Enhanced Security

• Endpoints now require authentication
• Clickjacking prevented
• Secure websockets, if https is used

Pre-release of the upcoming 2.0.0 incognito pilot release.

This release fixes u bug which prevented the correct working with Azure OpenAI services.

This release improves security by better protecting the websockets for the LLM and interpreter services.

New release with many exciting updates 🎉!

Llama 2 Support

We added support for Llama 2, so you can run Incognito Pilot fully locally. For now, there are two ways of using it:

• Using a cloud API from replicate.
  While you don't have the advantage of a fully local setup here, you can try out the 70B model in a quick way without owning powerful hardware.
• Using Hugging Face's Text Generation Inference container,
  which allows you to run llama 2 locally with a simple docker run command.

Further Improvements

• GPT models now also usable via Azure
• Streaming responses from LLMs
• Syntax highlighting in the code preview
• Reject code execution or results

Pre-release of the upcoming 2.0.0 incognito pilot release.

Pre-release of the upcoming 2.0.0 incognito pilot release.

First official release of Incognito Pilot 🎉

Pre-release of the upcoming 1.0.0 incognito pilot release, containing nearly all functionality, but missing most of the documentation