Helvia.ai

RAG Cache

Blog

Helvia RAG-Cache Documentation

API Reference

Dashboard

Support

RAG-Buddy API endpoint for the Text-Classification use case.

Text Classification

Content

Role

Tool Calls

ChatCompletionMessage

Type

ChatCompletionMessageToolCall

Finish Reason

Index

Choice

Completion Tokens

Prompt Tokens

Total Tokens

CompletionUsage

Arguments

Name

Function

FunctionCall

Location

Message

Error Type

ValidationError

TcRequest

HTTPBearer

ChatCompletion

HTTPValidationError

Welcome to the home of the RAG-Buddy documentation. Jump directly to the section you need or use the search bar to find what you are looking for.

RAG-Buddy Documentation

What services does RAG-Buddy provide and how can they help you improve your RAG setup?

Introduction to RAG-Buddy

RAG-Buddy provides services to enhance the capabilities of the Retrieval Augmented Generation with Citation (RAG+C) system. This section provides an overview of Retrieval Augmented Generation with Citation (RAG+C), its purpose, and its mechanics.

RAG with Citation

This section provides an overview of Text Classification, its purpose, and its mechanics.

Add RAG-Buddy to your RAG pipeline efficiently in five minutes or less.

RAG-Buddy Quickstart

Create your RAG-Buddy account and set up a project.

Setting Up

This section outlines the steps and best practices for integrating and utilizing RAG-Buddy within your RAG pipeline. The first step is to choose the right endpoint.

Endpoint Selection

The Proxy Endpoint serves as a straightforward way to enhance your existing LLM setup with RAG-Buddy capabilities.

Proxy Endpoint

This section guides you through integrating RAG-Buddy into your LLM pipeline using the REST API Endpoint, detailing the steps for a more customized and controlled implementation.

REST API Endpoints

RAG-Buddy integration and client code examples

Code examples

FAQs

RAG-Buddy API Endpoints reference and playground

Introduction

RAG-Buddy API endpoint for the RAG-Citation use case.

Rag Citation

RAG-Buddy Proxy endpoint to transparently read and write to cache and forward requests to the LLM API.

API Documentation

API Endpoints

Text Classification

Authorizations

Headers

Path Parameters

Body

Response