Prompt Chain

Route AI Requests via Helicone Gateway

Helicone is a promptfoo example demonstrating how to route AI requests through a self-hosted Helicone AI Gateway instance for unified provider access.

Works with githubhelicone

87
Spark score
out of 100
Updated 3 months ago
Version 1.0.0

Add to Favorites

Why it matters

Integrate your AI requests with a self-hosted Helicone AI Gateway for unified provider access and streamlined management.

Outcomes

What it gets done

01

Configure promptfoo to use the Helicone AI Gateway provider.

02

Route AI requests through your self-hosted Helicone instance.

03

Achieve unified access to multiple AI providers via Helicone.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/pfoo-helicone | bash

Capabilities

What this chain does

Extract

Pulls structured data fields from unstructured text.

Summarize

Condenses long documents or threads into key takeaways.

Classify

Labels or categorizes text, files, or data points.

Overview

Helicone

What it does

This is a promptfoo configuration example that demonstrates integration with the Helicone AI Gateway provider. It shows how to set up request routing through a self-hosted Helicone AI Gateway instance, enabling unified access to multiple AI providers within the promptfoo evaluation framework.

How it connects

Use this example when you want to evaluate prompts using promptfoo while routing all AI provider requests through your own self-hosted Helicone AI Gateway. It's ideal for teams that need centralized provider access and want to maintain control over their AI infrastructure during prompt testing and evaluation.

Source README

This example demonstrates how to use the Helicone AI Gateway provider in promptfoo to route requests through a self-hosted Helicone AI Gateway instance for unified provider access.

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.