A high-throughput and memory-efficient inference and serving engine for LLMs

An extremely fast Python package and project manager, written in Rust.

Implement a RAG step-by-step

The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching of inference workloads.

Examples and guides for using the OpenAI API

expose yourself

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Stable Diffusion web UI

Represent, send, store and search multimodal data

⚡ A fast embedded library for approximate nearest neighbor search

🌊 A Human-in-the-Loop workflow for creating HD images from text

Encoder that embeds documents using either the CLIP vision encoder or the CLIP text encoder, depending on the content type of the document.

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

☁️ Build multimodal AI applications with cloud-native stack