chatgpt-shell
chatgpt-shell copied to clipboard
xenodium
ChatGPT and DALL-E Emacs shells + Org babel 🦄 + a shell maker for other providers
I know that this was discussed in #279 and so I apologize if I am not understanding correctly. First - is it possible to prevent the buffer from scrolling while...
Hi! I often have multiple projects open at the same time, but currently chatgpt-shell uses a single shared chat buffer across all of them. It would be super helpful to...
This fix addresses #333 . It embeds the system_instruction portion of the POST body , conditionally. With this fix, using most Google-hosted models, the POST body looks like: ``` {...
It would be awesome if you can support GitHub Copilot CHAT like is integrated here: https://github.com/chep/copilot-chat.el TY!!!
at work we “locally” run several models that are all available via an API that works like the OpenAI API, but instead of `/v1/chat/completions` it uses something different (see below)....
Just figured I would put here this consult function for chatgpt-shell buffers I've been using, it uses the process name to fetch all the chatgpt-shell buffers so no need to...
When the Google API returns an error, there appears to be a race condition in shell-maker.el, which co-mingles error messages from shell-maker with error messages from the remote API. the...
The prompt sent via `chatgpt-shell-google--make-gemini-payload` includes a system instruction, and results in a JSON payload, something like this: ``` { "system_instruction": { "parts": { "text": "You use markdown liberally to...
o1-pro is now available in the OpenAI API. Unlike other OpenAI models, it only supports the responses API rather than the completions API. This will require a small amount of...
The idea is getting the performance I detected using DeepSeed models via OpenRouter.
