docs out of date

Open Beginner friendly
#929 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
68/100
Issue type
Documentation
Clarity
Clearly specified
Activity status
Stale
Tech stack
python
Domain
documentation

Research direction

Start with docs/custom-eval.md and compare its sample against the current evals code and commit 64fb72a9a83b5d14dc765dbd8722f2bbbab5ef76. Run the documented example with Python 3.10 to verify it no longer references check_sampled_text and that its sample structure matches the current format. Done means the documentation runs successfully and reflects the current API.

Written by the indexing model from the issue text.

Description

bug
Describe the bug

cods at https://github.com/openai/evals/blob/main/docs/custom-eval.md are out of date:

  1. the sample in the loop is an array so instead of
                   {"role": "system", "content": sample["problem"], "name": "example_user"},
                   {"role": "system", "content": sample["answer"], "name": "example_assistant"},
               ]
           else:
               prompt += [{"role": "user", "content": sample["problem"]}]```

the code should be:

                prompt += [
                    {"role": "system", "content": sample[0]["content"], "name": "example_user"},
                    {"role": "system", "content": sample[1]["content"], "name": "example_assistant"},
                ]
            else:
                prompt += [{"role": "user", "content": sample[0]["content"]}]
  1. the check_sampled_text function doesn't exist after https://github.com/openai/evals/commit/64fb72a9a83b5d14dc765dbd8722f2bbbab5ef76
To Reproduce
  1. try running code in https://github.com/openai/evals/blob/main/docs/custom-eval.md
Code snippets

No response

OS

macOs

Python version

Python 3.10

Library version

1.0.3.post1

Dominant language
Python
Stars
19.5k
Forks
3.1k
PR merge metrics
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from openai/evals

All issues in openai/evals

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.