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.
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
Integrate DeepSeek models with Azure AI Foundry.
Utilize the DeepSeek-R1 reasoning model for complex tasks.
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
Chunks, embeds, and indexes documents for semantic retrieval.
Condenses long documents or threads into key takeaways.
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.