Interesting, but why go through all of these steps instead of using something like double bot, which just works out of the box and has all of the right models?
@@AICodeKing the problem is that I don't know how many tokens day to day coding will use. Maybe more, maybe less. Maybe even using it for autocomplete works out cheaper, or not much more expensive. Please make a video in a while to let us know what the costs turn out to be.
Sadly, autocomplete does not seem to work. I installed the model and successfully tested it from console. I adjusted the config.json file to contain the tabAutocompleteModel property with all shown values (it was not there after plugin installation). I see no errors, continue tells me: "index up to date" in the status row. But nothing happens in my code files.
I even tried it with ollama server to spin up the API (ollama ps is showing the model as loaded). No success and no http request in the developer tools of vsc.
With Claude 3.5 as the Copilot, can it see your entire codebase? If it can, compare it to just embedding your codebase. The other day I sent my codebase to Claude 3 Opus and worked through some issues I was having. The API costs were $64. I'm wondering if the codebase got embedded into the prompt and was sent back and forth with each query. How else would it use up so many tokens?
There's option to add your entire codebase as context in ContinueDev. But, I wouldn't recommend that due to the huge API costs that might come. Instead, you can just add the context you need to work on. Also, The new Claude 3.5 Sonnet is much cheaper than the previous opus model (Previous one was like $15/m token while this is just $3/m token)
@@AICodeKing btw github copilot uses GPT-4 or so they say. Sonnet-3.5 is really good but is it going to be worth it using like that (as in pay as you go model)? Also, github copliot is privacy oriented and secure (or so they say) compared to Sonnet-3.5 which is not private (they will work on the data you provide afaik).
@@AICodeKing could I add files and knowledbase (entire codebase and related similar projects) to an assistant in OpenAi playground and then use that particular assistant. Would that bring down costs since does not need to send codebase back and forth?
Yeah I found it won't allow me to paste the API key in this way. Find the .sgptrc file in your C: drive. Navigate to C: > Users > "Whatever your username is" > .config > shell-gpt > .sgptrc Then edit as per his tutorial. Hope this helps!
Thanks for making these videos.
Thank you for this video, much appreciated
Pretty cool content. Not exactly step by step but I guess there are older videos to watch to catch up :)
Excellent walkthrough of how to set this up 🙌
Great video. Would be awesome to see more like this and other models used if possible
AiCodeKing sounds like the goth guy from the ITCrowd :))
this was the most easy and hands on explanation.
this worked! you're a legend!
Interesting, but why go through all of these steps instead of using something like double bot, which just works out of the box and has all of the right models?
love this! thanks for sharing!
That's an amazing content! Which LLM do you consider to be the best for local use in the ContinueDev chat? Do you have a video on this? Thanks :)
Groq API + Continue ❤
Hi, how much are you going to spend like that per month? Less than $10?
It costs about $3 for a million tokens. So, You could get it below that amount if you don't use it for autocompletion.
@@AICodeKing the problem is that I don't know how many tokens day to day coding will use. Maybe more, maybe less. Maybe even using it for autocomplete works out cheaper, or not much more expensive. Please make a video in a while to let us know what the costs turn out to be.
Surely less than $10. I've do the comparison last month with Chat gpt
@@d.d.z. lets hope. I would love to just use sonnet 3.5 for aurocomplete as well. Almost never use the chat and other functionality.
@@apester2 try it and come back to talk about
Thank you for this!
cool, what OS are you running?
How about using Claude 3.5 sonnet with gpt pilot Pythagora?
Excellent: 10/10
Sadly, autocomplete does not seem to work.
I installed the model and successfully tested it from console. I adjusted the config.json file to contain the tabAutocompleteModel property with all shown values (it was not there after plugin installation).
I see no errors, continue tells me: "index up to date" in the status row. But nothing happens in my code files.
I even tried it with ollama server to spin up the API (ollama ps is showing the model as loaded). No success and no http request in the developer tools of vsc.
Try restarting VS Code
its also not working for me :(
With Claude 3.5 as the Copilot, can it see your entire codebase?
If it can, compare it to just embedding your codebase.
The other day I sent my codebase to Claude 3 Opus and worked through some issues I was having.
The API costs were $64.
I'm wondering if the codebase got embedded into the prompt and was sent back and forth with each query.
How else would it use up so many tokens?
There's option to add your entire codebase as context in ContinueDev. But, I wouldn't recommend that due to the huge API costs that might come. Instead, you can just add the context you need to work on. Also, The new Claude 3.5 Sonnet is much cheaper than the previous opus model (Previous one was like $15/m token while this is just $3/m token)
@@AICodeKing btw github copilot uses GPT-4 or so they say. Sonnet-3.5 is really good but is it going to be worth it using like that (as in pay as you go model)? Also, github copliot is privacy oriented and secure (or so they say) compared to Sonnet-3.5 which is not private (they will work on the data you provide afaik).
@@SahilP2648 They use GPT-4 for chat, but GPT-3.5 for everything else.
@@AICodeKing could I add files and knowledbase (entire codebase and related similar projects) to an assistant in OpenAi playground and then use that particular assistant. Would that bring down costs since does not need to send codebase back and forth?
So cool if I knew how to code :) is there any setup for Notion?
Will try to cover something like in upcoming videos.
It was working great for me but now after a few hours Im getting a HTTP 429 too many requests error
i had the same issue
any reason why sgpt doesnt seem to work as a command for me
Check If pip package path is in your Terminal environment.
is the limitations same as claude 3.5 pro version ??
Pretty cool
What would you say is better, Continue or Cursor?
I prefer contiue because it's free
installing a python library globally sounds very windows-y. I know you can do it in *nix. I do it sometimes. Still feels dirty tbh 😅
Im not able to find the shell_gpt file you showed can you tell the location. Im using anaconda
It should be at ~/.config/shell_gpt/.sgptrc
It looks like OpenAI has changed the code, I am getting the "BadRequestError: 400 Bad Request" when I try to put in the API Key,
Yeah I found it won't allow me to paste the API key in this way. Find the .sgptrc file in your C: drive.
Navigate to C: > Users > "Whatever your username is" > .config > shell-gpt > .sgptrc
Then edit as per his tutorial. Hope this helps!
Is possible to handle questions to the web interface from vsc? instead of api i think the $20 plan would be cheaper for our use in much scenarios
What do you mean? Using the extension if you just use the pay as you go model, then yes, it's not for code only.
Claude in programming is waaay much better than ChatGPT
I am using Jetbrains AI.
You have very nice voice
Github copilot is driving me nuts. It's sooo dumb.
For real? GitHub Copilot still use GPT-3?
Yes, it does.
Chat says it uses gpt4 turbo?
how do i add it to nvim? thanks
checkout my Avante Nvim video.
@@AICodeKing will do, i just got claude api key and set up with shell_gpt, thought of using it in nvim too.
need support
really you are jumping from A to B...
can´t found .sgptrc, thanks for the video
found cmd+p ~/.config/shell_gpt/.sgptrc :)
You can check the ShellGPT github repo. It has the path listed there.
why i always got missing config key for openai?