Transformations UI and Long Form Podcasts

Please, take notice on the warning below for users migrating from 0.1.0

Changes in this release

• Transformations are not longer managed in yaml file. They've moved to the UI under the Transformations menu item, making it simpler and easier to customize your prompts.
• Long form podcasts (15+ minutes) are now available, with improved Gemini api
• Many bug fixes

Error Migrating from v0.1.0

If you are migrating from version v0.1.0, there was a problem in the Surreal SDK that made the migrations count go crazy. So upgrading to 0.1.1 might not trigger the new database migration that is required for this to run. I fixed the issue on my fork of the SDK for now. But if you already ran 0.1.0, you need to do a fix.

If that is your case, just follow this:

Start the app.

docker compose up

Enter the docker compose exec mode on the DB machine

docker compose exec surrealdb /surreal sql --endpoint http://localhost:8000 --ns open_notebook --user root --pass root --db open_notebook

Run this command to reset the migration count to the right number:

delete from _sbl_migrations where version > 4;

Then, just run the app on the browser and let it migrate correctly.

If you don't want to do all that, you can also just delete the surreal_data folder and start from scratch.

v0.1 - Release Candidate

• Better citations and improved search capabilities
• The "Ask" feature is much smarter now and let's you check its thinking
• Enabled support for X.AI and Groq models
• Select default transformations to apply to all content
• Save insights as custom notes
• Items are added to context by default

v0.0.10 - Gemini Podcast Support

This release enables the use of Gemini for Text to Speech.

The new Gemini Text to Speech models are amazing and definitely worth using. But in order to use them, you need to do a little setup. Please refer to this Podcastfy help page for details. But it basically requires you to enable the Text to Speech API and add it to your API Key.

The quality is definitely worth it, check out this demo:
https://www.veed.io/view/4c514532-9311-41a6-8af6-9053e14f7a5b?panel=share

v0.0.9 - Ask your Documents, Citations and Multiple Sessions

Ask the Documents (RAG)

• Added a tools model default for picking a tool-enabled model
• Create a RAG tool and the Ask the Docs feature. Now, you can ask questions and have the model search the catalog for documents before replying.

Multiple chat sessions

• You can now create as many separate conversations as you want on each Notebook. This way, you can keep different conversations separated and avoid getting the model confused with long histories.

Citations

• When a document is used to formulate an answer, it is now linked in the answer. Clicking it takes you to a page to review it.

Bug fixes

• Fixed item icons for sources and notes
• Fixed default model bug where default model was not updating without app reload

Improvements

• Model Manager for loading models
• Improved the quality of text and vector search results
• Content chunking is based in paragraphs, sentences now. Doesn't cut phrases in the middle.

v0.0.8 - Transformations Playground and New Pattern folder structure

Add Transformations Playground
Refactor pattern folder structure to support custom patterns
See boilerplate project on how to setup
Some bug fixes

v0.0.7 - Model Management 🗂️

• Manage your AI models and providers in a single interface
• Define default models for several tasks such as chat, transformation, embedding, etc
• Enabled support for Embedding models from Gemini, Vertex and Ollama

v0.0.6 - ePub and office support

• Epub support
• DOC, XLS, PPT support
• Clean up source files after processing

v0.0.5 - Audio and Video support + several bug fixes

• Process transcripts from audio files using Open AI
• Process transcripts from videos by first extracting the audio channels
• Fixed a problem where content > 1Mb was failing to save
• Organizing all data folders under /data for easier volume mounting and backup
• Prevent creating a podcast with no context
• Improve object validation to reduce errors
• Improve handling of unknown content-types
• Implement a version check feature to alert users about new versions
• Fixed an issue with pydantic date conversions

v0.0.4 - Creating Podcasts

Podcasts

For the audio learners

The podcast feature made Google Notebook LM famous and for a good reason. It can make your learning process 10x more enjoyable and efficient by processing a lot of insights in a way that is very easy to consume.

Define Templates

Setup a template for your podcast, you can get very creative here.

• Create a name and tagline for your podcast
• Define specific content instructions
• Define the role and tone of voice for both speakers
• Pick a language for the podcast
• Customize conversation style, engagement techniques, dialogue structure
• Define the length of each episode
• Pick your voice models (Open AI and Eleven Labs supported)

Pick your context

Pick the specific context you'd like to use to base your podcast.
You can use your own notes and assets and steer the content production.

Generate your podcast

Manage, Listen to and Download your episodes

Check out a sample using my own voice created on Eleven Labs and a interview format.

You can generate your podcast in dozens of languages.

Head to the Podcasts page for more info

v0.0.3: Introducing Transformations

Open Notebook v0.0.3: Introducing Transformations!

We're thrilled to announce Transformations, a brand new feature in Open Notebook that supercharges your research with a series of customizable content processing steps!

What Are Transformations?
Transformations are flexible workflows that allow you to take text content and apply a series of operations to it, producing a new, richer output. Whether it's summarizing articles, generating key insights, or creating reflective questions, Transformations make it easy to customize and enrich your research.

Transformations are built using Patterns that you can chain together in the transformations.yaml file. For instance, you could summarize a text and then generate topics from it—creating an insightful, layered output.

How to Set Up Your Transformations
Define your transformations in the transformations.yaml file, and add prompts in the patterns folder to tailor the output just how you like it.

Contribute to Our Growing Library!
Got a creative idea for a new transformation? We'd love for you to share it! Submit a pull request and contribute to making Open Notebook even more powerful.

Learn more about Transformations and get started: [link to full documentation]

Together, we can redefine how we approach note-taking and research. Transform your research today with Open Notebook!

Get Started Now