🎉 Unlock 20x productivity with AI understanding your entire codebase! Imagine talking to your codebase and coding faster in natural language. Introducing Praison AI Code – an innovative solution to supercharge your development process. 🚀 Knowing my entire code base with AI resulted in a 20x increase in performance of PraisonAI code In this video: Discover how AI can increase your productivity by 20x 📈 Learn to navigate and tune PraisonAI code effortlessly 🛠️ See real-time contextual updates and seamless integration with tools like ChatGPT, Google Gemini and more 🌐 Improve coding speed and accuracy with AI-assisted code suggestions ✨ Setup steps: Navigate to the codes folder and run the Praison code AI. Install required packages and integrate with preferred LLMs. Customize your context and start interacting with your entire code base. 🔗 Links: Patreon: Ko-fi: Discord:…
I just glanced through the video. I see the "knowing my entire code base" part, but don't see the "20x productivity increase" part. The more I watch AI coding videos the more it seems it's mostly beginner coders. I could be wrong, but that is what it seems.
How to use command r+ model?
@MervinPraison I did the export OPENAI_API_KEY="…" with my real key but nothing is being returned in the browser except your logo. Suggestions?
@MervinPraison I have been facing issues when i query my codebase and it crashes to the login page again
are you using chainlit to build that project ?
I was trying with it for few days, now when I login then submit a prompt it goes back to login?! any advice?
Good video 👍I need a small help in installation.
I'm getting error at the time of installation in Mac. can you please help @mervin?
pip3 install "praisonai[code]"
Collecting praisonai[code]
Using cached praisonAI-0.0.5-py3-none-any.whl.metadata (747 bytes)
WARNING: praisonai 0.0.5 does not provide the extra 'code'
How does this compare with Cursor?
Sure, let's just throw an arbitrary 20x developer now because the usual 10x is not hype enough anymore.
what languages does it work on
This sounds great, but oh my god, I have never had such problems with dependencies. Couldnt get it to work in colab or locally. Tried using poetry to install requirements. Specifically, right now the requirements cant solve a conflict between mdocs-material and mdocs-jupyter. It is unsolvable. Been trying to get this to run for DAYS. Please god give me an answer to resolve conflicts.
My initial feedback from trying it (with a larger project with 900K tokens), is:
1. It may help to have multiple profiles in the settings file. Like, iOS only folders, or Android only folders, docs folders (as per my own case)… Preferably the UI would have an option to switch between these profiles.
2. The settings file should have an allow_only option, as opposed to just an ignore option – that way, we could just white list a few directories.
3. A dropdown or autocomplete for most of the current OpenAI, Gemini, Anthropic, etc. models would simplify selection… May as well let the user enter their own preference. But for common cases, a dropdown would definitely be better.
Anyway, cool project… Very promising idea.
not local, not private… not pushing my work through to the cloud
Then there's no way to make it work for Windows?
Great serving to the community man its just amazing now the developers could save tons of time and even they can be more productive same time!
How is this different than Cursor? Did anyone tried both?
Hey Mervin! Thanks for all! You're amazing! For some reason I'm not able to set the Gemini API Key using EXPORT or even SET. Is there a way to define my key directly on the code? Thanks! (Ps. I'm running it on Windows)
Hi Guys, I am facing an error, when I give a prompt to praisonai chatbox, it's redirecting to the login page, after logging it starts from the beginning. I tried to explore the solutions but didn't get anything. Does anyone have any idea?
Does it only work with Python Repository?
Found solution but i think we need the ability to update the prompt as it always does the same specially with ollama.
Struct with the error:
2024-07-16 21:05:35,823 – 140099669417984 – __init__.py-__init__:632 – WARNING: SDK is disabled.
2024-07-16 21:05:35,824 – 140099669417984 – __init__.py-__init__:1218 – WARNING: SDK is disabled.
2024-07-16 21:05:38,085 – 140099669417984 – sql_alchemy.py-sql_alchemy:67 – WARNING: SQLAlchemyDataLayer storage client is not initialized and elements will not be persisted!
Amazing. I wanted to run on windows, but resorted to WSL Ubuntu.
I am getting this error. You may want to know:
(graphrag) dev@lenovo:~/graphrag$ praisonai code
2024-07-16 11:15:31,897 – 139739273670656 – __init__.py-__init__:632 – WARNING: SDK is disabled.
2024-07-16 11:15:31,898 – 139739273670656 – __init__.py-__init__:1218 – WARNING: SDK is disabled.
2024-07-16 11:15:33,872 – 139739273670656 – sql_alchemy.py-sql_alchemy:67 – WARNING: SQLAlchemyDataLayer storage client is not initialized and elements will not be persisted!
I am using mac, when i try to run 'praisonai code' command inside project directory i get this error, note that pip didnt work when I installed so I followed a chatgpt process where I successfully installed using 'pipx'.
The package works well including opening in the browser and displaying file structure in the console but when I try to chat is when I get this error """""ValueError: the greenlet library is required to use this function. No module named 'greenlet'"""""""""""""
great work! I have an issue though that every time I try my first prompt on my local codebase, praison ai logs me out! any ideas? tested on safari and chrome
everything work well until when i ask like this "give me overview of this code base." and then it log-out
Nice work. can you add some functions to include including folders instead of exclusions. Also it would be nice to just point and click on ui to exclude or include folder/files.
Mervin, is it possible to have an include yaml as opposed to exclude? I want to use this across different codebases and would like to just use a directory as my include to evaluate and work on.
1) So each time you send the whole context? (looking at the speed, seems unlikely you recreate embedding on every run — but you state "realtime updates")
For a medium sized project, it will prolly run into 1M input tokens spent in 15-20 prompts? That's pretty expensive.
2) Way easier to use an IDE plugin with context support, it will dynamically choose context (I mean unlikely whole context is even needed, if you want to change a small function in one file for example) and there are plenty of such plugins — so you wont have to open another app and copy stuff from there. Github Copilot, JetBrains AI, Machinet, Sourcegraph Cody are only a few.
Hardly see what are the benefits of using extra app, if you can have everything in the convenience of your IDE.
got it working. do not make your own login. it will log you in but every time you try to run code it will crash and kick you out. when i logged in as admin/admin it worked. are you going to put this on github so everyone has access to the core files?
aider-chat….. knows your codebase is integrated with git runs with gpt-4, claude-3.5 or local ai has realtime context updates, can search websites, you can speak to it via microfone and it will actually write git commits and commit changes in the actual files