder","last_synced_at":"2025-07-18T16:01:45.379Z","repository":{"id":304293075,"uuid":"1018358163","full_name":"AdityaEXP/ComicFinder","owner":"AdityaEXP","description":"🤖 AI-based manhwa recommender using OpenAI embeddings + Streamlit UI.","archived":false,"fork":false,"pushed_at":"2025-07-12T09:45:56.000Z","size":16585,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-12T10:27:38.614Z","etag":null,"topics":["ai","comic-recommender","cosine-similarity","embeddings","manga","manhua","manhwa","nlp","openai","python","recommender-system","semantic-search","streamlit","webtoon"],"latest_commit_sha":null,"homepage":"https://comicfinder.streamlit.app","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/AdityaEXP.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,"zenodo":null}},"created_at":"2025-07-12T05:11:28.000Z","updated_at":"2025-07-12T10:18:39.000Z","dependencies_parsed_at":"2025-07-12T10:38:49.810Z","dependency_job_id":null,"html_url":"https://github.com/AdityaEXP/ComicFinder","commit_stats":null,"previous_names":["adityaexp/manhwafinder","adityaexp/comicfinder"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/AdityaEXP/ComicFinder","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdityaEXP%2FComicFinder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdityaEXP%2FComicFinder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdityaEXP%2FComicFinder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdityaEXP%2FComicFinder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AdityaEXP","download_url":"https://codeload.github.com/AdityaEXP/ComicFinder/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdityaEXP%2FComicFinder/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265419613,"owners_count":23761846,"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":["ai","comic-recommender","cosine-similarity","embeddings","manga","manhua","manhwa","nlp","openai","python","recommender-system","semantic-search","streamlit","webtoon"],"created_at":"2025-07-15T08:00:40.770Z","updated_at":"2025-07-15T08:02:21.128Z","avatar_url":"https://github.com/AdityaEXP.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 ComicFinder\n\nComicFinder is an AI-powered content-based recommendation system built using Python and OpenAI Embeddings. \nIt helps users discover semantically similar manga, manhwa, manhua, and webtoons based on natural language descriptions, genres, or titles — ideal for fans seeking personalized recommendations beyond keyword search.\n\n![ComicFinder Preview: Streamlit interface for manga recommendation](asset/img.jpg)\n\n---\n\n## 💻 Live Demo Of Comic Finder\n**https://comicfinder.streamlit.app/**\n\n---\n\n## 🚀 Features Of Comic Finder\n\n- 🔍 Recommends similar manga/manhwa/manhua/webtoon based on descriptions or titles\n- 📦 Utilizes precomputed `clean_embeddings.npy` for fast results\n- 🧠 Embedding generation using OPENAI embeddings api\n- ⚡ Fast cosine similarity search for real-time recommendation\n- 🖥️ Clean Streamlit-based frontend\n- 📁 Organized data and scripts for easy retraining or extension\n\n---\n\n## 📁 Project Structure\n\n```\ncomic-recommender/\n├── app.py                       # Main application script\n├── data/\n│   ├── data.csv                 # Original manhwa dataset\n│   ├── clean_data.csv           # Cleaned and preprocessed data\n│   └── clean_embeddings.npy     # (Ignored from Git, must be downloaded separately)\n├── scripts/\n│   ├── clean_dataset.py         # Data cleaning script\n│   ├── generate_embeddings.py   # Embedding generation\n│   └── recommend.py             # Similarity-based recommendations but CLI version\n├── .env                         # Store API keys \n├── requirements.txt             # Python dependencies\n└── README.md                    # You're here!\n```\n\n---\n\n# 🔧 How to Install and Run ComicFinder Locally\n```\ngit clone https://github.com/AdityaEXP/ComicFinder.git\ncd ComicFinder\n\n# Optional: Create virtual environment\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\n\npip install -r requirements.txt\nstreamlit run .\\app.py\n```\n\n---\n## 📌 Example Use Cases\n- Find romance manhwa similar to *What's Wrong with Secretary Kim?*\n- Get fantasy webtoon recommendations with strong male leads\n- Discover hidden manga gems with character development arcs\n- Replace genre filters with AI-powered natural language queries\n\n---\n\n# 📥 Download Embedding File\nSince clean_embeddings.npy is large, it’s not included in this repo.\n[📦 Download clean_embeddings.npy](https://drive.google.com/file/d/1toZRablb8yCVhFrICdU1jQtmYh20mZ9P/view?usp=sharing)\nOr you can also generate the clean_embeddings.npy using your own openai api key it will cost around $0.02 per generation\n\n---\n\n# 🔐 Environment Variables\nCreate a .env file for your OpenAI API Key\n```\nOPENAIKEY=sk-xxxxxx\n```\n\n---\n\n# 📜 License\nMIT — free to use, modify, and distribute.\n\n---\n\n# 🤝 Author\nAditya\n🛠️ AI + Python + Web3 Enthusiast\n\n---\n\n## 📚 Dataset Source and Preprocessing\nThis project uses data inspired by or adapted from the following Kaggle dataset:\n\n**📊 [Kaggle - Manhwa and Webtoon Dataset](https://www.kaggle.com/datasets/victorsoeiro/manga-manhwa-and-manhua-dataset/data)**  \nCredit to **Victor Soeiro** for compiling and sharing this dataset.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadityaexp%2Fcomicfinder","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fadityaexp%2Fcomicfinder","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fadityaexp%2Fcomicfinder/lists"}