TensorZero Evaluations Overview

TensorZero offers two types of evaluations: Inference Evaluations focus on evaluating the performance of a TensorZero variant (i.e. a choice of prompt, model, inference strategy, etc.) on a given dataset. Workflow Evaluations focus on evaluating complex workflows that might include multiple TensorZero inference calls, arbitrary application logic, and more. As a vague analogy, inference evaluations are like unit tests for individual inference calls, and workflow evaluations are like integration tests for complex workflows.

Tutorial: Inference Evaluations

Tutorial: Workflow Evaluations

Supervised Fine-Tuning Tutorial

Introduction

Gateway

Observability

Optimization

Evaluations

Experimentation

Deployment

Operations

TensorZero Evaluations Overview

Tutorial: Inference Evaluations

Tutorial: Workflow Evaluations