============================================================
  Deep-Dive Video Note Taker  v1.0.0
  HOW TO RUN THE PROJECT  --  Step-by-Step Guide
============================================================


STEP 1 : Install Python 3.10+
-------------------------------
  Download from : https://www.python.org/downloads/
  During install, CHECK the box "Add Python to PATH"
  Verify after install by opening CMD and typing:
      python --version


STEP 2 : Install FFmpeg
--------------------------
  Download from : https://ffmpeg.org/download.html
  Extract the zip and add the "bin" folder to your system PATH
  Verify by opening CMD and typing:
      ffmpeg -version


STEP 3 : Download / Clone the Project
----------------------------------------
  Open CMD and run:
      git clone https://github.com/rajiv-ramteke/Deep-Dive-Video-Note-Taker.git
      cd Deep-Dive-Video-Note-Taker

  OR simply open the project folder if you already have it:
      cd "C:\Users\rajiv\OneDrive\Desktop\one page report\Deep-Dive-Video-Note-Taker"


STEP 4 : Create a Virtual Environment
----------------------------------------
  Run this command inside the project folder:
      python -m venv venv


STEP 5 : Activate the Virtual Environment
-------------------------------------------
  On Windows CMD:
      venv\Scripts\activate

  You will see (venv) appear at the start of the line.
  This means the virtual environment is active.


STEP 6 : Install All Dependencies
------------------------------------
  Run:
      pip install --upgrade pip
      pip install -r requirements.txt

  NOTE: This downloads large AI libraries (PyTorch, Whisper,
        Transformers, FAISS, etc.) and may take 5-15 minutes.


STEP 7 : Set Up the .env Configuration File
---------------------------------------------
  Copy the example config:
      copy .env.example .env

  Open the new ".env" file in Notepad or VS Code.
  Edit these important lines:

      OPENAI_API_KEY=sk-your-key-here    <-- Paste your OpenAI key here
      OPENAI_MODEL=gpt-3.5-turbo
      LLM_PROVIDER=openai
      WHISPER_MODEL=base
      WHISPER_DEVICE=cpu
      APP_PORT=7860

  If you do NOT have an OpenAI key, leave it blank:
      OPENAI_API_KEY=
      LLM_PROVIDER=huggingface

  Save and close the file.


STEP 8 : Create Required Folders
-----------------------------------
  Run these commands (copy-paste all at once):
      mkdir data\videos
      mkdir data\audio
      mkdir data\transcripts
      mkdir data\summaries
      mkdir data\embeddings
      mkdir outputs\final_notes
      mkdir outputs\timestamps
      mkdir outputs\action_items
      mkdir outputs\reports
      mkdir models\whisper
      mkdir models\embedding_model
      mkdir logs


STEP 9 : Start the Application
---------------------------------
  Run:
      python main.py

  You should see:
      ============================================================
         Deep-Dive Video Note Taker  v1.0.0
      ============================================================
        Host : 0.0.0.0
        Port : 7860
      ============================================================

  The server is now running!


STEP 10 : Open the Web Dashboard
-----------------------------------
  Open your browser and go to:
      http://localhost:7860

  Also available:
      http://localhost:7860/docs   --> Swagger API docs
      http://localhost:7860/redoc  --> ReDoc API docs


STEP 11 : Use the App
-----------------------
  1. Click "Upload Video" on the dashboard
  2. Select any video file (MP4, AVI, MOV, MKV, etc.)
     OR an audio file (MP3, WAV, etc.)
  3. Wait for transcription to finish
  4. Your structured notes will appear automatically
  5. Use the Q&A box to ask questions about the video
  6. Click "Generate Quiz" to test your understanding
  7. View Action Items and Topics tabs for more insights


STEP 12 : Stop the Server
----------------------------
  Press  Ctrl + C  in the terminal window.

  To deactivate the virtual environment:
      deactivate


============================================================
  WINDOWS ONE-CLICK SHORTCUT (Skip Steps 4-9)
============================================================

  If you just want to run it quickly on Windows:

  Double-click  "start.bat"  in the project folder.

  It does everything automatically:
    - Creates the virtual environment
    - Installs all packages
    - Creates the .env file
    - Creates all folders
    - Starts the server


============================================================
  QUICK TROUBLESHOOTING
============================================================

  Problem : "python is not recognized"
  Fix     : Reinstall Python and check "Add to PATH"

  Problem : "pip install" fails or is very slow
  Fix     : Try:  pip install -r requirements.txt --timeout 120

  Problem : FFmpeg error during video upload
  Fix     : Install FFmpeg and restart your CMD terminal

  Problem : Out of memory with local model
  Fix     : In .env, change  WHISPER_MODEL=tiny

  Problem : Notes quality is poor (no OpenAI key)
  Fix     : Add your OpenAI key to .env and set
                LLM_PROVIDER=openai

  Problem : Port 7860 already in use
  Fix     : In .env, change  APP_PORT=8080
            Then open  http://localhost:8080

============================================================
  AUTHOR  : Rajiv Ramteke
  VERSION : 1.0.0
  LICENSE : MIT
============================================================