# Llumo AI Docs

## Docs

- [Compress Prompt API](https://docs.llumo.ai/cost-saving/api-reference/compress-prompt-api.md): Compresses a prompt for query
- [Setup prompt compression API](https://docs.llumo.ai/cost-saving/how-to-docs/compress-first-prompt.md): Start cutting AI cost in just 10 minutes
- [LLUMO Compressor API with Langchain](https://docs.llumo.ai/cost-saving/how-to-docs/llumo-compressor-langchain.md): Save cost in Langchain pipeline using LLUMO compressor API
- [LLUMO Compressor API with Llama Index](https://docs.llumo.ai/cost-saving/how-to-docs/llumo-compressor-llama.md): Save cost in Llama Index pipeline using LLUMO compressor API
- [LLUMO Compressor API with OpenAI](https://docs.llumo.ai/cost-saving/how-to-docs/llumo-compressor-openai.md): Save cost in OpenAI API calls using LLUMO compressor API
- [LLUMO Compressor API with Google Vertex](https://docs.llumo.ai/cost-saving/how-to-docs/llumo-compressor-vertex.md): Save cost in Google Vertex pipeline using LLUMO compressor API
- [Setup prompt compression API](https://docs.llumo.ai/cost-saving/setup/api.md): Start cutting AI cost in just 2 minutes
- [Compression openai](https://docs.llumo.ai/developer-tools/sample-projects/compression-openai.md)
- [Api](https://docs.llumo.ai/developer-tools/setup-llumo/setup-cost-saving/api.md)
- [Api](https://docs.llumo.ai/developer-tools/setup-llumo/setup-evaluation/api.md)
- [Prompt compression api](https://docs.llumo.ai/developer-tools/troubleshoot/prompt-compression-api.md)
- [Experiment](https://docs.llumo.ai/experiment.md)
- [Getting started with LLUMO AI](https://docs.llumo.ai/getting-started-with-llumo.md)
- [Production](https://docs.llumo.ai/how-to-docs/annotate-human-feedback/production.md)
- [Testing](https://docs.llumo.ai/how-to-docs/annotate-human-feedback/testing.md)
- [Guide to Prompt Compress with LLUMO AI](https://docs.llumo.ai/how-to-docs/compress-prompts/compress-prompt-doc.md): Start cutting AI cost in just 2 minutes
- [Add LLUMO Compressor API to code and deploy](https://docs.llumo.ai/how-to-docs/compress-prompts/production.md): Save cost in LLM calls with OpenAI using LLUMO compressor API
- [Connect Your App to LLUMO AI in Minutes](https://docs.llumo.ai/how-to-docs/evaluate-llms/connect-python-sdk.md)
- [How to create a custom Eval from scratch?](https://docs.llumo.ai/how-to-docs/evaluate-llms/create-custom-evals.md): Start getting insights in just 2 minutes
- [How to customize Evals for your use case?](https://docs.llumo.ai/how-to-docs/evaluate-llms/customize-evaluations.md): Start getting insights in just 2 minutes
- [Production](https://docs.llumo.ai/how-to-docs/evaluate-llms/production.md)
- [Save RAG cost using Prompt Compression](https://docs.llumo.ai/how-to-docs/save-rag-cost.md): Start cutting AI cost in just 2 minutes
- [Create Eval Analytics API](https://docs.llumo.ai/llm-evaluation/api-reference/create-eval-analytics-api.md): Creates evaluation analytics
- [Evaluating a Bulk Dataset using 3-4 metrics](https://docs.llumo.ai/llm-evaluation/how-to-docs/evaluate-dataset-multiple-metric.md)
- [Setup prompt evaluation API](https://docs.llumo.ai/llm-evaluation/how-to-docs/evaluate-first-prompt.md): Use LLUMO AI's proprietary technology to evaluate LLM output and gain insights.
- [Setup Prompt Evaluation API with OpenAI output](https://docs.llumo.ai/llm-evaluation/how-to-docs/evaluate-openAI.md): Use LLUMO AI’s proprietary technology to evaluate output from OpenAI GPT models.
- [Setup Prompt Evaluation API with Vertex output](https://docs.llumo.ai/llm-evaluation/how-to-docs/evaluate-vertex.md): Use LLUMO AI’s proprietary technology to evaluate output from Google Gemini models.
- [How to integrate LLUMO API and learn evaluation in your codebase?](https://docs.llumo.ai/llm-evaluation/how-to-docs/integrate-api-code.md)
- [How to Run Evaluation in Production?](https://docs.llumo.ai/llm-evaluation/how-to-docs/run-eval-prod.md)
- [Setup Prompt Evaluation API](https://docs.llumo.ai/llm-evaluation/setup/api.md): Use LLUMO AI's proprietary technology to evaluate LLM output and gain insights.
- [Observe](https://docs.llumo.ai/observe.md)
- [Optimize](https://docs.llumo.ai/optimise.md)
- [OptiSave](https://docs.llumo.ai/optisave.md)
- [Quickstart](https://docs.llumo.ai/quickstart.md): Reduce LLM cost and gain 360° insights of your LLM outputs.
- [Setup prompt compression API](https://docs.llumo.ai/setup-llumo/setup-cost-saving/api.md): Start cutting AI cost in just 2 minutes
- [Setup Prompt Evaluation API](https://docs.llumo.ai/setup-llumo/setup-evaluation/api.md): Use LLUMO AI's proprietary technology to evaluate LLM output and gain insights.
- [Welcome to LLumo AI’s Support Page](https://docs.llumo.ai/support.md)

## OpenAPI Specs

- [package-lock](https://docs.llumo.ai/package-lock.json)
- [future-mint](https://docs.llumo.ai/future-mint.json)
- [openapi](https://docs.llumo.ai/openapi.json)

## Optional

- [Community](https://whatsapp.com/channel/0029VaGe7T9AYlUOZGWlgi1k/114?utm_source=docs-llumo&utm_medium=user-doc&utm_campaign=doc-redirect)
- [Blog](https://www.llumo.ai/blog)