fred-bf

You are able to use ollama in dev builds, for production builds tauri is using different hostname, you may need to configure `OLLAMA_ORIGINS` follow this instructions https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-configure-ollama-server

We will publish an individual doc with step by step guide to integrate ollama with NextChat

Duplicated to https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/4030 , olz follow the feature progress in issue https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/4030

@catsimple could you share the original prompt of the message? I guess the raw content return by GPT contains the character '/'

NextChat only support 1 api key per provider for now. Not clear what do you mean in Multiple api_key

Hi, the chat history is stored in client side. So you cannot retrieve others chat history. Its possible after we support server-side history sync

Hi, thank you very much for your contribution, because jailbreak will lead to potential OpenAI's risk control of model attacks in the future, so we will gradually remove the relevant...

@nnWhisperer Hi, you can easily using Vercel or CloudFlare deploy NextChat, may I ask is there any specific requires to deploy on HuggingFace. As for chat history, NextChat stores chat...

OneAPI doesnt support Google Gemini API definition, you can diectly config the enpoint in custom endpoint(GPT like). As for model providers, the progress will be tracked in issue https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/4030

@H0llyW00dzZ Cool! The base url of gemini api should be able to configured via `GOOGLE_URL`, have you encountered any issue while requesting with the variable?