The primary use case here seems to be that it might be possible to use this tool to spend <$20/mo for the same feature set as ChatGPT+. It does not currently make any effort to support locally-hosted open source models, which is what I would have assumed from its name.<p>If you're interested in a fully Libre LLM stack, I've had fun lately with ollama [0] and ollama-webui [1]. It was pretty trivial to take ollama-webui's docker-compose file and set up a locally-running chat server with Mistral 7B. Trying out different models and prompts was likewise very easy to get started with.<p>Mistral isn't anything like as good as GPT-4, but it's Apache licensed and fully local, which meets my definition of Libre. I'll continue to use both while the FOSS stacks catch up, but it's fun to keep up with the progress on the open source stuff as tooling develops.<p>[0] <a href="https://github.com/jmorganca/ollama">https://github.com/jmorganca/ollama</a><p>[1] <a href="https://github.com/ollama-webui/ollama-webui">https://github.com/ollama-webui/ollama-webui</a>
It's an open source client for ChatGPT.<p>(From the naming, I was expecting some "strongly free software", like LibreJS, Libreboot, linux-libre, which would not rely on something closed like ChatGPT - I guess if someone made a free LLM-based chat, they could call it ChatGPL (though they should probably not, too close to ChatGPT))<p>If I'm ever stuck in a situation where I need to use ChatGPT, I'll consider using LibreChat :-)
Libre ... seems to be co-opting the term a bit if it you can't run your llm local<p>What does this have that kobold.cpp, llama.cpp backends + sillytavern et al frontends with one of the thousand llm weights won't give you?<p>For entertainment, these offer simultaneous llm output with methods to retain context, allows outputs that can be vocalized via TTS voice simulation, inputs via mucrophone, and can provide illustrations of content via stable diffusion, and allow multiple chat bot "characters" to be in the same conversation, all of which honestly gets a bit surreal.
Decent list of UIs (includes LibreChat): <a href="https://github.com/korchasa/awesome-chatgpt">https://github.com/korchasa/awesome-chatgpt</a>
I have been wondering why I haven't really found good self-hosted UIs that could also use plugins / functions. Just installed this (which was quite easy) and it seems to work very well! Definitely gonna replace the one I was using before.
Is this truly open source? I mean, beyond just the UI/environment. A lot of AI models seem to be gratis-but-not-libre. It's great that they're even gratis but I'm curious just how libre this is overall.<p>I'm not being critical - just curious.
Totally misleading.<p>What you actually are looking for is gpt4all:<p><a href="https://github.com/nomic-ai/gpt4all">https://github.com/nomic-ai/gpt4all</a>
OpenAI trains with my chat if I enable history. I absolutely need history so that I can use it as an intelligent diary or note taker. I absolutely don’t want it to train with my data.<p>On the other hand, they dont train with API usage. So something like this is very interesting.<p>Question: does LibreChat support importing OpenAI history?
very cool! at first it looks like a lot to avoid spending $20/month but I realize I am already using LM Studio, which has a language model browser in it and lets you hot swap them in, in a nice single click GUI. Most notably, it also lets you switch to server mode and accepts and serves requests in the OpenAI REST format, across my local network or simply my main machine on various ports.<p>so some privacy and multimodal is great. glad the pieces are getting more user friendly to casually use