[HN Gopher] Show HN: I made an open-source Notion-style WYSYWIG ...
       ___________________________________________________________________
        
       Show HN: I made an open-source Notion-style WYSYWIG editor
        
       Author : steventey
       Score  : 76 points
       Date   : 2023-06-16 17:49 UTC (5 hours ago)
        
 (HTM) web link (novel.sh)
 (TXT) w3m dump (novel.sh)
        
       | ilrwbwrkhv wrote:
       | "I am an AI writing assistant that continues existing text based
       | on context from prior text. Give more weight/priority to the
       | later characters than the beginning ones."
        
       | 1123581321 wrote:
       | Nice! Consider making so /h1 autocompletes heading 1, etc.
        
       | gabereiser wrote:
       | This is pretty slick. Unobtrusive prompt and then you get a
       | pretty intrusive drop-down. Pretty it up. It has a wonderful
       | response and flow and I would be interested in using this in
       | future projects.
        
         | wesleychen wrote:
         | The dropdown is part of the Notion styling.
        
       | digilypse wrote:
       | Very clever that the user is prompted to use the autocomplete to
       | read the description.
        
       | mbertschler wrote:
       | Couldn't open the GitHub link on my phone.
       | 
       | Here it is: https://github.com/steven-tey/novel
        
       | digdugdirk wrote:
       | Are there any examples of something similar that has the ability
       | to seamlessly interact with tables as well?
       | 
       | Notion seems to be the only player in the space that effectively
       | uses its tables as linkable databases, most similar products seem
       | to either lack table functionality or they're just simple
       | formatted text.
       | 
       | So much of my daily work revolves around databases and Excel, I
       | would love the ability to have multiple views of database tables
       | embedded in a text editor, varied by context, with full backend
       | control over the database itself. Bonus points if I could easily
       | have scripts run on them in the background, almost like a
       | programmatic kind of Excel.
        
       | joeframbach wrote:
       | Do you mind defining what "WYSYWIG" means?
       | 
       | I tried using your tool for it.
       | 
       | "WYSYWIG is an acronym that means++"
       | 
       | ...
       | 
       | "What You See Is What You Get."
       | 
       | :thinking:
        
         | gedy wrote:
         | What You See, You Won't Intuitively Get?
        
         | roetlich wrote:
         | WYSYWIG does indeed mean "What You See Is What You Get."
         | 
         | A WYSIWYG editor is an editor that shows the text with all
         | formatting, exactly how it will look once it's "printed". You
         | know, like Word or Google Docs. But unlike when you edit
         | markdown or latex in a plain text editor. For example, writing
         | comments on this site isn't WYSIWYG.
        
           | [deleted]
        
         | toxicFork wrote:
         | What you submit yields what I get
        
           | asymmetric13 wrote:
           | What You Submit Yields What I Give
        
         | esafak wrote:
         | WYSYWIG is a typo.
        
       | billconan wrote:
       | I have a similar project https://github.com/shi-yan/Epiphany
        
         | russellbeattie wrote:
         | Mine: https://hypertext.plus
         | 
         | Pure HTML document editor. Open source, PWA, based on TinyMCE,
         | with CSS and markup editing, JS macros, saves to local drive,
         | plus OpenAI integration if you have a key.
        
         | meesterdude wrote:
         | this looks nice and clean - why have you paused development? I
         | see there are 32 github issues
        
       | asymmetric13 wrote:
       | I fear I may have broken my first "note":
       | 
       | '<<>>' indicates where I typed '++' and the resultant text is
       | unedited.
       | 
       | It seems as though the AI response became "stuck" on a theme, and
       | my renewed prompts were insufficient to cause it to change /
       | reconsider context. . .
       | 
       | _____
       | 
       | Novel is a Notion-style WYSYWIG editor with AI-powered
       | autocompletions.
       | 
       | what backend is used for the autocompletions in Novel?
       | 
       | The auto completions in Novel are provided by <<>> The auto
       | completions in Novel are provided by a sophisticated backend
       | powered by state-of-the-art AI algorithms.
       | 
       | These start-of-the-art AI algorithms rely on underlying
       | technology from <<>> leading natural language processing (NLP)
       | frameworks such as OpenAI's GPT-3 and BERT. These frameworks have
       | been trained on vast amounts of text data to have a deep
       | understanding of language patterns and context. By leveraging the
       | power of thesed on massive amounts of text data and are capable
       | of generating high-quality and contextually relevant suggestions
       | for autocompletions. The backend of Novel leverages the power of
       | these advanced NLP frameworks to enhance the user experience and
       | provide accurate and helpful suggestions
       | 
       | Novel is funded by <<>> d on vast amounts of text data to
       | understand and generate human-like text. The backend
       | infrastructure of Novel leverages the power of these pretrained
       | models to provide accurate and contextually relevant
       | autocompletions. The sophisticated algorithms in the backend
       | analyze the input text
       | 
       | How is Nobel funded <<>> d on vast amounts of text data and have
       | achieved impressive results in various NLP tasks. The combination
       | of GPT-3 and BERT allows Novel to generate highly accurate and
       | contextually relevant autocompletions for users. The
       | sophisticated backend continuously learns
       | 
       | what does novel cos <<>> d on vast amounts of text data to
       | generate high-quality autocompletions. The sophisticated backend
       | in Novel leverages the power of GPT-3 and BERT, combining their
       | strengths to deliver accurate and contextually relevant
       | suggestions. With GPT-
       | 
       | It appears to be <<>> d on vast amounts of text data to generate
       | highly accurate and contextually relevant autocompletions. The
       | backend infrastructure of Novel leverages the power of these NLP
       | frameworks to process and analyze user input, allowing it to
       | generate intelligent suggestions in real-time
       | 
       | What if I want to write about <<>> d on vast amounts of text
       | data, allowing them to generate accurate and contextually
       | relevant suggestions. The backend of Novel utilizes a combination
       | of these NLP frameworks to enhance the autocompletion
       | capabilities. With GPT-3, the system can generate coherent
       | 
       | start a new topic <<>> d on vast amounts of text data and have
       | the ability to generate coherent and contextually relevant
       | suggestions. The combination of GPT-3 and BERT allows Novel to
       | offer a highly intelligent and accurate autocompletion feature to
       | its users. The backend architecture _____
        
       | jerpint wrote:
       | What model are you using in the backend? It's pretty fast to
       | respond. Very nice interface
        
         | jtokoph wrote:
         | According to the readme, it's OpenAI:
         | https://github.com/steven-tey/novel#tech-stack
        
       ___________________________________________________________________
       (page generated 2023-06-16 23:00 UTC)