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

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

LLM Based NLP Library.

Deploy and Scale LLM-based applications

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

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

Ray and Anyscale for UC Berkeley AI Hackathon!

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

Interact with any LLM service

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

Vercel AI chatbot with Anyscale endpoints

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

An Apache Airflow provider for seamless integration with Anyscale.

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

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.

Pickup Line Generator is a fun and creative web application that helps you craft the perfect pickup line for your crush. Simply input a description of your crush and choose a style, and our AI-powered generator will create unique and creative pickup lines tailored to your preferences.

Scripts and documents related to the Vectara RAG hacakthon