--- title: YouTube RAG Chatbot Project description: "**YouTube RAG Chatbot** is an AI-powered web application that lets you have a conversation with any YouTube video. Instead of watching a 1-hour video to find one answer, you paste the URL, and the chatbot answers your questions instantly — using…" url: "https://csestudy247.com/docs/youtube-rag-chatbot-project/" updated: "2026-08-25" category: AI Projects --- # YouTube RAG Chatbot Project **YouTube RAG Chatbot** is an AI-powered web application that lets you have a conversation with any YouTube video. Instead of watching a 1-hour video to find one answer, you paste the URL, and the chatbot answers your questions instantly — using only the content from that video. It uses a technique called **Retrieval-Augmented Generation (RAG)**, which combines: ![](https://csestudy247.com/wp-content/uploads/2026/07/YouTube-RAG-Chatbot-Project.png) - **Document retrieval** — finding the most relevant parts of the transcript - **LLM generation** — using Gemini AI to generate accurate, context-aware answers ## Problem It Solves [https://github.com/sanjit507/Youtube-RAG-Chatbot#-problem-it-solves](https://github.com/sanjit507/Youtube-RAG-Chatbot#-problem-it-solves) | Problem | Solution | | --- | --- | | Videos are long and hard to search | Instantly answer specific questions from any video | | No way to "ctrl+F" a YouTube video | Semantic search over the full transcript | | AI might hallucinate facts | RAG anchors answers **only** to the video transcript | | Requires watching the whole video | Chat interface extracts what you need in seconds | **Real-world use cases:** - 📚 Students summarizing lecture videos - 🔬 Researchers extracting key findings from conference talks - 💼 Professionals reviewing long webinars or podcasts - 🎓 Quick revision before exams from educational YouTube content ![YouTube RAG Chatbot](https://csestudy247.com/wp-content/uploads/2026/07/YouTubeRAGChatbot.jpeg) [GitHub Code](https://github.com/sanjit507/Youtube-RAG-Chatbot) ## Tech Stack [https://github.com/sanjit507/Youtube-RAG-Chatbot#%EF%B8%8F-tech-stack](https://github.com/sanjit507/Youtube-RAG-Chatbot#%EF%B8%8F-tech-stack) | Layer | Technology | Purpose | | --- | --- | --- | | **UI** | [Streamlit](https://streamlit.io/) | Web interface with dark theme | | **Orchestration** | [LangChain](https://www.langchain.com/) | RAG pipeline & chain management | | **LLM** | [Google Gemini 2.5 Flash](https://ai.google.dev/) | Answer generation | | **Embeddings** | Google Gemini Embedding | Convert text to vectors | | **Vector Store** | [FAISS](https://github.com/facebookresearch/faiss) | Fast similarity search | | **Transcript** | [youtube-transcript-api](https://github.com/jdepoix/youtube-transcript-api) | Fetch YouTube subtitles | | **Text Splitting** | LangChain `RecursiveCharacterTextSplitter` | Chunk transcript into pieces | | **Environment** | `python-dotenv` | Secure API key management | ## Setup Guide (For Students) [https://github.com/sanjit507/Youtube-RAG-Chatbot#%EF%B8%8F-setup-guide-for-students](https://github.com/sanjit507/Youtube-RAG-Chatbot#%EF%B8%8F-setup-guide-for-students) ### Prerequisites [https://github.com/sanjit507/Youtube-RAG-Chatbot#prerequisites](https://github.com/sanjit507/Youtube-RAG-Chatbot#prerequisites) - Python 3.10 or higher installed - A Google AI Studio API key (free at [aistudio.google.com](https://aistudio.google.com/)) - Git installed --- ### Step 1 — Clone the Repository [https://github.com/sanjit507/Youtube-RAG-Chatbot#step-1--clone-the-repository](https://github.com/sanjit507/Youtube-RAG-Chatbot#step-1--clone-the-repository) ``` git clone https://github.com/sanjit507/Youtube-RAG-Chatbot.git cd Youtube-RAG-Chatbot ``` --- ### Step 2 — Create a Virtual Environment [https://github.com/sanjit507/Youtube-RAG-Chatbot#step-2--create-a-virtual-environment](https://github.com/sanjit507/Youtube-RAG-Chatbot#step-2--create-a-virtual-environment) **Windows:** ``` python -m venv venv venv\Scripts\activate ``` **macOS / Linux:** ``` python3 -m venv venv source venv/bin/activate ``` You should see `(venv)` appear at the start of your terminal line. --- ### Step 3 — Install Dependencies [https://github.com/sanjit507/Youtube-RAG-Chatbot#step-3--install-dependencies](https://github.com/sanjit507/Youtube-RAG-Chatbot#step-3--install-dependencies) ``` pip install -r requirements.txt ``` > ⚠️ This may take 2–3 minutes. FAISS and LangChain have several sub-dependencies. --- ### Step 4 — Set Up Your API Key [https://github.com/sanjit507/Youtube-RAG-Chatbot#step-4--set-up-your-api-key](https://github.com/sanjit507/Youtube-RAG-Chatbot#step-4--set-up-your-api-key) Create a file called `.env` in the project root: ``` # Windows echo GOOGLE_API_KEY=your_api_key_here > .env # macOS/Linux echo "GOOGLE_API_KEY=your_api_key_here" > .env ``` Or create it manually — create a new file named `.env` and add: ``` GOOGLE_API_KEY=AIzaSy...your_key_here ``` > 🔑 Get your free API key at [aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey) --- ### Step 5 — Run the App [https://github.com/sanjit507/Youtube-RAG-Chatbot#step-5--run-the-app](https://github.com/sanjit507/Youtube-RAG-Chatbot#step-5--run-the-app) ``` streamlit run app.py ``` The app will open at **[http://localhost:8501](http://localhost:8501/)** in your browser. --- ### Step 6 — Use the App [https://github.com/sanjit507/Youtube-RAG-Chatbot#step-6--use-the-app](https://github.com/sanjit507/Youtube-RAG-Chatbot#step-6--use-the-app) 1. Paste any YouTube URL in the input box e.g. `https://www.youtube.com/watch?v=LPZh9BOjkQs` 2. Click **🚀 Load** and wait ~10-30 seconds for indexing 3. Type your question and click **💬 Ask** 4. Get AI-powered answers based only on the video content! --- ## Example Questions to Try [https://github.com/sanjit507/Youtube-RAG-Chatbot#-example-questions-to-try](https://github.com/sanjit507/Youtube-RAG-Chatbot#-example-questions-to-try) Use this video: `https://www.youtube.com/watch?v=LPZh9BOjkQs` (3Blue1Brown — How LLMs work) | Question | Expected Answer Type | | --- | --- | | What is a large language model? | Definition from the video | | How does training work? | Step-by-step explanation | | What is backpropagation? | Concept from the video | | Summarize this video | Full summary | | What is the transformer architecture? | Technical explanation |