Content Integration
Open Notebook provides comprehensive support for various content formats, making it your central hub for all research materials.
Documents
- PDF, Epub
- Text, Markdown
- Office files
Media
- YouTube videos
- Local video files
- Audio recordings
Web Content
- Web articles
- Blog posts
- News articles
How each content is processed
Link Processing
Add a URL to any website and the tool will scrape its content for you.
Youtube Transcripts
Add a URL for an Youtube video and we'll extract the transcript.
PDF, DOC, PPT, ePub
Those documents will be processed and their text extract.
Roadmap: improvements to tables in PDFs and use of Vision model for images
Video / Audio processing
Videos are converted to audio files before processing. Audio files are processed for transcript extraction and the transcript text is saved.
Roadmap: We might add support for Gemini video understanding capabilities at some point.
More Formats Coming Soon
We're constantly working on adding support for more content types and formats. Have a specific format in mind? Share your suggestions in our GitHub discussions!
Embeddings
When you upload new content to the platform, you have the option to enable embedding for that content. This will trigger a process that consists of generating chunks of 1000 words and embedding them using the model of your choice. This enables the content to appear in searches when the model is doing research for you through the Ask feature.
Although this is not necessary for you to use the app, it will greatly improve your experience and it is pretty cheap to use.
- text-embedding-3-small (Open AI): $0.020 / 1M tokens
- text-embedding-004 (Gemini): $0.012 / 1M tokens - large free tier available
- free with Ollama models, like mxbai-embed-large