{"id":21810474,"url":"https://github.com/seyeong-han/bookmind","last_synced_at":"2025-03-21T08:45:46.603Z","repository":{"id":264414157,"uuid":"893137232","full_name":"seyeong-han/BookMind","owner":"seyeong-han","description":"Draw book mind maps to see the relationship between characters easily :)","archived":false,"fork":false,"pushed_at":"2024-11-29T23:03:29.000Z","size":1028,"stargazers_count":11,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-26T05:25:01.085Z","etag":null,"topics":["google-books-api","javascript","llama-stack","llama3","nodejs","python","react","ssambanova"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","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/seyeong-han.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":"2024-11-23T16:25:18.000Z","updated_at":"2024-12-19T21:21:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"f2b5f199-b100-43da-beb4-77de83c14201","html_url":"https://github.com/seyeong-han/BookMind","commit_stats":null,"previous_names":["seyeong-han/bookmind"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seyeong-han%2FBookMind","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seyeong-han%2FBookMind/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seyeong-han%2FBookMind/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seyeong-han%2FBookMind/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/seyeong-han","download_url":"https://codeload.github.com/seyeong-han/BookMind/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244767542,"owners_count":20507110,"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":["google-books-api","javascript","llama-stack","llama3","nodejs","python","react","ssambanova"],"created_at":"2024-11-27T13:35:55.957Z","updated_at":"2025-03-21T08:45:46.598Z","avatar_url":"https://github.com/seyeong-han.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# BookMind\n\n[![thumbnail](https://github.com/user-attachments/assets/11c6f1f3-59db-4638-9b1a-68f1d25efec4)](https://youtu.be/DL4-DswxfEM)\n\nBookMind is a web application that allows users to explore character relationships and storylines in books using AI-powered visualizations. The application provides interactive mind maps, AI chatbots for deep questions, book summaries, and community contributions.\n\n## Features\n\n- Interactive Mind Maps: Visualize relationships between characters and plot elements.\n- AI Chatbot: Ask deep questions about the book and get insightful answers.\n- Book Summaries: Get concise overviews of plots and themes.\n- Community Contributions: Add and refine maps with fellow book lovers.\n\n## Prerequisites\n\n- Node.js\n- Python \u003e= 3.10\n- LlamaStack server running locally\n- Environment variables:\n  - LLAMA_STACK_PORT\n  - INFERENCE_MODEL\n  - REACT_APP_GOOGLE_BOOKS_API_KEY\n\n## Getting Started\n\n### Backend Setup\n\n1. Install dependencies:\n\n```\npip install -r server/requirements.txt\n```\n\n2. Install and run our forked `llama-stack` docker\n\n```\ngit clone https://github.com/seyeong-han/llama-stack.git\ncd llama-stack\npip install -e .\n\n# Get your API_KEY from https://cloud.sambanova.ai/apis\nexport SSAMBANOVA_API_KEY=YOUR_API\n\nllama stack run --env INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct sambanova\n```\n\n3. Run the server:\n\n```\npython server/server.py\n```\n\n### Frontend Setup\n\n1. Install dependencies:\n\n```\nnpm install\n```\n\n2. Run the application:\n\n```\nnpm start\n```\n\n## Usage\n\n1. Initialize Memory: Upload your book or choose from the library to initialize memory.\n2. AI Analysis: The AI analyzes the book and generates a mind map.\n3. Explore Insights: Explore relationships, themes, and Q\u0026A insights.\n\n## What did we use Llama-stack in BookMind?\n\n1️⃣ Implemented SambaNova Systems Inference API: We contributed to the open-source Llama-stack by integrating the inference API and built a custom Docker container for the llama3.2-3B-instruct model.  \n2️⃣ RAG with FAISS: We leveraged FAISS in Llama-stack for Retrieval-Augmented Generation, enabling real-time responses to character relationship questions.  \n3️⃣ Multi-Hop Reasoning: Our system performs sequential inference—first extracting characters and relationships, then generating graphized mind map data in JSON for visual storytelling.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fseyeong-han%2Fbookmind","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fseyeong-han%2Fbookmind","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fseyeong-han%2Fbookmind/lists"}