{"id":30303853,"url":"https://github.com/sayed-ashfaq/youtuberag-app","last_synced_at":"2025-08-31T14:09:24.697Z","repository":{"id":303224011,"uuid":"1014750835","full_name":"sayed-ashfaq/YoutubeRAG-app","owner":"sayed-ashfaq","description":"A powerful GenAI application that summarizes YouTube videos and answers questions based on video content using LLMs, embeddings, and semantic search. Built using LangChain, Gemini Pro, ChromaDB, and deployed with Flask.","archived":false,"fork":false,"pushed_at":"2025-07-06T12:08:15.000Z","size":587,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-08-17T06:34:22.378Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/sayed-ashfaq.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":"2025-07-06T10:47:02.000Z","updated_at":"2025-07-06T12:08:52.000Z","dependencies_parsed_at":"2025-07-06T13:33:44.919Z","dependency_job_id":null,"html_url":"https://github.com/sayed-ashfaq/YoutubeRAG-app","commit_stats":null,"previous_names":["sayed-ashfaq/youtuberag-app"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sayed-ashfaq/YoutubeRAG-app","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayed-ashfaq%2FYoutubeRAG-app","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayed-ashfaq%2FYoutubeRAG-app/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayed-ashfaq%2FYoutubeRAG-app/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayed-ashfaq%2FYoutubeRAG-app/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sayed-ashfaq","download_url":"https://codeload.github.com/sayed-ashfaq/YoutubeRAG-app/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayed-ashfaq%2FYoutubeRAG-app/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272988919,"owners_count":25026961,"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":"2025-08-31T02:00:09.071Z","response_time":79,"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":[],"created_at":"2025-08-17T06:34:21.899Z","updated_at":"2025-08-31T14:09:24.679Z","avatar_url":"https://github.com/sayed-ashfaq.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 📺 YouTube Summarizer \u0026 QnA using GenAI (RAG Pipeline)\n\nA powerful GenAI application that **summarizes YouTube videos** and answers questions based on video content using **LLMs, embeddings, and semantic search**. Built using **LangChain**, **Gemini Pro**, **ChromaDB**, and deployed with **Flask**.\n\n---\n\n## 🚀 Features\n\n- 🔍 **YouTube Transcript Extraction** – Automatically pulls transcripts from any YouTube video.\n- 🧠 **RAG Pipeline (Retrieval-Augmented Generation)** – Uses vector search + LLMs to provide accurate, context-aware answers.\n- 🧾 **Summarization + Q\u0026A** – Ask any question about the video or request a summary.\n- 💾 **Persistent Memory** – Stores vectorized chunks in ChromaDB using unique hashes.\n- 🌐 **Flask REST API** – Backend ready for integration into web apps or platforms.\n\n---\n\n## 🧠 How It Works\n\n1. **Load Transcript** from a YouTube video using `YoutubeLoader`.\n2. **Split Transcript** into chunks using `RecursiveCharacterTextSplitter`.\n3. **Generate Embeddings** using `GoogleGenerativeAIEmbeddings`.\n4. **Store \u0026 Search** chunks using `Chroma` vector database.\n5. **Query** through a `RetrievalQA` or `RetrievalChain` powered by Gemini Pro and LangChain.\n6. **Respond** in a friendly tone customized for young learners using prompt templates.\n\n---\n\n## 🧪 Example Usage\n\n```bash\npython app.py\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsayed-ashfaq%2Fyoutuberag-app","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsayed-ashfaq%2Fyoutuberag-app","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsayed-ashfaq%2Fyoutuberag-app/lists"}