{"id":28904766,"url":"https://github.com/brucezhao1875/video-chat-transcript-web","last_synced_at":"2026-04-09T22:45:16.694Z","repository":{"id":299378239,"uuid":"1002838026","full_name":"brucezhao1875/video-chat-transcript-web","owner":"brucezhao1875","description":"An AI-powered chat application that provides intelligent, citable answers by leveraging a knowledge base built from video chat transcripts.","archived":false,"fork":false,"pushed_at":"2025-06-16T08:16:46.000Z","size":0,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-16T08:53:03.138Z","etag":null,"topics":["ai-assistant","conversational-ai","dify","llm","nextjs","prompt-engineering","rag","semantic-search","vercel"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/brucezhao1875.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2025-06-16T08:13:51.000Z","updated_at":"2025-06-16T08:19:45.000Z","dependencies_parsed_at":"2025-06-16T09:03:23.029Z","dependency_job_id":null,"html_url":"https://github.com/brucezhao1875/video-chat-transcript-web","commit_stats":null,"previous_names":["brucezhao1875/video-chat-transcript-web"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/brucezhao1875/video-chat-transcript-web","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brucezhao1875%2Fvideo-chat-transcript-web","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brucezhao1875%2Fvideo-chat-transcript-web/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brucezhao1875%2Fvideo-chat-transcript-web/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brucezhao1875%2Fvideo-chat-transcript-web/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/brucezhao1875","download_url":"https://codeload.github.com/brucezhao1875/video-chat-transcript-web/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brucezhao1875%2Fvideo-chat-transcript-web/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269201190,"owners_count":24377452,"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":"2025-08-07T02:00:09.698Z","response_time":73,"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":["ai-assistant","conversational-ai","dify","llm","nextjs","prompt-engineering","rag","semantic-search","vercel"],"created_at":"2025-06-21T13:02:09.593Z","updated_at":"2026-04-09T22:45:16.621Z","avatar_url":"https://github.com/brucezhao1875.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Video Chat Transcript AI\n\nAn AI-powered chat application that provides intelligent, citable answers by leveraging a knowledge base built from video chat transcripts. This project utilizes a **RAG (Retrieval-Augmented Generation)** architecture to allow a Large Language Model (LLM) to perform deep Q\u0026A on specific, unstructured conversation data, ensuring responses are accurate, context-aware, and verifiable.\n\n![Demo Screenshot](https://i.imgur.com/example-screenshot.png)\n*(tbd)*\n\n---\n\n## ✨ Features\n\n* **🤖 Core RAG Architecture**: Implements a full Retrieval-Augmented Generation pipeline, effectively combining an LLM with a private knowledge base of chat transcripts. This solves the problem of knowledge gaps and \"hallucinations\" in general-purpose models.\n* **⚙️ Automated Data Processing**: Includes scripts and methodologies for automated preprocessing of video chat transcript data, transforming raw conversation logs into structured, retrievable knowledge segments.\n* **🔍 High-Precision Semantic Search**: Utilizes a vector database and semantic similarity search to efficiently and accurately retrieve the most relevant conversational snippets from the knowledge base in response to user queries.\n* **📝 Advanced Prompt Engineering**: Features a sophisticated, persona-driven system prompt with strict output formatting instructions, guiding the LLM to generate responses that are stylistically consistent and include verifiable source citations (e.g., video links with timestamps).\n* **🌐 Modern Web Application**: A full-stack application built with Next.js and React, providing a responsive and user-friendly chat interface for seamless interaction.\n* **🚀 CI/CD \u0026 Global Deployment**: Deployed on Vercel with automated CI/CD pipelines, ensuring seamless updates and high-performance global access for users anywhere.\n\n## 🛠️ Tech Stack\n\n* **Frontend**: [Next.js](https://nextjs.org/), [React](https://react.dev/), [Tailwind CSS](https://tailwindcss.com/)\n* **AI Backend \u0026 Workflow**: [Dify.ai](https://dify.ai/) (Cloud Version)\n* **LLM (Large Language Model)**: [DeepSeek](https://www.deepseek.com/) (or your chosen model)\n* **Deployment**: [Vercel](https://vercel.com/)\n* **Node.js Version**: 20.x (LTS)\n\n## 🚀 Getting Started\n\nFollow these instructions to set up and run the project locally for development and testing.\n\n### Prerequisites\n\n* [Node.js](https://nodejs.org/) (Version 20.x recommended)\n* [npm](https://www.npmjs.com/) or [yarn](https://yarnpkg.com/)\n* A Dify.ai account and a configured application with an API key.\n\n### Installation\n\n1.  **Clone the repository:**\n    ```bash\n    git clone [https://github.com/brucezhao1875/video-chat-transcript-web.git](https://github.com/YourUsername/video-chat-transcript-web.git)\n    cd video-chat-transcript-web\n    ```\n    \n2.  **Install dependencies:**\n    ```bash\n    npm install\n    ```\n\n3.  **Set up environment variables:**\n    Create a file named `.env.local` in the root of the project and add the following environment variables. You can get these from your Dify application's \"API Access\" section.\n\n    ```env\n    # Your Dify application's API endpoint\n    NEXT_PUBLIC_API_URL=[https://api.dify.ai/v1](https://api.dify.ai/v1)\n    \n    # Your Dify application's API Key\n    NEXT_PUBLIC_APP_API_KEY=app-xxxxxxxxxxxxxxxxxxxx\n    ```\n\n4.  **Run the development server:**\n    ```bash\n    npm run dev\n    ```\n\nOpen [http://localhost:3000](http://localhost:3000) in your browser to see the application running.\n\n## 部署 (Deployment)\n\nThis project is optimized for deployment on [Vercel](https://vercel.com/).\n\n1.  Push your code to a Git repository (e.g., on GitHub).\n2.  Import the repository into Vercel.\n3.  Configure the same environment variables (`NEXT_PUBLIC_API_URL` and `NEXT_PUBLIC_APP_API_KEY`) in the Vercel project settings.\n4.  Deploy! Vercel will automatically handle the build process and deployment for you.\n\n## 📄 License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrucezhao1875%2Fvideo-chat-transcript-web","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbrucezhao1875%2Fvideo-chat-transcript-web","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrucezhao1875%2Fvideo-chat-transcript-web/lists"}