Llumo AI Docs

Getting started with LLUMO AI

Reduce LLM cost and gain 360° insights of your LLM outputs.

Quickstart

OptiSave

Experiment

Observe

Optimize

Support

Welcome to LLumo AI’s Support Page

Save RAG cost

Save RAG cost using Prompt Compression

Prompt Compression API

Setup prompt compression API

Save cost in Langchain pipeline using LLUMO compressor API

Langchain

LLUMO Compressor API with Langchain

Save cost in OpenAI API calls using LLUMO compressor API

OpenAI

LLUMO Compressor API with OpenAI

Save cost in Google Vertex pipeline using LLUMO compressor API

Google Vertex

LLUMO Compressor API with Google Vertex

Save cost in Llama Index pipeline using LLUMO compressor API

Llama Index

LLUMO Compressor API with Llama Index

Compress Prompt API

Use LLUMO AI's proprietary technology to evaluate LLM output and gain insights.

Prompt Evaluation API

Setup prompt evaluation API

Use LLUMO AI’s proprietary technology to evaluate output from OpenAI GPT models.

Setup Prompt Evaluation API with OpenAI output

Use LLUMO AI’s proprietary technology to evaluate output from Google Gemini models.

Vertex AI

Setup Prompt Evaluation API with Vertex output

Evaluate on 3-4 metrics

Evaluating a Bulk Dataset using 3-4 metrics

Integrate API in your codebase

How to integrate LLUMO API and learn evaluation in your codebase?

Run Evaluation in Production

How to Run Evaluation in Production?

Setup Prompt Evaluation API

Create Eval Analytics API

Community

Blog

Getting Started

Cost Saving

LLM Evaluation

Developer tools

Sign-up

Compress Prompt

Guide to Prompt Compress with LLUMO AI

Save cost in LLM calls with OpenAI using LLUMO compressor API

Production

Add LLUMO Compressor API to code and deploy

Customize Evaluation

How to customize Evals for your use case?

Create Custom Evals

How to create a custom Eval from scratch?

Setup LLUMO

Troubleshoot

Sample Project

Compression openai