# Step-by-step: Run NotebookLM Clone Locally

You **do not have to** create a `.env` file. The app will run without it (it will use `MOCK_USER=localuser` automatically). A `.env` file is **optional** and useful if you want to set a custom username or use a Hugging Face token.

---

## Option A: Run without .env (fastest)

1. **Open a terminal** in the project folder:
   ```bash
   cd c:\Users\shail\Downloads\notebooklm__clone
   ```

2. **Create a virtual environment** (recommended):
   ```bash
   python -m venv .venv
   ```
   Then activate it:
   - **Windows (PowerShell):** `.\.venv\Scripts\Activate.ps1`
   - **Windows (CMD):** `.\.venv\Scripts\activate.bat`

3. **Install dependencies**:
   ```bash
   pip install -r requirements.txt
   ```

4. **Run the app**:
   ```bash
   python app.py
   ```
   If `MOCK_USER` is not set, the app sets it to `localuser` automatically.

5. **Open in browser**:  
   Go to **http://localhost:7860**

6. **Use the app**:
   - Click **Create** to add a notebook (e.g. name it "My first notebook").
   - Upload a **PDF**, **PPTX**, or **TXT** file, or paste a **URL** and click **Ingest URL**.
   - Click **Refresh sources** to see ingested sources.
   - Type a question in the chat and click **Send** (RAG will use your sources).
   - **Report, Quiz, and Podcast** require **GEMINI_API_KEY** (see Option B). Without it, the app shows a clear message and does not crash.

Data is stored under the `data` folder in the project (e.g. `data/users/localuser/notebooks/...`).

---

## Option B: Run with a .env file (optional)

Use this if you want a custom username or to use Hugging Face APIs (better embeddings and LLM).

1. **Create `.env`** from the example:
   - Copy `.env.example` to `.env` in the project root:
     ```bash
     copy .env.example .env
     ```
   - Or create a new file named `.env` in `c:\Users\shail\Downloads\notebooklm__clone\` with at least:
     ```
     MOCK_USER=localuser
     ```

2. **Add GEMINI_API_KEY for artifacts** (report, quiz, podcast transcript):
   - Get a key at [https://aistudio.google.com/apikey](https://aistudio.google.com/apikey).
   - In `.env`, add:
     ```
     GEMINI_API_KEY=your_key_here
     GEMINI_MODEL=gemini-1.5-flash
     ```

3. **(Optional) Add your Hugging Face token** for better RAG and chat:
   - Go to [https://huggingface.co/settings/tokens](https://huggingface.co/settings/tokens) and create a token (read access is enough for inference).
   - In `.env`, add or uncomment:
     ```
     HF_TOKEN=hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
     ```
   - Save the file.

4. **Then run as in Option A** (steps 2–6): activate venv, `pip install -r requirements.txt`, then `python app.py`. The app will load variables from `.env` automatically.

---

## Summary

| Step | Action |
|------|--------|
| 1 | Open terminal in `notebooklm__clone` |
| 2 | `python -m venv .venv` then activate (e.g. `.\.venv\Scripts\Activate.ps1`) |
| 3 | `pip install -r requirements.txt` |
| 4 | *(Optional)* Copy `.env.example` to `.env`; add **`GEMINI_API_KEY`** for artifacts (report/quiz/podcast); add `HF_TOKEN` for chat |
| 5 | `python app.py` |
| 6 | Open **http://localhost:7860** and create a notebook, ingest sources, then chat or generate artifacts |

You need **GEMINI_API_KEY** for report/quiz/podcast generation; without it the app shows a clear message and does not crash. Use `.env` for Gemini key and optional HF token.