streaming-architecture

Community

Unified streaming for multi-provider SSE.

Authormajiayu000
Version1.0.0
Installs0

System Documentation

What problem does it solve?

LiteLLM-RS Streaming Architecture provides a unified, provider-agnostic streaming pipeline that normalizes diverse SSE formats from 66+ providers and outputs an OpenAI-compatible chat stream in real time.

Core Features & Use Cases

  • Unified SSE parsing and buffering with a provider-agnostic Transformer system.
  • Provider-specific transformations to normalize data into OpenAI-compatible chunks.
  • Real-time, streaming chat outputs with consistent formatting and error handling.
  • Use Case: Route SSE from multiple providers (OpenAI, Anthropic, Google, etc.) and present a single OpenAI-like stream to clients.

Quick Start

Use the streaming architecture for building a multi-provider streaming gateway that produces OpenAI-compatible chat chunks from provider SSE streams and supports backpressure and error handling.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: streaming-architecture
Download link: https://github.com/majiayu000/litellm-rs/archive/main.zip#streaming-architecture

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.