FastIQ is an innovative platform designed to streamline the integration and utilization of multiple API providers for large language models (LLMs). Our platform serves as a hub for developers, researchers, and businesses to access a diverse range of AI models from leading providers such as Groq, OpenAI, Anyscale, and TogetherAI, among others.

SDK for Anyscale Endpoint that makes it easy and cheap to use LLama 2

Scripts and documents related to the Vectara RAG hacakthon

This custom component for Home Assistant allows you to generate text responses using GigaChain LLM framework (like GigaChat, YandexGPT, ChatGPT, Anyscale).

Interact with any LLM service

Vercel AI chatbot with Anyscale endpoints

Scalable NLP model fine-tuning and batch inference with Ray and Anyscale

Artifacts intended to support the Ray Developer Community: SIGs, RFC overviews, and governance. We're very glad you're here! ✨

A simple discord bot that listens to voice channel and generates a transcript, then assigns tasks and summarises the conversation

Ray and Anyscale for UC Berkeley AI Hackathon!

langchain-streamlit demo with streaming llm, memory, and langsmith feedback

Interact with an LLM service

Deploy and Scale LLM-based applications

LLM Based NLP Library.

End-to-end platform for building voice first multimodal agents

A comprehensive guide to building RAG-based LLM applications for production.