Evaluations

​

What are Evaluations?

1. Context Relevance: Evaluates how relevant the retrieved context is to the question specified.
2. Factual Accuracy: Evaluates whether the response generated is factually correct and grounded by the provided context.
3. Response Completeness: Evaluates whether the response has answered all the aspects of the question specified

​

How does it work?

1

Create a new Project

Click on Create New Project from Home

2

Enter Project Information

• Project name: Create a name for your project
• Dataset name: Create a name for your dataset
• Choose File: Upload your Dataset Sample Dataset:
  Copy

  {"question":"","response":"","context":""}
  {"question":"","response":"","context":""}
  

• Select Evaluation LLM: Select an LLM to run evaluations
• Use same info to run Evaluations: No (since we are running evaluations here) If you wish to run experiments, you can select Yes and follow the steps here

3

Select Evaluations to Run

4

View Evaluations

You can see all the evaluations ran using UpTrain

You can also see individual logs