RactoGateway

Getting Started

Installation
Quick Start

User Guide

RactoGateway — Complete User Guide
LLM Discovery Guide
Prompt Engine
Developer Kits
Ollama — Local Model Inference
HuggingFace — Cloud and Local Inference
Streaming
Tool Calling
Embeddings
Chain of Thoughts
Native Thinking
Fine-Tuning
RAG — Retrieval-Augmented Generation
Prebuilt Pipelines
Batch Processing
Caching
Cost-Aware Routing
Token Truncation
MCP — Model Context Protocol
Redis
Celery
Kafka

API Reference

API Reference

RactoGateway

Streaming
View page source

Streaming

All developer kits support token-by-token streaming via sync and async generators.

Previous Next

© Copyright 2026, Ved Prakash Pathak.

Built with Sphinx using a theme provided by Read the Docs.