FastAPI

Built 2 core endpoints of my backend.

What’s new?

• POST endpoint where we’ll get data from user in json format and write it to our redis db.
• GET endpoint where we’ll search for data with same id and return it, if there is no such data we’ll get 404
• Data deletes automatically after 1 hour.
• Now can handle only Python dict, but I’m planning to add at least few formats for different languages

GIT commits

5dbf63d

What next?

• Add more flexibility to POST endpoint and handle wrong types of data right.

Minor bug fixes

When you added api key for AI it was possible to paste wrong one and it still bypassed my checks. Also we had problem with links in the source notes.
But now everything works perfect!

Finished everything

Worked on some minor bugs and docs.

What’s new?

• You can change default AI model to any that you want.
• Good readme.
• Docs for all commands so –help looks good now.
• Pretty green loader on commands like ask or scan, makes it look much more “alive”.
• Published as pypi package!

GIT commits

2451efb

What next?

SHIUIIIIIP!

AI module

Worked on creating AI module for notee.

What’s new?

• You can ask AI questions related to your notes and it’ll respond based on them.
• You can choose between openAI, Google gemini and hackclub ai api.
• You can setup ai module either while running setup command or later.
• You can freely change your ai provider later.

GIT commits

98f3bf5

What next?

• Polish AI module
• Add loaders on slow funcitons
• Test notee more

Open any file from your vault

Worked on open file feature(autocompletion included!)

What’s new?

• Open any file from vault
• Autocompletion helps you to find this file(my pride)

GIT commits

b938806

What next?

• AI module. I’m planning to support as many apis as possible for ease of use.

Sticks up together

Project starts to look like something actually working

What’s new?

• md viewing with rich library
• when you search for some note you can choose and open note in few clicks
• cleaned code structure a little
  That’s all, but it made things 1000x times cooler

GIT commits

f5a18de

What next?

• open any file from vault with comfortable search tab

New features

Added vector database to store your notes.

What’s new?

• Chromadb where all notes are stored
• Scanning function(to add files that was created not with notee to the db)
• Automatically add new files to the db.
• Search needed note by query(doesn’t have to be exact because we use vector db)
• Commands to toggle obsidian_mode and different_folders features.

GIT commits

34c8db2 - Added almost all features that I told about(without testing).
2ae5d20 - Fixed all bugs that I found and added toggles.

What next?

• cli md viewer/webapp for this. I haven’t decided yet what to use.
• add ai module that will give you responces based on notes.

More templates

Created more templates and features

What’s new?

• Movie, source, todo, idea notes templates
• Obsidian handling(you can choose mode when you setting up project obsidian or default md)
• Added help texts for both commands and their arguments
• Cleaned code a little

GIT commits

2110d32 - Initializatoin of the project
81ce637 - First commands and lots of helper funcitons
3452cc8 - All new commands and clean up

What next?

• tags autocomplition
• chromadb to search notes by user promt
• more commands to cusomize everything

Start

Initialized project. Created stable base with config and CLI app. Started working on notemaking feature.

What’s new?

• Reliable project structure
• Config handling
• Setup command so set folder for notes and your notes “mode”
• First template for notes - book note

What next?

• Add more templates
• Handle notes mode(obsidian and default)
• Cleanup code a little till it didn’t turn into mess

Fixed bugs that I found using it by myself. Biggest one was with autostart. Now it’s 100% ready to be used by anyone!!

Finished everything!

Worked on some upgrades and cleaned codebase

What’s new?

• Evertything works well
• Now if you change default message it changes for new user too automatically
• If you gave someone custom message it won’t be overwritten by changing default message
• Autostart fixed
• Changed readme so it’s up to date

GIT commits

a4be5c4 - everything I wrote above

What next?

Ship!

Tik Tok interaction and debugging

Worked with tik tok interaction and debugging things that already existed.

What’s new?

• Now we can actually send messages to the people.
• New user searching script(previous sometimes lagged and wasn’t reliable).
• Added feature that we’ll send messages only once a day.
• Made console prints prettier
• Added almost full readme for the github

GIT commits

02bc3f9 - everything I wrote above

What next?

I’ll rework default and custom messages system, so it’ll work perfectly. Also I want to remake autostart command so it’ll work just with flags smth like streak-saver autostart --on.

CLI commands creation

I wanted to do login and cookie save first, but when I tested my code for 100th time tik tok just stopped to let me login. So I worked with CLI side of the project

What’s new?

• Created project structure and initial files
• Choosed libs for the project and organized dependencies
• Created setup command that downloads browser deps and sets up all project files
• Created login command that lets you to login to your account and save cookies(still testing)
• Created commands to interact with your friends list and default messages
• Created autostart commands to turn it on/off(still testing)
• And some utils to interact with config files and etc

GIT commits

7123cc3 - cookie retrieval and setup templates
0b23539 - structured project and added basic CLI commands
7548283 - restructured project, added more CLI commands and tested it all

What next?

I’ll add more commands and test them all while waiting till my tiktok shutdown ends, then I’ll start working on the actual messages sending and all features related to this.

Finalized everything!

• I’ve wrote styles for the pc version, fixed some for the mobile cuz they were too big for this skreens.
• Also added cat that runs after your cursor from oneko.js - wonderfull lib, and found purple version of the cat - what I needed for my purple theme.
• I changed background from static image to the gif so website looks even more alive now.
• Added Title and icon on for the page
• Loaded everything to the gh pages
  And now - SHIIIIP

Added last block. I decided not to overcomplicate the structure of the site and to keep it simple. Next I’ll optimize everything for pc’s, add few “cherries” and it’s done! Probably will ship in 2 days.

Added 3 more blocks, 2 more and mobile version is done! Also I wanna add something like a “snow” or just particles so website will look more alive. Also may be I’ll change background to something glitchi so it’ll look really cool. But I don’t want to add too much stuff cuz it’s not my style, but few kitties won’t hurt:}

Now available on the pypi!

Created “teamplate” on the paper, cuz I’m 0 at figma and too lazy. Watched some tutorial on typescript and then read docs - beautiful tool for someone like me, lets you to create styled websites realy easy and fast. Also found bounch of gifs and images that I’ll use in the website.
And finaly created first 2 sections of the website and added bg, I think it already looks good, but I’ll definetly change smth so it’ll be even better!

Made final changes to the code base, so now Jarvis should work on any computer. And I made a full trailer for v0.1!! I’ve never created stuff like that before, so this 2 minute video took me 3 hours. But I think it look pretty nice and can touch hurt. This was really great time, but after the ship I will probably take break from jarvis project for like a week to create some stuff that I wanted to create previously. I already have huge plans on what I’ll do with v0.2, but I wont tell yeh hehe. And now shiiip!

I’ve spent like a 5 unloged hours trying to setup everything to use pipx and understood - this project just not for this. There is too much troubles to setup it as a pipx package, because this project needs lot’s of customization and setting. So I fallen back to the github repo downloading. Now I’m setting up scripts and optimization so It will be really easy to setup it on your pc.

I’ve added preferences functional. Now Jarvis remembers some basic facts and preferences about you, that helps to respond to questions a lot. It uses internal db that I created previously. Also I reworked config file, now it has clean structure and comments for each variable. Now I’m starting to work on publishing to the pipx and easy setup. There is probably 1-2 to devlogs before I finally finish v0.1!!

I’ve added 2 new tools: 1 - interaction with user clipboard, it makes communication with Jarvis much easier. 2 - todo, now Jarvis can create, read and delete your todos, so you won’t forget anything, for this I created internal db - we can use it later for anything that we need just by creating new table. Also I rewrited readme, so now it looks almost solid and there is already some instruction how you can use Jarvis. Now I’m going to work on easy setup, so you’ll be able to setup everything in less than 10 munutes!!

I’ve added some sounds so Jarvis now feels more alive. It plays default sounds when the wake word detects “Hey Jarvis” and when we saving the chat, so we don’t need to see terminal to understand what’s happaning now. Also when it gets a user message it plays some of ready to use phrases like “Calculating” or “Working on it”, so our long latency don’t feel so long now. Also added him tools to fetch weather so now we can ask him about it, but sometimes he can choose wrong location like Kiev instead of Kyiv, but I’ll work on it!!

I cleaned project structure and added some logging(still haven’t finished with that). Then I started to test how Jarvis works and found really big issues with transcription and memory tools: 1. It transcribed some of things that he said, and then looped the chat speaking “with itself”. 2. When we retrieved memory there was too much context and he started to think that it isn’t just previous chat, but that it’s the chat we’re in and continued ended conversations.
I fixed both of this and now it works better than it was, but I understood that there is still lot’s of work till v0.1 is shipped😢

That was really lot’s of work, unloged work. I’ve set up tts(Yeah it sounds kinda weird and also it’s slow, but if it must be local it’s the best set up I’ve created so long), changed GPT model because previous wasn’t working with tools and thinking, set up memory for Jarvis using Chroma DB - best tool for this. Created lot’s of helper functions for all tasks that you can think off. Created audio player module that is working with tts on multithread(that was hard stuff for me to understand, but it saves us lot’s of responce time). And I tried to clean project structure, but there is still lot’s of things that I can do.
Talking about technical side - v0.1 is ready, so now I’m starting to clean the code, may be fix some bugs and prepare it for shipment. I’ll try to make devlogs more frequently cuz this one is too big.

This was a hella amount of work. I finished stabilization of speech transcribtion and connected local AI model that will respond to me, that was easy part. But now I’m literally for 12 hours trying to find a best TTS model/api to do work for me. I tried to fine tune model, but it was very bad idea with electricity problems in my country, then tried QWEN TTS - too slow. Now I’m writing it while downloading xtts model files, I really hope that it’ll work, cuz it’s already 11pm

Finaly! I added wake word functional, so now it only responds when I say “hey Jarvis”(just “Jarvis” works too). It works pretty well and even when I have background noice or music it captures this wake word.
Now I’m starting to work on real AI model that will run on my pc and give me responces, also I want to give it a voice of the real Jarvis from movies, so I’ll probably use some AI model to replicate the voice.
See you soon!!

Now Jarvis can hear me in realtime!! That was kinda hard to design, but easy to realize. I think I should play with models and decide which is better for me. In future it’ll be hard to combine lot’s of models on my single pc, but i’ll come up with some idea, I’m sure. Also my English is problem for transcribing, cuz model can’t understand what I’m saying, but I’ll fix it too!!

Worked on trying differet transcribing models, stopped on faster-whisper and then spent lot’s of time on installing drivers and everything else for it. Next step is to create alghorithm so it’ll transcribe me in real time and start to write promt after hearing word “Jarvis”.