Frequently Asked Questions

These are some of the most frequently asked questions about Pythagora. There's additional articles in our wiki. If you're new to Pythagora, check out the YouTube playlist How to use Pythagora Like a Pro. There's additional help videos on our YouTube channel.

If you don't find an answer below, try asking in our Discord community or you can contact us here.

What is the difference between Pythagora and GPT Pilot?

Pythagora is our VS Code extension as well as the name of our company. GPT Pilot is our open-source codebase Pythagora is built on top of.

What is Pythagora v1 and how does it differ than the beta VS Code extension?

Version 1 (v1) of the Pythagora VS Code extension was released in October of 2024 and we're rolling out access over the coming weeks. v1 is a completely new VS Code extension and the old, beta version of the VS Code extension has been deprecated.

How do I get access to Pythagora v1?

You can sign up for access here. To check on the status of your v1 invite, you can contact us here.

What is Pythagora Pro?

Pythagora Pro is our pay-as-you-go pricing model where you pay upfront for usage. The token costs with Pythagora Pro are the same as the underlying LLMs, just like if you were using your own API keys.

What is the pricing if I use my own API key?

If you’re using your own API key(s), the cost will depend on the LLM provider and model you choose. For example, if you're using an OpenAI api key, your pricing will be determined by OpenAI and their pricing plans. Switching to a more expensive model will make the price go up, etc.

Which version of Python do I need?

You will need a Python version between 3.9 and 3.12. You can see your current version by running this command in your command line interface tool:

python3 --version

Which LLMs and models can I use?

For Pythagora Pro users, we recommend not making any changes to the LLM providers and/or models used. Our team does extensive testing to ensure that Pythagora uses the best models currently available for all of Pythagora's agents. Modifying the configuration to use different models may cause Pythagora to underperform or not work as expected.

If you're using your API key, this article will explain how.

The Pythagora VSCode extension asks me to log in? What am I logging into? Do I need to use my OpenAI email and password?

This is separate from your OpenAI email/password. We're building a cloud version of Pythagora so the VSCode extension already signs up to our system. We also use this to ask you for feedback (how was Pythagora for you).

I entered my API key but I get "you don't have access to gpt-4" or "openai model not found" error

Please note that Pythagora subscription and OpenAI API/Anthropic subscriptions are separate. To use Pythagora with GPT4 (as an example), you need to have a paid subscription to OpenAI API. To verify this, you can go to OpenAI API Playground and check if you can use the appropriate models.

I start Pythagora/GPT Pilot and get an error like TypeError: 'type' object is not subscriptable

Check that you're running Python version 3.9-3.12. If you have multiple Python installations on your system, GPT Pilot might have picked up the incorrect version. You can check your version with the command python3 --version in your CLI.

You can fix this by manually setting up Python virtual environment in gpt-pilot/pilot-env directory using your preferred version of Python:

cd '/install/path/of/gpt-pilot/`
rm -rf pilot-env venv
/path/to/correct/python3 -m venv venv
./venv/bin/python -m pip -r requirements.txt

(on Windows it's the same, except it's easier to remove the pilot-env folder in File Explorer, you need to use '' instead of '/' for paths, and you need to run 'pilot-env\Scripts\python.exe` instead of './venv/bin/python').

I get the following error in the VSCode extension: "No module named dotenv"

The Python virtual environment, which should have been automatically set up by VSCode installation, wasn't complete. You can do the same workaround as in the previous answer.

Can I use this for an existing project?

Yes, we have experimental support for smaller, existing projects. More info available in this article.

Pythagora/GPT Pilot is very slow and eats tokens like there's no tomorrow, why?

Pythagora/GPT Pilot currently gets slower the more files you have in your project.

I got TokenLimitError, how to work around it?

Pythagora/GPT Pilot sends project files to the LLM. If you have large text files in your project, Pythagora/GPT Pilot might pick them up and trigger this error. To avoid this, you can list those files (or folders) in fs.ignore_paths setting in your Pythagora/GPT Pilot config.json configuration file, like in this example:

{
  ...
  "fs": {
    ...
    "ignore_paths": [
     ... // default files that are already ignored by Pythagora
     // add additional ignore rules here, for example:
    "*.log",
    "*.lock"     
    ]
  }
}

Which language(s) does Pythagora support?

We're focusing on the Node/Mongo/Express stack for now, as our team is doing all of our internal testing with this stack. Our team is still smoothing out the edges for web app development, but once we nail that, we’re planning to branch out to other languages.

With Pythagora Pro, do my credits expire?

With Pythagora Pro, you’re prepaying for usage, so it doesn’t expire. Your balance only goes down as you use it, but if you don’t, your money stays put in your account.

This rocks! Can I buy you coffee?

Thanks! The best way to help right now is to tell your friends about Pythagora, star the GPT Pilot repo, help spread the word about us, and be active in our Discord community!