What is a Version?

A version in Galtea represents a specific iteration of a product. Versions allow you to track changes to your product over time and compare different implementations against the same tests.

You can create, view and manage your versions on the Galtea dashboard or programmatically using the Galtea SDK.

Comparing Versions

One of the key benefits of tracking versions in Galtea is the ability to compare different implementations of your product. This allows you to:

  • Measure improvements between versions
  • Identify regressions in newer versions
  • Compare different model providers or approaches
  • Make data-driven decisions about which version to deploy

Run a Comparison Evaluation

Learn how to compare different versions using the same test

SDK Integration

The Galtea SDK allows you to create, view, and manage versions programmatically. This is particularly useful for organizations that want to automate their versioning process or integrate it into their CI/CD pipeline.

Version Properties

Version Name
Text
required

The name of the version. Example: “v1.2.0” or “GPT-4 Implementation”

Version Description
Text

A description of the version, typically highlighting what makes it different from other versions. Example: “Improved summarization algorithm with better fact retention”

Model
Model
required

The AI Model used by this version. This is used for cost tracking and associating the version with a specific LLM’s pricing and tokenization characteristics.

This is used to calculate the cost of the inference for the version during evaluation tasks.

System Prompt
Text

The system prompt used for this version. Example: “You are an expert legal document summarizer. Provide concise summaries that capture all key legal points.”

Dataset URI
Text

The URI of the dataset used to train or fine-tune this version. Example: “s3://company-datasets/legal-documents-v2/”

Dataset Description
Text

A description of the dataset used in the version. Example: “Collection of 10,000 legal contracts and agreements with expert-created summaries”

Guardrails
Text

The guardrails applied to the version, separated by commas. Example: “content filtering, citation checking, legal compliance”

Endpoint
Text

The endpoint connection for the version. Example: “https://api.company.com/summarizer/v2