Prompt Chain

Evaluate DeepSeek models on Azure AI Foundry

Example configuration demonstrating how to test DeepSeek models, including DeepSeek-R1 reasoning model, on Azure AI Foundry using promptfoo for evaluation.

Works with azuregithub

78
Spark score
out of 100
Updated 3 months ago
Version 1.0.0
Models

Add to Favorites

Why it matters

Leverage the power of DeepSeek models, including the DeepSeek-R1 reasoning model, within Azure AI Foundry. This asset facilitates the evaluation and integration of these advanced models for various AI tasks.

Outcomes

What it gets done

01

Integrate DeepSeek models with Azure AI Foundry.

02

Utilize the DeepSeek-R1 reasoning model for complex tasks.

03

Evaluate model performance using promptfoo.

Install

Add it to your toolbox

Run in your project directory:

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

Capabilities

What this chain does

RAG index

Chunks, embeds, and indexes documents for semantic retrieval.

Summarize

Condenses long documents or threads into key takeaways.

Classify

Labels or categorizes text, files, or data points.

Overview

Deepseek

What it does

This is a configuration example that shows how to use DeepSeek models on Azure AI Foundry with promptfoo. It demonstrates the setup required to test DeepSeek models, including the DeepSeek-R1 reasoning model, through promptfoo's evaluation framework when these models are deployed on Azure's AI platform.

How it connects

Use this example when you need to set up testing and evaluation workflows for DeepSeek models that are hosted on Azure AI Foundry. It is particularly relevant when you want to leverage promptfoo's testing capabilities to assess DeepSeek-R1 or other DeepSeek models in an Azure environment.

Source README

This example demonstrates how to use DeepSeek models on Azure AI Foundry with promptfoo, including the DeepSeek-R1 reasoning model.

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.