confident-ai/deepeval

Evaluation Dataset Generation

Open

#530 opened on Feb 26, 2024

View on GitHub
 (2 comments) (0 reactions) (1 assignee)Python (1,677 forks)auto 404
enhancementhelp wanted

Repository metrics

Stars
 (16,939 stars)
PR merge metrics
 (PR metrics pending)

Description

Evaluation dataset generation is coming to deepeval by end of this week. For this feature, we're looking at the following:

  1. Allow users to generate test cases based on their knowledge base
  2. Allow users to choose how to chunk their knowledge base
  3. Allow users to specify how many test cases to generate
  4. Allow users to complicate test cases to make them more realistic (https://arxiv.org/pdf/2304.12244.pdf, https://mlabonne.github.io/blog/notes/Large%20Language%20Models/phi1.htm)

Feedback, suggestions, and contributions for any of the points above are welcomed 😊

Contributor guide

Research direction
Review the linked papers on test case generation and complication, explore existing chunking strategies, and understand the deepeval codebase for dataset generation.
Tech stack
python
Domain
aimachine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonLLM basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60