-
text-generation-webui
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
primevue-chatbot
A simple chatbot using primevue for the components, nuxt3 for management, and Open AI API
-
LibreChat
Enhanced ChatGPT Clone: Features OpenAI, Assistants API, Azure, Groq, GPT-4 Vision, Mistral, Bing, Anthropic, OpenRouter, Vertex AI, Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
No training yourself needed. Free, but don't expect gpt4 quality, especially for coding or factual stuff, but for rpg/chat stuff is pretty awesome (if you have the video card for it, to run a 30-33b model), although some good 14b models exist too, like WizardLM... you use pre trained models via huggingface. Start here: https://github.com/oobabooga/text-generation-webui
If all this sounds like too much trouble, you're on windows, or you want something that's not super specialized, you can definitely give Wizard-30b-v1.0 a try running via llama.cpp. If you don't have 32 GB of RAM, vicuna 1.1 13B is decent, too.
You inspired me! This morning I decided to take on a quick little project and built a Vue based chatbot. Repo Here
Then, you'll need Starcoder cpp (NOT LLaMA cpp)
koboldcpp is the easiest, locally hosted LLM application I've found.