Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add Evaluations area with Weave as a supported eval flow #917

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Conversation

johndmulhausen
Copy link
Contributor

@johndmulhausen johndmulhausen commented Nov 7, 2024

In several areas where the W&B ecosystem is described, the content is reflecting the old days when we were a one-product company and didn't have Weave to offer as part of the evaluation story. This PR is integrating Weave into the ecosystem more and highlighting our Evaluation options (Tables, Weave) with a new high-level section.

Resolves DOCS-1024

@johndmulhausen johndmulhausen requested a review from a team as a code owner November 7, 2024 21:59
Copy link

cloudflare-workers-and-pages bot commented Nov 7, 2024

Deploying docodile with  Cloudflare Pages  Cloudflare Pages

Latest commit: 3e3f4da
Status: ✅  Deploy successful!
Preview URL: https://5853e7dc.docodile.pages.dev
Branch Preview URL: https://weave-evaluations.docodile.pages.dev

View logs

docs/guides/evaluations/evaluate-models-weave.md Outdated Show resolved Hide resolved
docs/guides/evaluations/evaluate-models-weave.md Outdated Show resolved Hide resolved
docs/guides/evaluations/evaluate-models-weave.md Outdated Show resolved Hide resolved
docs/guides/evaluations/evaluate-models-weave.md Outdated Show resolved Hide resolved
docs/guides/evaluations/evaluate-models-weave.md Outdated Show resolved Hide resolved

First, create a W&B account at https://wandb.ai and copy your API key from https://wandb.ai/authorize.

Then, you can follow along in the below Colab notebook that demonstrates Weave evaluating an LLM (in this case, OpenAI, for which you will also need [an API key](https://platform.openai.com/docs/quickstart/step-2-setup-your-api-key)).
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ [vale] reported by reviewdog 🐶
[Google.Will] Avoid using 'will'.


## Use Weave to evaluate models in production

This [tutorial on how to build an evaluation pipeline with Weave](https://weave-docs.wandb.ai/tutorial-eval/) demonstrates how multiple versions of an application that uses a model is evolving using the `weave.Evaluation` function, which assess a Model's performance on a set of examples using a list of specified scoring functions or `weave.scorer.Scorer` classes, producing dashboards with advanced breakdowns of the model's performance.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ [vale] reported by reviewdog 🐶
[Google.WordList] Use 'app' instead of 'application'.

Copy link
Contributor

Summary

Status Count
🔍 Total 34
✅ Successful 16
⏳ Timeouts 0
🔀 Redirected 0
👻 Excluded 17
❓ Unknown 0
🚫 Errors 1

Errors per input

Errors in docs/guides/evaluations/evaluate-models-weave.md

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants