Do you love NotebookLM but hate Google? Try this open source alternative

Open Notebook is practically a clone of NotebookLLM’s core functionality, including notable features like audio summaries, the ability to ask questions about your research sources, and much more. Of course, nothing is perfect and it is not without drawbacks. Below, I’ll delve into what I love about Open Notebook, what’s less ideal, and how to try it for yourself.

The main features are practically the same as those of NotebookLLM. You upload feeds from PDF files to YouTube videos and everything in between, and then synthesize this information into audio, quizzes, or you can just chat with them.

Let’s start with what really differentiates Open Notebook from NotebookLLM: it’s an open source project that you have to configure yourself. This has some disadvantages, which we will talk about later. It also means that your data is truly secure in a way that NotebookLLM is not. You even have greater flexibility and customization options than Google offers.

You can run Open Notebook locally using a model like Ollama or connect it to your favorite cloud-based AI models, including GPT, Gemini Pro, Opus, and more. It’s also pretty easy to switch between models, so there’s no need to lock down a single option here either.

Even better, there are no limits on the number of notebooks you create or the number of fonts you use. Meanwhile, the free version of NotebookLM limits you to 100 notebooks with no more than 50 fonts each. That said, using Open Notebook will still exhaust token limits if you use a cloud-based model, so it’s worth keeping that in mind.

As much as I like Open Notebook, it’s important to be honest about its disadvantages.

First, this is not a plug-and-play experience by any means. While I’m a computer expert with decades of experience, installing Open Notebook manually on a Chromebook was a huge hassle, to say the least. It took me two tries and several hours to set it up this way. It was much easier on Windows thanks to the Docker Desktop app, which took about half an hour to set up, but still required a bit of DIY knowledge and troubleshooting to get everything right.

Let’s also talk about your audio summary podcasts. While I appreciate that you can have up to four voices instead of just the two-voice option with NotebookLLM, the audio breakdowns are much shorter by default. Instead of the 8 to 15 minute limit you’ll get with NotebookLM, audio interruptions are typically closer to a few minutes.

You can customize it and increase the length to 30 minutes or more, but I still found the quality of the podcast to be not as clear. I used a few different models and still felt that NotebookLM crashed a little harder.

You’ll also need to have the service running through a central PC or your own cloud setup before you can use it on other devices like Android. Even then, you’ll have to use a web browser since there’s no native app.

As I said before, installing Open Notebook can be a bit complicated, but the easiest way is to install attachable desktop, It allows you to run containerized applications directly without using both the command line interface.

Once the program is running, you will want to obtain the API key from the chosen provider. The exact process for this will vary.

While there is an official getting started guide for this process, it is important to note that it is actually outdated in several areas. For those planning to install a cloud model, the steps below will guide you through the basic initial setup.

Start by creating a configuration file. You’ll want to open something like Notepad and paste the following:

services:
surrealdb:
image: surrealdb/surrealdb:v2
command: start –root user –password –bind 0.0.0.0:8000 rocksdb:/mydata/mydatabase.db
ports:
– “8000:8000”
volumes:
– ./surreal_data:/mydata
# Removed health check because v2 image is too minimal to run wget/curl
restart: always

open_notebook:
image: lfnovo/open_notebook:v1-latest
pull_policy: always
ports:
– “8502:8502” # Web UI
– “5055:5055”#API
atmosphere:
– OPEN_NOTEBOOK_ENCRYPTION_KEY=change-me-to-a-secret-string
– SURREAL_URL=ws://surrealdb:8000/rpc
– SURREAL_USER=root
– SURREAL_PASSWORD=password
– SURREAL_NAMESPACE=open_notebook
– SURREAL_DATABASE=open_notebook
volumes:
– ./notebook_data:/app/data
depends_on:
– surrealdb
restart: always

After creating the file, you’ll want to edit it. change-me-to-a-secret-chain and replace it with a phrase of your choice. It will then save the file as docker-compose.yml in a new folder called open notebook.

Next, you’ll want to run Docker Desktop. Once it is active, open File Explorer and navigate to the Open Notebook folder where you placed the configuration file. Right click anywhere in the window and select Open in terminal.

The Terminal window will open and you will want to enter: docker compose -d

After about 15 seconds, the services will start and you can access Open Notebook in your browser by typing http://localhost:8502 in the address bar. The Open Notebook user interface should open, but it’s not done yet.

You will want to go to Manage > Models, Find your preferred AI company in the list and click Add configuration button. A new box will appear asking you to enter a name for your configuration and the API key. After adding both, click Add configuration button.

You will notice a Proof next to your new configuration at this time. Click this button to test the connection. You will also need to specify which model you want to use for chat, embedding, and transformations. The last of these options refers to the process used to create reflections, indexes, audio summaries, and more.

Once all of this is complete, you should be in business. Then you can go to New and create a new Notepad. From there, it’s just a matter of adding sources and testing all their transformation capabilities. That said, you’ll still need to configure Podcasts settings and a few other things. For brevity, I won’t go into all of these details, but you can find more in the Open the Notebook Getting Started Guide.

So, is Open Notebook better than NotebookLM? Honestly, the answer depends on your needs and how much you’re willing to play with the settings to customize them to your liking. Open Notebook could certainly be worth it for those who love the idea of ​​NotebookLM but don’t like their data sitting on a Google server. The same goes for those who like the tool but prefer a model that is not based on Gemini technology.

For everyone else, NotebookLM still performs slightly better, is easy to get started with, and can be further improved with an upgrade to NotebookLM Pro or Plus. But if you don’t mind doing some tweaking, Open Notebook is worth a try.